Token | her |
Token ID | 607 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
destination | +0.015 |
aman | +0.014 |
isn | +0.014 |
heit | +0.014 |
ement | +0.013 |
Neg logit contributions | |
blown | -0.009 |
Blood | -0.009 |
blood | -0.009 |
bitten | -0.009 |
spilled | -0.008 |
Token | doll |
Token ID | 3654 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
aman | +0.012 |
mmm | +0.011 |
hew | +0.011 |
heit | +0.011 |
isn | +0.011 |
Neg logit contributions | |
blood | -0.007 |
blown | -0.007 |
bitten | -0.006 |
Blood | -0.006 |
cat | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
heit | +0.036 |
aman | +0.034 |
isn | +0.033 |
destination | +0.033 |
hew | +0.033 |
Neg logit contributions | |
blown | -0.023 |
blood | -0.022 |
Blood | -0.021 |
bitten | -0.021 |
spilled | -0.020 |
Token | watched |
Token ID | 7342 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
destination | +0.008 |
aman | +0.008 |
isn | +0.007 |
heit | +0.007 |
ement | +0.007 |
Neg logit contributions | |
blown | -0.005 |
blood | -0.005 |
Blood | -0.005 |
bitten | -0.005 |
spilled | -0.005 |
Token | in |
Token ID | 287 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
destination | +0.046 |
heit | +0.045 |
aman | +0.045 |
isn | +0.044 |
hew | +0.043 |
Neg logit contributions | |
blown | -0.030 |
blood | -0.030 |
Blood | -0.029 |
bitten | -0.028 |
spilled | -0.025 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.26e+00 |
Pos logit contributions | |
heit | +0.045 |
aman | +0.043 |
hew | +0.043 |
mmm | +0.041 |
isn | +0.041 |
Neg logit contributions | |
blood | -0.064 |
blown | -0.061 |
bitten | -0.059 |
Blood | -0.058 |
spilled | -0.054 |
Token | ement |
Token ID | 972 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
destination | +0.061 |
heit | +0.058 |
olog | +0.058 |
bek | +0.055 |
isn | +0.055 |
Neg logit contributions | |
blood | -0.283 |
Blood | -0.267 |
blown | -0.265 |
bitten | -0.259 |
agged | -0.258 |
Token | as |
Token ID | 355 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
destination | +0.038 |
aman | +0.037 |
heit | +0.037 |
isn | +0.036 |
ement | +0.034 |
Neg logit contributions | |
blown | -0.032 |
blood | -0.032 |
Blood | -0.031 |
bitten | -0.031 |
spilled | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
blood | +0.028 |
blown | +0.027 |
Blood | +0.026 |
bitten | +0.025 |
spilled | +0.023 |
Neg logit contributions | |
destination | -0.048 |
aman | -0.048 |
heit | -0.048 |
isn | -0.046 |
hew | -0.046 |
Token | slowly |
Token ID | 6364 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
blown | +0.007 |
blood | +0.006 |
Blood | +0.006 |
bitten | +0.006 |
spilled | +0.005 |
Neg logit contributions | |
destination | -0.013 |
aman | -0.012 |
isn | -0.012 |
heit | -0.012 |
ement | -0.012 |
Token | flew |
Token ID | 13112 |
Feature activation | +7.74e-02 |
Pos logit contributions | |
Blood | +0.028 |
blood | +0.027 |
blown | +0.025 |
bitten | +0.025 |
spilled | +0.021 |
Neg logit contributions | |
destination | -0.044 |
isn | -0.042 |
aman | -0.042 |
heit | -0.041 |
ement | -0.041 |
Token | but |
Token ID | 475 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
blood | +0.021 |
bitten | +0.020 |
blown | +0.020 |
spilled | +0.019 |
Blood | +0.017 |
Neg logit contributions | |
heit | -0.045 |
aman | -0.043 |
destination | -0.042 |
bek | -0.041 |
hew | -0.040 |
Token | they |
Token ID | 484 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
aman | +0.051 |
destination | +0.049 |
heit | +0.049 |
hew | +0.048 |
ement | +0.047 |
Neg logit contributions | |
blown | -0.029 |
blood | -0.029 |
Blood | -0.027 |
bitten | -0.027 |
spilled | -0.025 |
Token | ran |
Token ID | 4966 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
destination | +0.022 |
aman | +0.021 |
heit | +0.021 |
isn | +0.021 |
ement | +0.020 |
Neg logit contributions | |
blown | -0.018 |
blood | -0.018 |
Blood | -0.017 |
bitten | -0.017 |
spilled | -0.016 |
Token | back |
Token ID | 736 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
blown | +0.007 |
blood | +0.007 |
bitten | +0.007 |
Blood | +0.006 |
spilled | +0.006 |
Neg logit contributions | |
aman | -0.010 |
heit | -0.010 |
isn | -0.010 |
destination | -0.010 |
ement | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
blown | +0.006 |
blood | +0.006 |
bitten | +0.006 |
Blood | +0.006 |
spilled | +0.005 |
Neg logit contributions | |
heit | -0.011 |
aman | -0.011 |
destination | -0.011 |
isn | -0.011 |
ement | -0.011 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.22e+00 |
Pos logit contributions | |
heit | +0.056 |
aman | +0.055 |
destination | +0.055 |
isn | +0.054 |
hew | +0.054 |
Neg logit contributions | |
blood | -0.034 |
blown | -0.033 |
bitten | -0.032 |
Blood | -0.031 |
spilled | -0.027 |
Token | ement |
Token ID | 972 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
destination | +0.053 |
heit | +0.050 |
isn | +0.048 |
olog | +0.047 |
aman | +0.041 |
Neg logit contributions | |
blood | -0.291 |
Blood | -0.279 |
blown | -0.279 |
bitten | -0.273 |
agged | -0.268 |
Token | ! |
Token ID | 0 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
destination | +0.051 |
heit | +0.050 |
aman | +0.050 |
isn | +0.049 |
hew | +0.046 |
Neg logit contributions | |
blown | -0.037 |
blood | -0.036 |
Blood | -0.036 |
bitten | -0.035 |
spilled | -0.031 |
Token | The |
Token ID | 383 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
destination | +0.015 |
heit | +0.014 |
aman | +0.014 |
isn | +0.014 |
ement | +0.014 |
Neg logit contributions | |
Blood | -0.008 |
blown | -0.008 |
blood | -0.007 |
bitten | -0.007 |
spilled | -0.006 |
Token | post |
Token ID | 1281 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
blown | +0.024 |
blood | +0.023 |
Blood | +0.023 |
bitten | +0.023 |
spilled | +0.021 |
Neg logit contributions | |
destination | -0.022 |
aman | -0.022 |
isn | -0.021 |
heit | -0.021 |
ement | -0.020 |
Token | had |
Token ID | 550 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
blown | +0.011 |
blood | +0.011 |
Blood | +0.010 |
bitten | +0.010 |
spilled | +0.009 |
Neg logit contributions | |
destination | -0.011 |
heit | -0.011 |
aman | -0.011 |
isn | -0.010 |
ement | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
heit | +0.020 |
destination | +0.019 |
aman | +0.019 |
hew | +0.018 |
isn | +0.018 |
Neg logit contributions | |
blood | -0.010 |
blown | -0.010 |
Blood | -0.010 |
bitten | -0.009 |
spilled | -0.009 |
Token | pointed |
Token ID | 6235 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
destination | +0.035 |
aman | +0.034 |
heit | +0.033 |
isn | +0.033 |
ement | +0.033 |
Neg logit contributions | |
blown | -0.023 |
blood | -0.022 |
Blood | -0.021 |
bitten | -0.021 |
spilled | -0.019 |
Token | at |
Token ID | 379 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
heit | +0.096 |
aman | +0.096 |
mmm | +0.096 |
hew | +0.095 |
destination | +0.094 |
Neg logit contributions | |
blood | -0.039 |
bitten | -0.036 |
blown | -0.036 |
Blood | -0.032 |
ked | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
destination | +0.060 |
aman | +0.059 |
heit | +0.058 |
isn | +0.057 |
hew | +0.056 |
Neg logit contributions | |
blood | -0.026 |
blown | -0.026 |
bitten | -0.024 |
Blood | -0.024 |
spilled | -0.021 |
Token | in |
Token ID | 287 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
heit | +0.020 |
aman | +0.020 |
hew | +0.018 |
destination | +0.018 |
bek | +0.018 |
Neg logit contributions | |
blown | -0.014 |
blood | -0.013 |
bitten | -0.013 |
Blood | -0.013 |
spilled | -0.012 |
Token | amaz |
Token ID | 40642 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
destination | +0.026 |
heit | +0.026 |
aman | +0.026 |
isn | +0.026 |
hew | +0.025 |
Neg logit contributions | |
blood | -0.022 |
blown | -0.022 |
bitten | -0.021 |
Blood | -0.021 |
spilled | -0.018 |
Token | ement |
Token ID | 972 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
destination | +0.056 |
heit | +0.053 |
olog | +0.048 |
isn | +0.047 |
hew | +0.045 |
Neg logit contributions | |
blood | -0.281 |
Blood | -0.269 |
blown | -0.269 |
bitten | -0.263 |
agged | -0.254 |
Token | . |
Token ID | 13 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
destination | +0.040 |
heit | +0.040 |
aman | +0.039 |
isn | +0.039 |
hew | +0.037 |
Neg logit contributions | |
blown | -0.033 |
blood | -0.033 |
Blood | -0.032 |
bitten | -0.031 |
spilled | -0.029 |
Token | The |
Token ID | 383 |
Feature activation | -9.52e-01 |
Pos logit contributions | |
blown | +0.004 |
blood | +0.004 |
Blood | +0.004 |
bitten | +0.004 |
spilled | +0.003 |
Neg logit contributions | |
destination | -0.006 |
aman | -0.006 |
heit | -0.006 |
isn | -0.006 |
ement | -0.005 |
Token | bird |
Token ID | 6512 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
blown | +0.017 |
Blood | +0.017 |
bitten | +0.016 |
blood | +0.016 |
elt | +0.013 |
Neg logit contributions | |
destination | -0.029 |
isn | -0.028 |
aman | -0.028 |
ement | -0.027 |
heit | -0.027 |
Token | stopped |
Token ID | 5025 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
blown | +0.014 |
blood | +0.013 |
bitten | +0.013 |
Blood | +0.013 |
spilled | +0.011 |
Neg logit contributions | |
destination | -0.019 |
aman | -0.019 |
heit | -0.018 |
isn | -0.018 |
ement | -0.017 |
Token | just |
Token ID | 655 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
destination | +0.024 |
heit | +0.023 |
aman | +0.023 |
isn | +0.022 |
ement | +0.022 |
Neg logit contributions | |
blown | -0.019 |
blood | -0.019 |
bitten | -0.018 |
Blood | -0.018 |
spilled | -0.018 |
Token | stared |
Token ID | 18484 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
destination | +0.019 |
aman | +0.018 |
heit | +0.018 |
isn | +0.017 |
ement | +0.017 |
Neg logit contributions | |
blown | -0.014 |
blood | -0.013 |
Blood | -0.013 |
bitten | -0.013 |
spilled | -0.012 |
Token | at |
Token ID | 379 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
heit | +0.044 |
aman | +0.042 |
destination | +0.041 |
hew | +0.040 |
isn | +0.040 |
Neg logit contributions | |
blood | -0.033 |
blown | -0.033 |
bitten | -0.031 |
Blood | -0.031 |
elt | -0.029 |
Token | him |
Token ID | 683 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
destination | +0.067 |
heit | +0.066 |
aman | +0.065 |
isn | +0.064 |
hew | +0.063 |
Neg logit contributions | |
blood | -0.040 |
blown | -0.038 |
Blood | -0.036 |
bitten | -0.036 |
spilled | -0.032 |
Token | in |
Token ID | 287 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
heit | +0.024 |
aman | +0.024 |
hew | +0.022 |
destination | +0.021 |
bek | +0.021 |
Neg logit contributions | |
blood | -0.011 |
blown | -0.011 |
bitten | -0.010 |
spilled | -0.010 |
Blood | -0.010 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
heit | +0.037 |
aman | +0.037 |
destination | +0.037 |
hew | +0.036 |
isn | +0.036 |
Neg logit contributions | |
blood | -0.043 |
blown | -0.041 |
bitten | -0.041 |
Blood | -0.040 |
spilled | -0.036 |
Token | ement |
Token ID | 972 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
heit | +0.061 |
olog | +0.059 |
destination | +0.057 |
hew | +0.054 |
isn | +0.053 |
Neg logit contributions | |
blood | -0.270 |
blown | -0.255 |
Blood | -0.253 |
bitten | -0.249 |
agged | -0.244 |
Token | . |
Token ID | 13 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
destination | +0.043 |
heit | +0.043 |
aman | +0.042 |
isn | +0.042 |
hew | +0.040 |
Neg logit contributions | |
blood | -0.033 |
blown | -0.033 |
Blood | -0.032 |
bitten | -0.031 |
spilled | -0.028 |
Token | So |
Token ID | 1406 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
destination | +0.007 |
heit | +0.007 |
aman | +0.007 |
isn | +0.007 |
ement | +0.006 |
Neg logit contributions | |
Blood | -0.003 |
blown | -0.003 |
blood | -0.003 |
bitten | -0.003 |
spilled | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
heit | +0.023 |
aman | +0.023 |
hew | +0.022 |
destination | +0.022 |
isn | +0.022 |
Neg logit contributions | |
blown | -0.011 |
blood | -0.010 |
Blood | -0.010 |
bitten | -0.010 |
spilled | -0.009 |
Token | he |
Token ID | 339 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
blown | +0.002 |
blood | +0.002 |
Blood | +0.002 |
bitten | +0.002 |
spilled | +0.002 |
Neg logit contributions | |
destination | -0.005 |
heit | -0.005 |
aman | -0.005 |
isn | -0.005 |
hew | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
destination | +0.064 |
aman | +0.062 |
heit | +0.060 |
isn | +0.058 |
exactly | +0.057 |
Neg logit contributions | |
Blood | -0.046 |
blown | -0.044 |
blood | -0.044 |
bitten | -0.043 |
elt | -0.040 |
Token | bush |
Token ID | 24484 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
destination | +0.034 |
aman | +0.033 |
isn | +0.033 |
heit | +0.032 |
ement | +0.031 |
Neg logit contributions | |
blown | -0.026 |
Blood | -0.026 |
blood | -0.026 |
bitten | -0.025 |
spilled | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
heit | +0.065 |
destination | +0.061 |
isn | +0.061 |
aman | +0.060 |
ement | +0.057 |
Neg logit contributions | |
blown | -0.044 |
blood | -0.042 |
Blood | -0.041 |
bitten | -0.041 |
spilled | -0.038 |
Token | watched |
Token ID | 7342 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
destination | +0.017 |
aman | +0.017 |
isn | +0.017 |
heit | +0.017 |
ement | +0.016 |
Neg logit contributions | |
Blood | -0.012 |
blown | -0.012 |
blood | -0.012 |
bitten | -0.012 |
spilled | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
destination | +0.041 |
aman | +0.040 |
heit | +0.040 |
isn | +0.039 |
hew | +0.038 |
Neg logit contributions | |
blown | -0.031 |
blood | -0.031 |
Blood | -0.030 |
bitten | -0.029 |
spilled | -0.026 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.86e+00 |
Pos logit contributions | |
heit | +0.057 |
destination | +0.057 |
aman | +0.056 |
isn | +0.056 |
hew | +0.054 |
Neg logit contributions | |
blood | -0.044 |
blown | -0.044 |
bitten | -0.041 |
Blood | -0.041 |
spilled | -0.037 |
Token | ement |
Token ID | 972 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
destination | +0.050 |
heit | +0.046 |
isn | +0.043 |
olog | +0.039 |
bek | +0.036 |
Neg logit contributions | |
blood | -0.280 |
blown | -0.270 |
Blood | -0.266 |
bitten | -0.264 |
agged | -0.251 |
Token | as |
Token ID | 355 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
destination | +0.032 |
aman | +0.031 |
heit | +0.031 |
isn | +0.031 |
ement | +0.029 |
Neg logit contributions | |
blown | -0.027 |
blood | -0.027 |
Blood | -0.027 |
bitten | -0.026 |
spilled | -0.023 |
Token | it |
Token ID | 340 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
blown | +0.030 |
blood | +0.030 |
Blood | +0.029 |
bitten | +0.028 |
spilled | +0.025 |
Neg logit contributions | |
destination | -0.046 |
aman | -0.045 |
heit | -0.044 |
isn | -0.044 |
ement | -0.042 |
Token | flew |
Token ID | 13112 |
Feature activation | +5.20e-04 |
Pos logit contributions | |
Blood | +0.007 |
blood | +0.007 |
blown | +0.007 |
bitten | +0.006 |
elt | +0.006 |
Neg logit contributions | |
destination | -0.012 |
isn | -0.011 |
aman | -0.011 |
heit | -0.011 |
ement | -0.011 |
Token | away |
Token ID | 1497 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
heit | +0.000 |
destination | +0.000 |
aman | +0.000 |
isn | +0.000 |
ement | +0.000 |
Neg logit contributions | |
blown | -0.000 |
blood | -0.000 |
bitten | -0.000 |
Blood | -0.000 |
spilled | -0.000 |
Token | door |
Token ID | 3420 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
aman | +0.024 |
heit | +0.024 |
mmm | +0.024 |
hew | +0.023 |
idays | +0.022 |
Neg logit contributions | |
blood | -0.013 |
blown | -0.012 |
bitten | -0.011 |
Blood | -0.011 |
spilled | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
blown | +0.005 |
blood | +0.004 |
Blood | +0.004 |
bitten | +0.004 |
spilled | +0.004 |
Neg logit contributions | |
heit | -0.008 |
isn | -0.008 |
aman | -0.008 |
hew | -0.008 |
destination | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
destination | +0.012 |
aman | +0.012 |
isn | +0.012 |
heit | +0.012 |
ement | +0.011 |
Neg logit contributions | |
blown | -0.010 |
blood | -0.010 |
Blood | -0.010 |
bitten | -0.010 |
spilled | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
destination | +0.018 |
aman | +0.018 |
heit | +0.017 |
isn | +0.017 |
ement | +0.017 |
Neg logit contributions | |
blown | -0.011 |
blood | -0.011 |
Blood | -0.011 |
bitten | -0.011 |
spilled | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
destination | +0.028 |
aman | +0.027 |
isn | +0.027 |
heit | +0.027 |
ement | +0.026 |
Neg logit contributions | |
blown | -0.017 |
blood | -0.017 |
Blood | -0.017 |
bitten | -0.016 |
spilled | -0.014 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.80e+00 |
Pos logit contributions | |
aman | +0.024 |
mmm | +0.023 |
heit | +0.023 |
hew | +0.023 |
idays | +0.021 |
Neg logit contributions | |
blown | -0.022 |
blood | -0.022 |
bitten | -0.021 |
Blood | -0.021 |
cat | -0.020 |
Token | ement |
Token ID | 972 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
heit | +0.043 |
isn | +0.038 |
destination | +0.037 |
hew | +0.037 |
aman | +0.031 |
Neg logit contributions | |
blood | -0.284 |
blown | -0.278 |
Blood | -0.273 |
bitten | -0.270 |
spilled | -0.254 |
Token | , |
Token ID | 11 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
destination | +0.037 |
heit | +0.037 |
isn | +0.036 |
aman | +0.036 |
ement | +0.034 |
Neg logit contributions | |
blown | -0.037 |
blood | -0.037 |
Blood | -0.036 |
bitten | -0.036 |
spilled | -0.033 |
Token | she |
Token ID | 673 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
blown | +0.003 |
blood | +0.003 |
Blood | +0.002 |
bitten | +0.002 |
spilled | +0.002 |
Neg logit contributions | |
destination | -0.006 |
heit | -0.006 |
aman | -0.006 |
isn | -0.006 |
ement | -0.006 |
Token | could |
Token ID | 714 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
aman | +0.020 |
heit | +0.019 |
destination | +0.019 |
isn | +0.018 |
ement | +0.018 |
Neg logit contributions | |
blown | -0.011 |
Blood | -0.010 |
bitten | -0.010 |
blood | -0.010 |
spilled | -0.009 |
Token | see |
Token ID | 766 |
Feature activation | +4.77e-01 |
Pos logit contributions | |
blown | +0.018 |
blood | +0.017 |
Blood | +0.017 |
bitten | +0.017 |
spilled | +0.014 |
Neg logit contributions | |
destination | -0.033 |
aman | -0.032 |
isn | -0.032 |
heit | -0.032 |
ement | -0.031 |
Token | pond |
Token ID | 16723 |
Feature activation | -8.25e-02 |
Pos logit contributions | |
blown | +0.002 |
blood | +0.002 |
Blood | +0.002 |
bitten | +0.002 |
spilled | +0.002 |
Neg logit contributions | |
destination | -0.004 |
aman | -0.004 |
isn | -0.004 |
heit | -0.004 |
ement | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
blown | +0.002 |
blood | +0.002 |
Blood | +0.002 |
bitten | +0.002 |
spilled | +0.002 |
Neg logit contributions | |
heit | -0.002 |
destination | -0.002 |
aman | -0.002 |
isn | -0.002 |
hew | -0.002 |
Token | everyone |
Token ID | 2506 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
destination | +0.018 |
aman | +0.018 |
heit | +0.018 |
isn | +0.018 |
ement | +0.017 |
Neg logit contributions | |
blown | -0.013 |
blood | -0.012 |
Blood | -0.012 |
bitten | -0.012 |
spilled | -0.011 |
Token | watched |
Token ID | 7342 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
blown | +0.037 |
blood | +0.036 |
bitten | +0.035 |
Blood | +0.035 |
spilled | +0.033 |
Neg logit contributions | |
destination | -0.046 |
aman | -0.045 |
heit | -0.044 |
isn | -0.043 |
ement | -0.041 |
Token | in |
Token ID | 287 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
destination | +0.052 |
heit | +0.052 |
aman | +0.051 |
isn | +0.050 |
hew | +0.049 |
Neg logit contributions | |
blown | -0.027 |
blood | -0.027 |
Blood | -0.025 |
bitten | -0.025 |
spilled | -0.022 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
heit | +0.043 |
hew | +0.040 |
aman | +0.039 |
mmm | +0.039 |
isn | +0.038 |
Neg logit contributions | |
blood | -0.067 |
blown | -0.064 |
bitten | -0.062 |
Blood | -0.059 |
spilled | -0.057 |
Token | ement |
Token ID | 972 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
destination | +0.051 |
heit | +0.051 |
isn | +0.048 |
olog | +0.047 |
hew | +0.042 |
Neg logit contributions | |
blood | -0.269 |
blown | -0.258 |
Blood | -0.256 |
bitten | -0.252 |
agged | -0.244 |
Token | as |
Token ID | 355 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
destination | +0.029 |
heit | +0.028 |
aman | +0.028 |
isn | +0.028 |
ement | +0.026 |
Neg logit contributions | |
blown | -0.024 |
blood | -0.024 |
Blood | -0.024 |
bitten | -0.023 |
spilled | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | -4.81e-01 |
Pos logit contributions | |
blown | +0.028 |
blood | +0.028 |
Blood | +0.027 |
bitten | +0.026 |
spilled | +0.024 |
Neg logit contributions | |
destination | -0.049 |
aman | -0.048 |
heit | -0.048 |
isn | -0.047 |
hew | -0.046 |
Token | thread |
Token ID | 4704 |
Feature activation | -5.92e-01 |
Pos logit contributions | |
blown | +0.010 |
blood | +0.010 |
Blood | +0.009 |
bitten | +0.009 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.014 |
aman | -0.014 |
heit | -0.013 |
isn | -0.013 |
ement | -0.013 |
Token | gl |
Token ID | 1278 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Blood | +0.011 |
blood | +0.011 |
blown | +0.010 |
bitten | +0.010 |
elt | +0.008 |
Neg logit contributions | |
destination | -0.018 |
isn | -0.017 |
aman | -0.017 |
heit | -0.016 |
ement | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
blown | +0.009 |
blood | +0.009 |
bitten | +0.009 |
Blood | +0.008 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.013 |
isn | -0.013 |
aman | -0.013 |
ement | -0.012 |
heit | -0.012 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
blown | +0.021 |
blood | +0.021 |
Blood | +0.020 |
bitten | +0.020 |
spilled | +0.017 |
Neg logit contributions | |
destination | -0.036 |
aman | -0.036 |
heit | -0.035 |
isn | -0.035 |
ement | -0.034 |
Token | stepped |
Token ID | 10764 |
Feature activation | +7.83e-01 |
Pos logit contributions | |
blown | +0.034 |
bitten | +0.032 |
blood | +0.032 |
Blood | +0.031 |
spilled | +0.030 |
Neg logit contributions | |
aman | -0.050 |
destination | -0.049 |
heit | -0.049 |
mmm | -0.046 |
isn | -0.046 |
Token | back |
Token ID | 736 |
Feature activation | -8.99e-01 |
Pos logit contributions | |
destination | +0.023 |
aman | +0.022 |
isn | +0.022 |
heit | +0.022 |
ement | +0.021 |
Neg logit contributions | |
blown | -0.015 |
blood | -0.015 |
Blood | -0.015 |
bitten | -0.015 |
spilled | -0.013 |
Token | in |
Token ID | 287 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
blown | +0.015 |
blood | +0.015 |
bitten | +0.014 |
Blood | +0.014 |
spilled | +0.013 |
Neg logit contributions | |
heit | -0.028 |
aman | -0.028 |
isn | -0.027 |
destination | -0.027 |
hew | -0.027 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
destination | +0.045 |
heit | +0.044 |
aman | +0.044 |
isn | +0.043 |
hew | +0.042 |
Neg logit contributions | |
blood | -0.030 |
blown | -0.029 |
Blood | -0.028 |
bitten | -0.028 |
spilled | -0.025 |
Token | ement |
Token ID | 972 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
destination | +0.039 |
heit | +0.032 |
isn | +0.032 |
aman | +0.026 |
hew | +0.023 |
Neg logit contributions | |
blood | -0.291 |
Blood | -0.283 |
blown | -0.281 |
bitten | -0.276 |
spilled | -0.261 |
Token | as |
Token ID | 355 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
destination | +0.042 |
heit | +0.041 |
aman | +0.041 |
isn | +0.041 |
ement | +0.038 |
Neg logit contributions | |
blown | -0.033 |
blood | -0.033 |
Blood | -0.033 |
bitten | -0.032 |
spilled | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
blown | +0.033 |
Blood | +0.032 |
blood | +0.032 |
bitten | +0.032 |
spilled | +0.027 |
Neg logit contributions | |
destination | -0.049 |
isn | -0.047 |
aman | -0.047 |
heit | -0.046 |
ement | -0.045 |
Token | dark |
Token ID | 3223 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
blown | +0.025 |
blood | +0.025 |
Blood | +0.025 |
bitten | +0.024 |
spilled | +0.021 |
Neg logit contributions | |
destination | -0.043 |
aman | -0.042 |
heit | -0.042 |
isn | -0.042 |
ement | -0.040 |
Token | started |
Token ID | 2067 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
Blood | +0.051 |
blown | +0.050 |
bitten | +0.050 |
blood | +0.049 |
Tweet | +0.041 |
Neg logit contributions | |
destination | -0.070 |
isn | -0.068 |
aman | -0.066 |
ement | -0.064 |
heit | -0.060 |
Token | her |
Token ID | 607 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
blown | +0.022 |
blood | +0.021 |
Blood | +0.021 |
bitten | +0.020 |
spilled | +0.017 |
Neg logit contributions | |
destination | -0.039 |
aman | -0.038 |
isn | -0.038 |
heit | -0.037 |
ement | -0.036 |
Token | mom |
Token ID | 1995 |
Feature activation | -9.36e-01 |
Pos logit contributions | |
blown | +0.060 |
Blood | +0.059 |
bitten | +0.058 |
blood | +0.058 |
elt | +0.052 |
Neg logit contributions | |
destination | -0.051 |
isn | -0.047 |
aman | -0.046 |
heit | -0.045 |
ement | -0.045 |
Token | my |
Token ID | 1820 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
blown | +0.024 |
Blood | +0.024 |
blood | +0.023 |
bitten | +0.023 |
spilled | +0.020 |
Neg logit contributions | |
destination | -0.022 |
aman | -0.021 |
isn | -0.021 |
heit | -0.020 |
hew | -0.020 |
Token | watched |
Token ID | 7342 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
destination | +0.007 |
aman | +0.007 |
isn | +0.006 |
heit | +0.006 |
ement | +0.006 |
Neg logit contributions | |
blown | -0.005 |
blood | -0.005 |
Blood | -0.005 |
bitten | -0.005 |
spilled | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
destination | +0.041 |
heit | +0.040 |
aman | +0.040 |
isn | +0.039 |
hew | +0.038 |
Neg logit contributions | |
blown | -0.026 |
blood | -0.026 |
Blood | -0.025 |
bitten | -0.024 |
spilled | -0.022 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
heit | +0.031 |
hew | +0.030 |
aman | +0.029 |
mmm | +0.029 |
isn | +0.028 |
Neg logit contributions | |
blood | -0.052 |
blown | -0.048 |
bitten | -0.046 |
Blood | -0.045 |
spilled | -0.044 |
Token | ement |
Token ID | 972 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
destination | +0.042 |
heit | +0.038 |
isn | +0.036 |
aman | +0.028 |
olog | +0.028 |
Neg logit contributions | |
blood | -0.284 |
blown | -0.274 |
Blood | -0.274 |
bitten | -0.267 |
spilled | -0.255 |
Token | as |
Token ID | 355 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
destination | +0.037 |
aman | +0.036 |
isn | +0.035 |
heit | +0.035 |
ement | +0.034 |
Neg logit contributions | |
blown | -0.027 |
blood | -0.026 |
Blood | -0.026 |
bitten | -0.025 |
spilled | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
blown | +0.038 |
blood | +0.037 |
Blood | +0.037 |
bitten | +0.036 |
spilled | +0.032 |
Neg logit contributions | |
destination | -0.050 |
aman | -0.048 |
isn | -0.048 |
heit | -0.048 |
ement | -0.045 |
Token | machine |
Token ID | 4572 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
Blood | +0.040 |
bitten | +0.040 |
blown | +0.040 |
blood | +0.039 |
elt | +0.038 |
Neg logit contributions | |
destination | -0.031 |
isn | -0.029 |
aman | -0.027 |
heit | -0.027 |
ement | -0.027 |
Token | flew |
Token ID | 13112 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
destination | +0.000 |
aman | +0.000 |
heit | +0.000 |
isn | +0.000 |
ement | +0.000 |
Neg logit contributions | |
blown | -0.000 |
blood | -0.000 |
bitten | -0.000 |
Blood | -0.000 |
spilled | -0.000 |
Token | hill |
Token ID | 12788 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
destination | +0.011 |
aman | +0.011 |
heit | +0.011 |
isn | +0.011 |
ement | +0.010 |
Neg logit contributions | |
blown | -0.006 |
blood | -0.006 |
Blood | -0.006 |
bitten | -0.006 |
spilled | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
heit | +0.021 |
destination | +0.021 |
aman | +0.021 |
isn | +0.020 |
hew | +0.019 |
Neg logit contributions | |
blown | -0.016 |
blood | -0.015 |
Blood | -0.015 |
bitten | -0.015 |
spilled | -0.013 |
Token | everyone |
Token ID | 2506 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
destination | +0.005 |
isn | +0.005 |
aman | +0.005 |
heit | +0.005 |
ement | +0.005 |
Neg logit contributions | |
blood | -0.004 |
Blood | -0.004 |
blown | -0.004 |
bitten | -0.004 |
spilled | -0.003 |
Token | watched |
Token ID | 7342 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
blown | +0.046 |
blood | +0.045 |
Blood | +0.044 |
bitten | +0.044 |
spilled | +0.040 |
Neg logit contributions | |
destination | -0.050 |
aman | -0.049 |
heit | -0.048 |
isn | -0.047 |
ement | -0.045 |
Token | in |
Token ID | 287 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
destination | +0.043 |
aman | +0.043 |
heit | +0.042 |
isn | +0.040 |
hew | +0.039 |
Neg logit contributions | |
blown | -0.030 |
blood | -0.030 |
Blood | -0.029 |
bitten | -0.028 |
spilled | -0.025 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.68e+00 |
Pos logit contributions | |
heit | +0.044 |
aman | +0.043 |
hew | +0.041 |
isn | +0.041 |
destination | +0.041 |
Neg logit contributions | |
blood | -0.058 |
blown | -0.056 |
bitten | -0.053 |
Blood | -0.053 |
spilled | -0.049 |
Token | ement |
Token ID | 972 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
destination | +0.050 |
heit | +0.045 |
isn | +0.042 |
olog | +0.040 |
aman | +0.038 |
Neg logit contributions | |
blood | -0.272 |
blown | -0.262 |
Blood | -0.261 |
bitten | -0.256 |
agged | -0.247 |
Token | . |
Token ID | 13 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
destination | +0.028 |
aman | +0.027 |
heit | +0.027 |
isn | +0.027 |
ement | +0.025 |
Neg logit contributions | |
blown | -0.025 |
blood | -0.025 |
Blood | -0.024 |
bitten | -0.024 |
spilled | -0.021 |
Token | The |
Token ID | 383 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
destination | +0.028 |
aman | +0.027 |
heit | +0.027 |
isn | +0.026 |
ement | +0.025 |
Neg logit contributions | |
Blood | -0.016 |
blown | -0.016 |
blood | -0.015 |
bitten | -0.014 |
spilled | -0.013 |
Token | rock |
Token ID | 3881 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
blown | +0.010 |
Blood | +0.009 |
bitten | +0.009 |
blood | +0.009 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.017 |
isn | -0.016 |
heit | -0.016 |
aman | -0.016 |
ement | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -9.66e-02 |
Pos logit contributions | |
blown | +0.032 |
blood | +0.031 |
Blood | +0.031 |
bitten | +0.030 |
spilled | +0.027 |
Neg logit contributions | |
destination | -0.038 |
aman | -0.037 |
heit | -0.037 |
isn | -0.036 |
ement | -0.035 |
Token | his |
Token ID | 465 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
destination | +0.030 |
aman | +0.029 |
isn | +0.029 |
heit | +0.029 |
hew | +0.028 |
Neg logit contributions | |
blood | -0.017 |
blown | -0.017 |
bitten | -0.016 |
Blood | -0.015 |
spilled | -0.013 |
Token | mummy |
Token ID | 38567 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
blood | +0.011 |
blown | +0.011 |
Blood | +0.011 |
bitten | +0.011 |
spilled | +0.009 |
Neg logit contributions | |
aman | -0.023 |
destination | -0.022 |
heit | -0.022 |
isn | -0.021 |
hew | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +8.81e-02 |
Pos logit contributions | |
heit | +0.005 |
destination | +0.005 |
isn | +0.005 |
aman | +0.005 |
ement | +0.005 |
Neg logit contributions | |
blown | -0.006 |
blood | -0.005 |
bitten | -0.005 |
spilled | -0.005 |
Blood | -0.005 |
Token | trembling |
Token ID | 39228 |
Feature activation | -4.35e-01 |
Pos logit contributions | |
destination | +0.002 |
aman | +0.002 |
isn | +0.002 |
heit | +0.002 |
ement | +0.002 |
Neg logit contributions | |
blown | -0.002 |
blood | -0.002 |
Blood | -0.002 |
bitten | -0.002 |
spilled | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
blown | +0.009 |
blood | +0.009 |
bitten | +0.009 |
Blood | +0.008 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.012 |
aman | -0.012 |
heit | -0.012 |
isn | -0.012 |
hew | -0.011 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.68e+00 |
Pos logit contributions | |
destination | +0.037 |
aman | +0.036 |
heit | +0.036 |
isn | +0.036 |
hew | +0.035 |
Neg logit contributions | |
blown | -0.032 |
blood | -0.032 |
bitten | -0.031 |
Blood | -0.031 |
spilled | -0.027 |
Token | ement |
Token ID | 972 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
destination | +0.050 |
heit | +0.049 |
isn | +0.044 |
olog | +0.041 |
hew | +0.038 |
Neg logit contributions | |
blood | -0.271 |
blown | -0.258 |
Blood | -0.258 |
bitten | -0.253 |
agged | -0.240 |
Token | . |
Token ID | 13 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
destination | +0.051 |
heit | +0.050 |
isn | +0.050 |
aman | +0.050 |
ement | +0.047 |
Neg logit contributions | |
blown | -0.042 |
blood | -0.041 |
Blood | -0.040 |
bitten | -0.040 |
spilled | -0.036 |
Token | They |
Token ID | 1119 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Blood | +0.001 |
blown | +0.001 |
blood | +0.001 |
bitten | +0.001 |
elt | +0.001 |
Neg logit contributions | |
destination | -0.002 |
heit | -0.002 |
aman | -0.002 |
isn | -0.002 |
ement | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
blown | +0.004 |
blood | +0.004 |
bitten | +0.003 |
Blood | +0.003 |
spilled | +0.003 |
Neg logit contributions | |
aman | -0.006 |
destination | -0.006 |
isn | -0.006 |
heit | -0.006 |
ement | -0.006 |
Token | just |
Token ID | 655 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
blown | +0.010 |
blood | +0.010 |
bitten | +0.010 |
Blood | +0.009 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.015 |
aman | -0.014 |
heit | -0.014 |
isn | -0.014 |
ement | -0.014 |
Token | THE |
Token ID | 3336 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
blown | +0.023 |
Blood | +0.022 |
blood | +0.022 |
bitten | +0.022 |
spilled | +0.020 |
Neg logit contributions | |
destination | -0.023 |
aman | -0.022 |
heit | -0.022 |
ement | -0.021 |
isn | -0.021 |
Token | BE |
Token ID | 9348 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
heit | +0.003 |
destination | +0.003 |
aman | +0.003 |
hew | +0.003 |
exactly | +0.003 |
Neg logit contributions | |
Blood | -0.003 |
bitten | -0.003 |
blown | -0.003 |
blood | -0.003 |
spilled | -0.002 |
Token | LL |
Token ID | 3069 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
aman | +0.059 |
heit | +0.058 |
destination | +0.057 |
ement | +0.055 |
isn | +0.054 |
Neg logit contributions | |
Blood | -0.067 |
blown | -0.059 |
Tweet | -0.059 |
bitten | -0.058 |
blood | -0.056 |
Token | WHEN |
Token ID | 42099 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
destination | +0.051 |
isn | +0.051 |
aman | +0.050 |
heit | +0.049 |
hew | +0.047 |
Neg logit contributions | |
blown | -0.055 |
blood | -0.054 |
bitten | -0.051 |
Blood | -0.050 |
spilled | -0.047 |
Token | YOU |
Token ID | 7013 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
destination | +0.030 |
aman | +0.029 |
isn | +0.028 |
heit | +0.028 |
ement | +0.026 |
Neg logit contributions | |
blown | -0.061 |
blood | -0.060 |
Blood | -0.059 |
bitten | -0.059 |
spilled | -0.055 |
Token | FE |
Token ID | 18630 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
aman | +0.050 |
destination | +0.047 |
ement | +0.045 |
heit | +0.043 |
destinations | +0.041 |
Neg logit contributions | |
Blood | -0.049 |
blown | -0.047 |
bitten | -0.046 |
blood | -0.042 |
spilled | -0.042 |
Token | EL |
Token ID | 3698 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
aman | +0.145 |
destination | +0.144 |
heit | +0.140 |
amaz | +0.133 |
isn | +0.132 |
Neg logit contributions | |
Blood | -0.170 |
bitten | -0.146 |
agged | -0.145 |
blood | -0.145 |
blown | -0.144 |
Token | LIKE |
Token ID | 34178 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
destination | +0.052 |
aman | +0.052 |
heit | +0.049 |
isn | +0.048 |
exactly | +0.048 |
Neg logit contributions | |
bitten | -0.038 |
blown | -0.037 |
Blood | -0.037 |
blood | -0.036 |
spilled | -0.032 |
Token | IT |
Token ID | 7283 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
aman | +0.087 |
isn | +0.086 |
rd | +0.084 |
destination | +0.083 |
hew | +0.082 |
Neg logit contributions | |
Blood | -0.088 |
blood | -0.085 |
blown | -0.081 |
bitten | -0.076 |
hes | -0.070 |
Token | ". |
Token ID | 1911 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
aman | +0.032 |
destination | +0.030 |
ement | +0.028 |
heit | +0.028 |
hew | +0.027 |
Neg logit contributions | |
blown | -0.045 |
Blood | -0.044 |
bitten | -0.043 |
blood | -0.043 |
spilled | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
heit | +0.011 |
destination | +0.011 |
aman | +0.010 |
isn | +0.010 |
ement | +0.010 |
Neg logit contributions | |
Blood | -0.005 |
blood | -0.005 |
bitten | -0.004 |
blown | -0.004 |
spilled | -0.003 |
Token | baby |
Token ID | 5156 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
blown | +0.024 |
Blood | +0.023 |
blood | +0.023 |
bitten | +0.022 |
spilled | +0.019 |
Neg logit contributions | |
destination | -0.042 |
isn | -0.041 |
aman | -0.040 |
heit | -0.040 |
ement | -0.038 |
Token | le |
Token ID | 443 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
blown | +0.026 |
blood | +0.025 |
Blood | +0.025 |
bitten | +0.024 |
spilled | +0.020 |
Neg logit contributions | |
destination | -0.059 |
isn | -0.058 |
aman | -0.058 |
heit | -0.057 |
ement | -0.056 |
Token | opard |
Token ID | 15478 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
blown | +0.022 |
blood | +0.020 |
Blood | +0.019 |
spilled | +0.018 |
bitten | +0.018 |
Neg logit contributions | |
aman | -0.030 |
ement | -0.030 |
isn | -0.030 |
hew | -0.030 |
destination | -0.029 |
Token | watched |
Token ID | 7342 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
destination | +0.001 |
aman | +0.001 |
heit | +0.001 |
isn | +0.001 |
ement | +0.001 |
Neg logit contributions | |
blown | -0.001 |
blood | -0.001 |
bitten | -0.001 |
Blood | -0.001 |
spilled | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
destination | +0.023 |
aman | +0.022 |
isn | +0.022 |
heit | +0.022 |
ement | +0.021 |
Neg logit contributions | |
blown | -0.018 |
blood | -0.017 |
Blood | -0.017 |
bitten | -0.017 |
spilled | -0.015 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.65e+00 |
Pos logit contributions | |
destination | +0.031 |
aman | +0.030 |
heit | +0.030 |
isn | +0.030 |
hew | +0.028 |
Neg logit contributions | |
blood | -0.044 |
blown | -0.043 |
bitten | -0.042 |
Blood | -0.042 |
spilled | -0.038 |
Token | ement |
Token ID | 972 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
destination | +0.047 |
isn | +0.039 |
heit | +0.039 |
olog | +0.034 |
aman | +0.033 |
Neg logit contributions | |
blood | -0.275 |
Blood | -0.266 |
blown | -0.263 |
bitten | -0.260 |
agged | -0.247 |
Token | as |
Token ID | 355 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
destination | +0.029 |
aman | +0.028 |
isn | +0.028 |
heit | +0.028 |
ement | +0.027 |
Neg logit contributions | |
blown | -0.026 |
blood | -0.026 |
Blood | -0.025 |
bitten | -0.025 |
spilled | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
blown | +0.043 |
Blood | +0.042 |
bitten | +0.041 |
blood | +0.041 |
elt | +0.037 |
Neg logit contributions | |
destination | -0.050 |
isn | -0.050 |
heit | -0.048 |
aman | -0.048 |
ement | -0.046 |
Token | lion |
Token ID | 18744 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
blown | +0.027 |
Blood | +0.027 |
blood | +0.026 |
bitten | +0.025 |
elt | +0.024 |
Neg logit contributions | |
destination | -0.039 |
isn | -0.038 |
heit | -0.037 |
aman | -0.036 |
ement | -0.035 |
Token | flex |
Token ID | 7059 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
blown | +0.021 |
blood | +0.020 |
bitten | +0.020 |
Blood | +0.020 |
spilled | +0.018 |
Neg logit contributions | |
destination | -0.040 |
aman | -0.039 |
heit | -0.039 |
isn | -0.038 |
ement | -0.037 |
Token | He |
Token ID | 679 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
Blood | +0.005 |
blood | +0.005 |
blown | +0.005 |
bitten | +0.005 |
spilled | +0.004 |
Neg logit contributions | |
destination | -0.013 |
heit | -0.013 |
aman | -0.013 |
isn | -0.012 |
ement | -0.012 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
blown | +0.001 |
blood | +0.001 |
Blood | +0.001 |
bitten | +0.001 |
spilled | +0.001 |
Neg logit contributions | |
destination | -0.002 |
aman | -0.002 |
heit | -0.002 |
isn | -0.002 |
ement | -0.002 |
Token | at |
Token ID | 379 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
aman | +0.033 |
destination | +0.033 |
heit | +0.032 |
hew | +0.031 |
mmm | +0.031 |
Neg logit contributions | |
blood | -0.022 |
blown | -0.022 |
bitten | -0.021 |
Blood | -0.020 |
spilled | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
destination | +0.041 |
aman | +0.039 |
heit | +0.039 |
isn | +0.039 |
ement | +0.037 |
Neg logit contributions | |
blood | -0.034 |
blown | -0.034 |
Blood | -0.033 |
bitten | -0.033 |
spilled | -0.029 |
Token | in |
Token ID | 287 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
heit | +0.004 |
aman | +0.004 |
destination | +0.003 |
bek | +0.003 |
rd | +0.003 |
Neg logit contributions | |
blown | -0.002 |
blood | -0.002 |
Blood | -0.002 |
bitten | -0.002 |
spilled | -0.002 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.64e+00 |
Pos logit contributions | |
destination | +0.029 |
aman | +0.028 |
heit | +0.028 |
isn | +0.028 |
ement | +0.027 |
Neg logit contributions | |
blood | -0.026 |
blown | -0.026 |
Blood | -0.025 |
bitten | -0.025 |
spilled | -0.022 |
Token | ement |
Token ID | 972 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
destination | +0.053 |
heit | +0.050 |
olog | +0.045 |
isn | +0.043 |
virtue | +0.042 |
Neg logit contributions | |
blood | -0.268 |
Blood | -0.256 |
blown | -0.250 |
bitten | -0.248 |
agged | -0.241 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
destination | +0.047 |
aman | +0.045 |
heit | +0.045 |
isn | +0.045 |
ement | +0.042 |
Neg logit contributions | |
blown | -0.042 |
blood | -0.041 |
Blood | -0.041 |
bitten | -0.040 |
spilled | -0.036 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
destination | +0.035 |
aman | +0.035 |
heit | +0.033 |
ement | +0.032 |
isn | +0.032 |
Neg logit contributions | |
blood | -0.020 |
blown | -0.019 |
Blood | -0.019 |
bitten | -0.019 |
spilled | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
blood | +0.021 |
blown | +0.021 |
Blood | +0.021 |
bitten | +0.020 |
elt | +0.018 |
Neg logit contributions | |
aman | -0.031 |
heit | -0.031 |
destination | -0.030 |
isn | -0.029 |
hew | -0.029 |
Token | Now |
Token ID | 2735 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
destination | +0.004 |
aman | +0.003 |
heit | +0.003 |
ement | +0.003 |
isn | +0.003 |
Neg logit contributions | |
Blood | -0.002 |
blood | -0.002 |
blown | -0.002 |
bitten | -0.002 |
spilled | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | -6.48e-02 |
Pos logit contributions | |
Blood | +0.005 |
blood | +0.005 |
blown | +0.005 |
bitten | +0.005 |
spilled | +0.004 |
Neg logit contributions | |
destination | -0.013 |
heit | -0.013 |
aman | -0.013 |
isn | -0.012 |
ement | -0.012 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
blown | +0.001 |
blood | +0.001 |
Blood | +0.001 |
bitten | +0.001 |
spilled | +0.001 |
Neg logit contributions | |
destination | -0.002 |
aman | -0.002 |
heit | -0.002 |
isn | -0.002 |
ement | -0.002 |
Token | at |
Token ID | 379 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
aman | +0.033 |
destination | +0.033 |
heit | +0.032 |
hew | +0.031 |
mmm | +0.031 |
Neg logit contributions | |
blood | -0.022 |
blown | -0.022 |
bitten | -0.021 |
Blood | -0.020 |
spilled | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
destination | +0.041 |
aman | +0.039 |
heit | +0.039 |
isn | +0.039 |
ement | +0.037 |
Neg logit contributions | |
blood | -0.034 |
blown | -0.034 |
Blood | -0.033 |
bitten | -0.033 |
spilled | -0.029 |
Token | in |
Token ID | 287 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
heit | +0.004 |
aman | +0.004 |
destination | +0.003 |
bek | +0.003 |
rd | +0.003 |
Neg logit contributions | |
blown | -0.002 |
blood | -0.002 |
Blood | -0.002 |
bitten | -0.002 |
spilled | -0.002 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.64e+00 |
Pos logit contributions | |
destination | +0.029 |
aman | +0.028 |
heit | +0.028 |
isn | +0.028 |
ement | +0.027 |
Neg logit contributions | |
blood | -0.026 |
blown | -0.026 |
Blood | -0.025 |
bitten | -0.025 |
spilled | -0.022 |
Token | ement |
Token ID | 972 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
destination | +0.053 |
heit | +0.050 |
olog | +0.045 |
isn | +0.043 |
virtue | +0.042 |
Neg logit contributions | |
blood | -0.268 |
Blood | -0.256 |
blown | -0.250 |
bitten | -0.248 |
agged | -0.241 |
Token | and |
Token ID | 290 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
destination | +0.047 |
aman | +0.045 |
heit | +0.045 |
isn | +0.045 |
ement | +0.042 |
Neg logit contributions | |
blown | -0.042 |
blood | -0.041 |
Blood | -0.041 |
bitten | -0.040 |
spilled | -0.036 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
destination | +0.035 |
aman | +0.035 |
heit | +0.033 |
ement | +0.032 |
isn | +0.032 |
Neg logit contributions | |
blood | -0.020 |
blown | -0.019 |
Blood | -0.019 |
bitten | -0.019 |
spilled | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
blood | +0.021 |
blown | +0.021 |
Blood | +0.021 |
bitten | +0.020 |
elt | +0.018 |
Neg logit contributions | |
aman | -0.031 |
heit | -0.031 |
destination | -0.030 |
isn | -0.029 |
hew | -0.029 |
Token | Now |
Token ID | 2735 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
destination | +0.004 |
aman | +0.003 |
heit | +0.003 |
ement | +0.003 |
isn | +0.003 |
Neg logit contributions | |
Blood | -0.002 |
blood | -0.002 |
blown | -0.002 |
bitten | -0.002 |
spilled | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
blood | +0.037 |
blown | +0.037 |
bitten | +0.035 |
Blood | +0.034 |
spilled | +0.031 |
Neg logit contributions | |
aman | -0.050 |
destination | -0.049 |
heit | -0.049 |
ement | -0.046 |
isn | -0.046 |
Token | Everyone |
Token ID | 11075 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
blown | +0.014 |
blood | +0.013 |
bitten | +0.013 |
Blood | +0.013 |
spilled | +0.011 |
Neg logit contributions | |
destination | -0.028 |
isn | -0.027 |
aman | -0.027 |
heit | -0.026 |
ement | -0.025 |
Token | watched |
Token ID | 7342 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
blown | +0.055 |
blood | +0.054 |
bitten | +0.053 |
Blood | +0.052 |
spilled | +0.050 |
Neg logit contributions | |
destination | -0.074 |
aman | -0.073 |
heit | -0.069 |
ement | -0.066 |
isn | -0.065 |
Token | him |
Token ID | 683 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
destination | +0.024 |
aman | +0.024 |
heit | +0.023 |
isn | +0.022 |
hew | +0.022 |
Neg logit contributions | |
blood | -0.017 |
blown | -0.017 |
Blood | -0.016 |
bitten | -0.016 |
spilled | -0.014 |
Token | in |
Token ID | 287 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
aman | +0.004 |
destination | +0.004 |
heit | +0.004 |
isn | +0.004 |
ement | +0.004 |
Neg logit contributions | |
blown | -0.003 |
blood | -0.003 |
Blood | -0.002 |
bitten | -0.002 |
spilled | -0.002 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.61e+00 |
Pos logit contributions | |
destination | +0.044 |
aman | +0.043 |
heit | +0.043 |
isn | +0.042 |
ement | +0.041 |
Neg logit contributions | |
blood | -0.035 |
blown | -0.035 |
Blood | -0.034 |
bitten | -0.033 |
spilled | -0.030 |
Token | ement |
Token ID | 972 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
destination | +0.043 |
heit | +0.041 |
isn | +0.038 |
olog | +0.036 |
aman | +0.032 |
Neg logit contributions | |
blood | -0.272 |
Blood | -0.264 |
blown | -0.262 |
bitten | -0.257 |
agged | -0.248 |
Token | and |
Token ID | 290 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
destination | +0.040 |
aman | +0.039 |
isn | +0.038 |
heit | +0.038 |
ement | +0.036 |
Neg logit contributions | |
blown | -0.037 |
blood | -0.036 |
Blood | -0.036 |
bitten | -0.035 |
spilled | -0.032 |
Token | cheered |
Token ID | 34767 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
aman | +0.037 |
destination | +0.037 |
heit | +0.036 |
ement | +0.035 |
isn | +0.035 |
Neg logit contributions | |
blown | -0.024 |
blood | -0.023 |
bitten | -0.022 |
Blood | -0.022 |
spilled | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
Blood | +0.005 |
blood | +0.005 |
blown | +0.005 |
bitten | +0.004 |
mice | +0.004 |
Neg logit contributions | |
aman | -0.012 |
heit | -0.011 |
destination | -0.011 |
hew | -0.011 |
ement | -0.010 |
Token | |
Token ID | 220 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
destination | +0.012 |
aman | +0.011 |
heit | +0.011 |
isn | +0.011 |
ement | +0.011 |
Neg logit contributions | |
Blood | -0.005 |
blood | -0.004 |
blown | -0.004 |
bitten | -0.004 |
elt | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +8.61e-01 |
Pos logit contributions | |
heit | +0.005 |
aman | +0.005 |
destination | +0.005 |
isn | +0.004 |
ement | +0.004 |
Neg logit contributions | |
blown | -0.004 |
blood | -0.004 |
Blood | -0.004 |
bitten | -0.003 |
spilled | -0.003 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
destination | +0.026 |
heit | +0.025 |
aman | +0.024 |
isn | +0.024 |
ement | +0.023 |
Neg logit contributions | |
Blood | -0.017 |
blood | -0.016 |
blown | -0.016 |
bitten | -0.015 |
elt | -0.014 |
Token | my |
Token ID | 1820 |
Feature activation | +3.87e-02 |
Pos logit contributions | |
destination | +0.028 |
heit | +0.027 |
aman | +0.027 |
isn | +0.026 |
ement | +0.025 |
Neg logit contributions | |
blood | -0.021 |
blown | -0.021 |
Blood | -0.021 |
bitten | -0.021 |
spilled | -0.019 |
Token | watched |
Token ID | 7342 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
destination | +0.001 |
aman | +0.001 |
heit | +0.001 |
isn | +0.001 |
ement | +0.001 |
Neg logit contributions | |
blown | -0.001 |
blood | -0.001 |
Blood | -0.001 |
bitten | -0.001 |
spilled | -0.001 |
Token | in |
Token ID | 287 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
destination | +0.018 |
aman | +0.018 |
isn | +0.018 |
heit | +0.017 |
ement | +0.017 |
Neg logit contributions | |
blown | -0.014 |
blood | -0.014 |
Blood | -0.014 |
bitten | -0.013 |
spilled | -0.012 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
destination | +0.039 |
heit | +0.039 |
aman | +0.039 |
isn | +0.038 |
hew | +0.036 |
Neg logit contributions | |
blood | -0.031 |
blown | -0.030 |
Blood | -0.029 |
bitten | -0.029 |
spilled | -0.026 |
Token | ement |
Token ID | 972 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
destination | +0.045 |
heit | +0.040 |
isn | +0.036 |
aman | +0.032 |
olog | +0.030 |
Neg logit contributions | |
blood | -0.275 |
Blood | -0.265 |
blown | -0.262 |
bitten | -0.258 |
spilled | -0.245 |
Token | as |
Token ID | 355 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
destination | +0.030 |
aman | +0.029 |
isn | +0.028 |
heit | +0.028 |
ement | +0.027 |
Neg logit contributions | |
blown | -0.024 |
blood | -0.023 |
Blood | -0.023 |
bitten | -0.023 |
spilled | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
blown | +0.043 |
bitten | +0.042 |
Blood | +0.041 |
blood | +0.039 |
elt | +0.037 |
Neg logit contributions | |
destination | -0.049 |
isn | -0.048 |
aman | -0.048 |
exactly | -0.047 |
heit | -0.046 |
Token | black |
Token ID | 2042 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
blown | +0.033 |
Blood | +0.030 |
bitten | +0.029 |
blood | +0.028 |
elt | +0.026 |
Neg logit contributions | |
destination | -0.046 |
isn | -0.045 |
aman | -0.042 |
ement | -0.042 |
heit | -0.041 |
Token | board |
Token ID | 3526 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
blown | +0.099 |
bitten | +0.089 |
Blood | +0.084 |
Tweet | +0.083 |
blood | +0.083 |
Neg logit contributions | |
isn | -0.055 |
destination | -0.051 |
ement | -0.049 |
aman | -0.047 |
hew | -0.042 |
Token | uddle |
Token ID | 24500 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
destination | +0.022 |
aman | +0.022 |
heit | +0.021 |
isn | +0.021 |
ement | +0.019 |
Neg logit contributions | |
blood | -0.039 |
blown | -0.039 |
Blood | -0.039 |
bitten | -0.038 |
spilled | -0.035 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
blown | +0.007 |
blood | +0.007 |
bitten | +0.007 |
Blood | +0.007 |
spilled | +0.007 |
Neg logit contributions | |
destination | -0.004 |
aman | -0.004 |
heit | -0.004 |
isn | -0.004 |
ement | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
blown | +0.017 |
blood | +0.017 |
Blood | +0.017 |
bitten | +0.016 |
spilled | +0.014 |
Neg logit contributions | |
destination | -0.033 |
aman | -0.032 |
heit | -0.032 |
isn | -0.031 |
hew | -0.031 |
Token | said |
Token ID | 531 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
blown | +0.033 |
blood | +0.033 |
Blood | +0.033 |
bitten | +0.032 |
spilled | +0.029 |
Neg logit contributions | |
destination | -0.040 |
aman | -0.039 |
heit | -0.038 |
isn | -0.037 |
ement | -0.037 |
Token | in |
Token ID | 287 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
blown | +0.026 |
blood | +0.025 |
Blood | +0.025 |
bitten | +0.025 |
spilled | +0.022 |
Neg logit contributions | |
destination | -0.033 |
heit | -0.033 |
aman | -0.033 |
isn | -0.032 |
hew | -0.031 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.57e+00 |
Pos logit contributions | |
destination | +0.003 |
aman | +0.003 |
isn | +0.003 |
heit | +0.003 |
ement | +0.003 |
Neg logit contributions | |
blown | -0.002 |
Blood | -0.002 |
blood | -0.002 |
bitten | -0.002 |
spilled | -0.002 |
Token | ement |
Token ID | 972 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
destination | +0.045 |
heit | +0.038 |
isn | +0.037 |
hew | +0.032 |
aman | +0.031 |
Neg logit contributions | |
blood | -0.275 |
Blood | -0.268 |
blown | -0.266 |
bitten | -0.262 |
agged | -0.247 |
Token | . |
Token ID | 13 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
destination | +0.049 |
isn | +0.047 |
aman | +0.047 |
heit | +0.047 |
ement | +0.044 |
Neg logit contributions | |
blown | -0.043 |
blood | -0.043 |
Blood | -0.043 |
bitten | -0.042 |
spilled | -0.038 |
Token | |
Token ID | 220 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
destination | +0.003 |
heit | +0.003 |
aman | +0.003 |
isn | +0.003 |
ement | +0.003 |
Neg logit contributions | |
Blood | -0.003 |
blown | -0.003 |
blood | -0.002 |
bitten | -0.002 |
elt | -0.002 |
Token | |
Token ID | 220 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
blown | +0.032 |
Blood | +0.032 |
blood | +0.032 |
bitten | +0.031 |
spilled | +0.027 |
Neg logit contributions | |
destination | -0.045 |
heit | -0.043 |
aman | -0.043 |
isn | -0.042 |
ement | -0.041 |
Token |
|
Token ID | 198 |
Feature activation | +7.67e-02 |
Pos logit contributions | |
blown | +0.032 |
blood | +0.032 |
Blood | +0.032 |
bitten | +0.031 |
spilled | +0.027 |
Neg logit contributions | |
destination | -0.043 |
aman | -0.042 |
heit | -0.042 |
isn | -0.041 |
ement | -0.040 |
Token | gazed |
Token ID | 50255 |
Feature activation | +3.17e-02 |
Pos logit contributions | |
Blood | +0.029 |
blood | +0.029 |
blown | +0.027 |
bitten | +0.026 |
elt | +0.023 |
Neg logit contributions | |
isn | -0.027 |
heit | -0.026 |
destination | -0.026 |
aman | -0.026 |
hew | -0.025 |
Token | at |
Token ID | 379 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
destination | +0.001 |
aman | +0.001 |
heit | +0.001 |
isn | +0.001 |
ement | +0.001 |
Neg logit contributions | |
blown | -0.001 |
blood | -0.001 |
Blood | -0.001 |
bitten | -0.001 |
spilled | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
destination | +0.049 |
aman | +0.048 |
heit | +0.047 |
isn | +0.047 |
ement | +0.045 |
Neg logit contributions | |
blown | -0.046 |
blood | -0.046 |
Blood | -0.045 |
bitten | -0.044 |
spilled | -0.040 |
Token | butterfly |
Token ID | 35113 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
destination | +0.005 |
isn | +0.005 |
aman | +0.005 |
heit | +0.005 |
ement | +0.005 |
Neg logit contributions | |
Blood | -0.004 |
bitten | -0.004 |
blown | -0.004 |
blood | -0.004 |
elt | -0.004 |
Token | in |
Token ID | 287 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
heit | +0.023 |
aman | +0.023 |
destination | +0.023 |
isn | +0.022 |
ement | +0.021 |
Neg logit contributions | |
blown | -0.018 |
blood | -0.017 |
bitten | -0.016 |
Blood | -0.016 |
spilled | -0.015 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
destination | +0.029 |
aman | +0.029 |
heit | +0.029 |
isn | +0.028 |
ement | +0.027 |
Neg logit contributions | |
blown | -0.032 |
blood | -0.032 |
Blood | -0.031 |
bitten | -0.031 |
spilled | -0.028 |
Token | ement |
Token ID | 972 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
destination | +0.037 |
heit | +0.036 |
isn | +0.031 |
aman | +0.027 |
hew | +0.024 |
Neg logit contributions | |
blood | -0.278 |
blown | -0.272 |
Blood | -0.269 |
bitten | -0.265 |
spilled | -0.251 |
Token | . |
Token ID | 13 |
Feature activation | +3.80e-01 |
Pos logit contributions | |
destination | +0.036 |
aman | +0.035 |
isn | +0.034 |
heit | +0.034 |
ement | +0.033 |
Neg logit contributions | |
blown | -0.035 |
blood | -0.034 |
Blood | -0.034 |
bitten | -0.034 |
spilled | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
destination | +0.010 |
isn | +0.010 |
aman | +0.010 |
heit | +0.010 |
ement | +0.009 |
Neg logit contributions | |
blown | -0.008 |
blood | -0.008 |
Blood | -0.008 |
bitten | -0.008 |
spilled | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
destination | +0.001 |
aman | +0.001 |
heit | +0.001 |
isn | +0.001 |
ement | +0.001 |
Neg logit contributions | |
blown | -0.001 |
blood | -0.001 |
Blood | -0.001 |
bitten | -0.001 |
spilled | -0.001 |
Token | But |
Token ID | 1537 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
blown | +0.007 |
blood | +0.007 |
Blood | +0.007 |
bitten | +0.007 |
spilled | +0.006 |
Neg logit contributions | |
destination | -0.007 |
aman | -0.007 |
isn | -0.007 |
heit | -0.007 |
ement | -0.006 |
Token | at |
Token ID | 379 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
aman | +0.027 |
heit | +0.026 |
destination | +0.026 |
mmm | +0.026 |
hew | +0.026 |
Neg logit contributions | |
blown | -0.020 |
blood | -0.019 |
bitten | -0.018 |
Blood | -0.018 |
spilled | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
destination | +0.044 |
aman | +0.043 |
isn | +0.043 |
heit | +0.043 |
hew | +0.041 |
Neg logit contributions | |
blood | -0.024 |
blown | -0.024 |
Blood | -0.023 |
bitten | -0.022 |
spilled | -0.019 |
Token | red |
Token ID | 2266 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
blown | +0.009 |
blood | +0.009 |
Blood | +0.009 |
bitten | +0.009 |
spilled | +0.007 |
Neg logit contributions | |
destination | -0.018 |
isn | -0.017 |
aman | -0.017 |
heit | -0.017 |
ement | -0.016 |
Token | blocks |
Token ID | 7021 |
Feature activation | -7.92e-02 |
Pos logit contributions | |
blown | +0.040 |
bitten | +0.038 |
blood | +0.038 |
Blood | +0.037 |
spilled | +0.031 |
Neg logit contributions | |
destination | -0.071 |
isn | -0.070 |
ement | -0.066 |
aman | -0.066 |
heit | -0.065 |
Token | in |
Token ID | 287 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
blown | +0.002 |
blood | +0.002 |
Blood | +0.001 |
bitten | +0.001 |
spilled | +0.001 |
Neg logit contributions | |
heit | -0.002 |
destination | -0.002 |
aman | -0.002 |
isn | -0.002 |
hew | -0.002 |
Token | amaz |
Token ID | 40642 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
heit | +0.024 |
destination | +0.024 |
isn | +0.024 |
aman | +0.024 |
hew | +0.024 |
Neg logit contributions | |
blood | -0.012 |
blown | -0.011 |
Blood | -0.011 |
bitten | -0.011 |
spilled | -0.009 |
Token | ement |
Token ID | 972 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
heit | +0.050 |
destination | +0.046 |
olog | +0.041 |
isn | +0.039 |
hew | +0.037 |
Neg logit contributions | |
blood | -0.265 |
Blood | -0.255 |
blown | -0.252 |
bitten | -0.246 |
agged | -0.238 |
Token | . |
Token ID | 13 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
destination | +0.044 |
heit | +0.043 |
aman | +0.042 |
isn | +0.042 |
hew | +0.039 |
Neg logit contributions | |
blown | -0.038 |
blood | -0.038 |
Blood | -0.037 |
bitten | -0.036 |
spilled | -0.033 |
Token | He |
Token ID | 679 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
Blood | +0.007 |
blood | +0.007 |
blown | +0.007 |
bitten | +0.007 |
elt | +0.006 |
Neg logit contributions | |
destination | -0.015 |
heit | -0.015 |
aman | -0.015 |
isn | -0.014 |
hew | -0.014 |
Token | couldn |
Token ID | 3521 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
blown | +0.004 |
Blood | +0.004 |
blood | +0.004 |
bitten | +0.004 |
spilled | +0.004 |
Neg logit contributions | |
aman | -0.008 |
destination | -0.008 |
heit | -0.007 |
ement | -0.007 |
isn | -0.007 |
Token | 't |
Token ID | 470 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
destination | +0.004 |
isn | +0.003 |
aman | +0.003 |
heit | +0.003 |
ement | +0.003 |
Neg logit contributions | |
blown | -0.002 |
blood | -0.002 |
bitten | -0.002 |
Blood | -0.002 |
spilled | -0.002 |
Token | modest |
Token ID | 12949 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
blown | +0.021 |
blood | +0.020 |
bitten | +0.020 |
Blood | +0.019 |
elt | +0.016 |
Neg logit contributions | |
isn | -0.029 |
destination | -0.028 |
aman | -0.028 |
heit | -0.028 |
ement | -0.027 |
Token | barn |
Token ID | 25203 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
blood | +0.002 |
blown | +0.002 |
Blood | +0.002 |
bitten | +0.002 |
spilled | +0.001 |
Neg logit contributions | |
destination | -0.004 |
heit | -0.004 |
aman | -0.004 |
isn | -0.004 |
hew | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
destination | +0.032 |
isn | +0.030 |
aman | +0.030 |
heit | +0.030 |
ement | +0.029 |
Neg logit contributions | |
blown | -0.033 |
blood | -0.032 |
Blood | -0.032 |
bitten | -0.032 |
spilled | -0.028 |
Token | Two |
Token ID | 4930 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
blown | +0.019 |
blood | +0.019 |
bitten | +0.018 |
Blood | +0.018 |
spilled | +0.016 |
Neg logit contributions | |
destination | -0.028 |
isn | -0.028 |
aman | -0.027 |
heit | -0.026 |
ement | -0.026 |
Token | mis |
Token ID | 2984 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
blown | +0.022 |
blood | +0.021 |
Blood | +0.021 |
bitten | +0.021 |
spilled | +0.018 |
Neg logit contributions | |
destination | -0.049 |
aman | -0.048 |
heit | -0.047 |
isn | -0.046 |
ement | -0.045 |
Token | chie |
Token ID | 3043 |
Feature activation | -6.46e+00 |
Pos logit contributions | |
blood | +0.065 |
Blood | +0.063 |
blown | +0.062 |
bitten | +0.059 |
spilled | +0.058 |
Neg logit contributions | |
destination | -0.068 |
aman | -0.065 |
heit | -0.065 |
hew | -0.064 |
isn | -0.063 |
Token | vous |
Token ID | 31222 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
blown | +0.103 |
blood | +0.102 |
Blood | +0.099 |
bitten | +0.096 |
spilled | +0.082 |
Neg logit contributions | |
destination | -0.208 |
isn | -0.204 |
aman | -0.203 |
heit | -0.202 |
ement | -0.194 |
Token | kittens |
Token ID | 45584 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
blown | +0.024 |
blood | +0.023 |
Blood | +0.023 |
bitten | +0.022 |
spilled | +0.019 |
Neg logit contributions | |
destination | -0.050 |
isn | -0.049 |
aman | -0.048 |
heit | -0.048 |
ement | -0.046 |
Token | lived |
Token ID | 5615 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
destination | +0.004 |
aman | +0.004 |
heit | +0.004 |
isn | +0.004 |
ement | +0.004 |
Neg logit contributions | |
blown | -0.003 |
blood | -0.003 |
bitten | -0.003 |
Blood | -0.003 |
spilled | -0.003 |
Token | in |
Token ID | 287 |
Feature activation | -6.23e-02 |
Pos logit contributions | |
blood | +0.018 |
Blood | +0.017 |
blown | +0.017 |
bitten | +0.017 |
spilled | +0.015 |
Neg logit contributions | |
destination | -0.021 |
aman | -0.020 |
isn | -0.020 |
exactly | -0.020 |
heit | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
blown | +0.001 |
blood | +0.001 |
Blood | +0.001 |
bitten | +0.001 |
elt | +0.001 |
Neg logit contributions | |
destination | -0.002 |
isn | -0.002 |
aman | -0.002 |
heit | -0.002 |
ement | -0.002 |
Token | too |
Token ID | 1165 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
aman | +0.006 |
destination | +0.006 |
heit | +0.006 |
isn | +0.006 |
ement | +0.006 |
Neg logit contributions | |
blown | -0.006 |
bitten | -0.005 |
blood | -0.005 |
Blood | -0.005 |
spilled | -0.005 |
Token | close |
Token ID | 1969 |
Feature activation | -6.99e-02 |
Pos logit contributions | |
blown | +0.042 |
blood | +0.041 |
Blood | +0.040 |
bitten | +0.040 |
spilled | +0.035 |
Neg logit contributions | |
destination | -0.051 |
isn | -0.050 |
aman | -0.050 |
heit | -0.049 |
ement | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
blown | +0.001 |
blood | +0.001 |
bitten | +0.001 |
Blood | +0.001 |
spilled | +0.001 |
Neg logit contributions | |
heit | -0.002 |
destination | -0.002 |
aman | -0.002 |
ement | -0.002 |
isn | -0.002 |
Token | The |
Token ID | 383 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
destination | +0.037 |
aman | +0.036 |
heit | +0.036 |
ement | +0.034 |
isn | +0.034 |
Neg logit contributions | |
Blood | -0.033 |
blown | -0.033 |
blood | -0.033 |
bitten | -0.032 |
spilled | -0.028 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
blown | +0.003 |
blood | +0.003 |
bitten | +0.003 |
Blood | +0.003 |
spilled | +0.003 |
Neg logit contributions | |
aman | -0.006 |
heit | -0.006 |
destination | -0.006 |
ement | -0.006 |
isn | -0.006 |
Token | ric |
Token ID | 1173 |
Feature activation | -6.28e+00 |
Pos logit contributions | |
destination | +0.025 |
aman | +0.024 |
isn | +0.023 |
heit | +0.023 |
ement | +0.022 |
Neg logit contributions | |
blown | -0.033 |
blood | -0.033 |
Blood | -0.032 |
bitten | -0.032 |
spilled | -0.030 |
Token | hes |
Token ID | 956 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
blown | +0.058 |
blood | +0.055 |
Blood | +0.050 |
bitten | +0.050 |
spilled | +0.038 |
Neg logit contributions | |
isn | -0.239 |
heit | -0.235 |
destination | -0.235 |
aman | -0.231 |
ement | -0.229 |
Token | might |
Token ID | 1244 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
blown | +0.046 |
blood | +0.045 |
bitten | +0.044 |
Blood | +0.044 |
spilled | +0.041 |
Neg logit contributions | |
destination | -0.046 |
aman | -0.046 |
heit | -0.045 |
isn | -0.043 |
ement | -0.043 |
Token | pe |
Token ID | 613 |
Feature activation | -8.13e-02 |
Pos logit contributions | |
blown | +0.009 |
blood | +0.009 |
Blood | +0.008 |
bitten | +0.008 |
spilled | +0.007 |
Neg logit contributions | |
destination | -0.012 |
aman | -0.012 |
isn | -0.012 |
heit | -0.012 |
ement | -0.011 |
Token | ck |
Token ID | 694 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
blown | +0.002 |
blood | +0.002 |
Blood | +0.002 |
bitten | +0.002 |
spilled | +0.002 |
Neg logit contributions | |
destination | -0.002 |
heit | -0.002 |
aman | -0.002 |
isn | -0.002 |
ement | -0.002 |
Token | you |
Token ID | 345 |
Feature activation | -6.84e-02 |
Pos logit contributions | |
blown | +0.021 |
blood | +0.021 |
bitten | +0.020 |
Blood | +0.020 |
spilled | +0.018 |
Neg logit contributions | |
destination | -0.027 |
aman | -0.027 |
heit | -0.026 |
isn | -0.025 |
ement | -0.025 |
Token | but |
Token ID | 475 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
destination | +0.015 |
heit | +0.014 |
aman | +0.014 |
ement | +0.014 |
destinations | +0.013 |
Neg logit contributions | |
blood | -0.014 |
Blood | -0.012 |
blown | -0.012 |
bitten | -0.012 |
spilled | -0.012 |
Token | be |
Token ID | 307 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
destination | +0.093 |
heit | +0.091 |
ement | +0.090 |
aman | +0.090 |
isn | +0.087 |
Neg logit contributions | |
blood | -0.080 |
blown | -0.078 |
Blood | -0.077 |
bitten | -0.075 |
spilled | -0.067 |
Token | careful |
Token ID | 8161 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
blood | +0.004 |
bitten | +0.004 |
blown | +0.004 |
Blood | +0.004 |
hes | +0.004 |
Neg logit contributions | |
destination | -0.005 |
aman | -0.005 |
heit | -0.005 |
isn | -0.005 |
ement | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
destination | +0.047 |
aman | +0.047 |
heit | +0.046 |
ement | +0.043 |
isn | +0.042 |
Neg logit contributions | |
blood | -0.034 |
Blood | -0.034 |
blown | -0.033 |
bitten | -0.032 |
spilled | -0.029 |
Token | Ost |
Token ID | 38919 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
destination | +0.042 |
heit | +0.040 |
aman | +0.040 |
isn | +0.039 |
ement | +0.038 |
Neg logit contributions | |
Blood | -0.030 |
blood | -0.030 |
blown | -0.030 |
bitten | -0.028 |
spilled | -0.024 |
Token | ric |
Token ID | 1173 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
destination | +0.070 |
aman | +0.067 |
isn | +0.066 |
heit | +0.066 |
ement | +0.062 |
Neg logit contributions | |
blown | -0.084 |
blood | -0.083 |
Blood | -0.082 |
bitten | -0.081 |
spilled | -0.074 |
Token | hes |
Token ID | 956 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
blown | +0.063 |
blood | +0.057 |
Blood | +0.054 |
bitten | +0.054 |
spilled | +0.043 |
Neg logit contributions | |
isn | -0.232 |
heit | -0.228 |
destination | -0.225 |
hew | -0.223 |
exactly | -0.222 |
Token | can |
Token ID | 460 |
Feature activation | +6.16e-03 |
Pos logit contributions | |
blown | +0.032 |
blood | +0.032 |
Blood | +0.031 |
bitten | +0.031 |
spilled | +0.028 |
Neg logit contributions | |
destination | -0.024 |
aman | -0.024 |
heit | -0.023 |
ement | -0.022 |
isn | -0.022 |
Token | be |
Token ID | 307 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
destination | +0.000 |
aman | +0.000 |
isn | +0.000 |
heit | +0.000 |
mmm | +0.000 |
Neg logit contributions | |
blown | -0.000 |
Blood | -0.000 |
blood | -0.000 |
bitten | -0.000 |
elt | -0.000 |
Token | gr |
Token ID | 1036 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Blood | +0.038 |
blood | +0.038 |
blown | +0.038 |
bitten | +0.035 |
spilled | +0.032 |
Neg logit contributions | |
destination | -0.050 |
isn | -0.050 |
heit | -0.049 |
aman | -0.049 |
hew | -0.047 |
Token | umpy |
Token ID | 32152 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
blown | +0.021 |
blood | +0.021 |
Blood | +0.021 |
bitten | +0.020 |
spilled | +0.019 |
Neg logit contributions | |
destination | -0.027 |
isn | -0.026 |
aman | -0.026 |
hew | -0.026 |
heit | -0.026 |
Token | ostr |
Token ID | 42387 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
heit | +0.024 |
ement | +0.023 |
aman | +0.023 |
isn | +0.022 |
mmm | +0.022 |
Neg logit contributions | |
blood | -0.016 |
blown | -0.015 |
bitten | -0.014 |
Blood | -0.014 |
spilled | -0.014 |
Token | ich |
Token ID | 488 |
Feature activation | +9.10e-02 |
Pos logit contributions | |
blown | +0.001 |
blood | +0.001 |
Blood | +0.001 |
bitten | +0.001 |
spilled | +0.001 |
Neg logit contributions | |
destination | -0.002 |
aman | -0.002 |
isn | -0.002 |
heit | -0.001 |
ement | -0.001 |
Token | pen |
Token ID | 3112 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
heit | +0.003 |
aman | +0.002 |
destination | +0.002 |
isn | +0.002 |
mmm | +0.002 |
Neg logit contributions | |
blood | -0.002 |
blown | -0.002 |
bitten | -0.002 |
Blood | -0.002 |
spilled | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
destination | +0.016 |
heit | +0.016 |
aman | +0.016 |
isn | +0.016 |
ement | +0.015 |
Neg logit contributions | |
blown | -0.013 |
blood | -0.013 |
Blood | -0.013 |
bitten | -0.013 |
spilled | -0.012 |
Token | Ost |
Token ID | 38919 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
Blood | +0.012 |
blood | +0.011 |
blown | +0.011 |
bitten | +0.010 |
elt | +0.009 |
Neg logit contributions | |
destination | -0.032 |
heit | -0.031 |
aman | -0.031 |
hew | -0.030 |
ement | -0.030 |
Token | ric |
Token ID | 1173 |
Feature activation | -6.25e+00 |
Pos logit contributions | |
destination | +0.066 |
aman | +0.064 |
isn | +0.062 |
heit | +0.062 |
ement | +0.059 |
Neg logit contributions | |
blown | -0.083 |
blood | -0.082 |
Blood | -0.081 |
bitten | -0.080 |
spilled | -0.074 |
Token | hes |
Token ID | 956 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
blown | +0.071 |
blood | +0.065 |
bitten | +0.060 |
Blood | +0.058 |
spilled | +0.049 |
Neg logit contributions | |
isn | -0.221 |
heit | -0.215 |
exactly | -0.213 |
hew | -0.213 |
ement | -0.212 |
Token | are |
Token ID | 389 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
blown | +0.027 |
blood | +0.027 |
bitten | +0.026 |
Blood | +0.026 |
spilled | +0.025 |
Neg logit contributions | |
destination | -0.023 |
aman | -0.023 |
heit | -0.022 |
isn | -0.021 |
ement | -0.021 |
Token | big |
Token ID | 1263 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
blown | +0.013 |
blood | +0.013 |
Blood | +0.012 |
bitten | +0.012 |
spilled | +0.011 |
Neg logit contributions | |
destination | -0.018 |
aman | -0.018 |
heit | -0.018 |
isn | -0.018 |
ement | -0.017 |
Token | birds |
Token ID | 10087 |
Feature activation | -8.90e-01 |
Pos logit contributions | |
destination | +0.003 |
aman | +0.003 |
heit | +0.003 |
isn | +0.003 |
ement | +0.003 |
Neg logit contributions | |
blood | -0.002 |
blown | -0.002 |
bitten | -0.002 |
Blood | -0.002 |
spilled | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
blown | +0.018 |
blood | +0.018 |
bitten | +0.018 |
Blood | +0.017 |
spilled | +0.016 |
Neg logit contributions | |
destination | -0.026 |
heit | -0.025 |
aman | -0.025 |
isn | -0.024 |
ement | -0.023 |
Token | you |
Token ID | 345 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
destination | +0.040 |
aman | +0.039 |
heit | +0.039 |
isn | +0.038 |
ement | +0.036 |
Neg logit contributions | |
blown | -0.050 |
blood | -0.050 |
Blood | -0.049 |
bitten | -0.048 |
spilled | -0.044 |
Token | count |
Token ID | 954 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
blown | +0.034 |
blood | +0.034 |
Blood | +0.034 |
bitten | +0.033 |
spilled | +0.030 |
Neg logit contributions | |
destination | -0.044 |
isn | -0.042 |
aman | -0.042 |
heit | -0.042 |
ement | -0.039 |
Token | how |
Token ID | 703 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
aman | +0.057 |
destination | +0.057 |
heit | +0.056 |
ement | +0.054 |
isn | +0.053 |
Neg logit contributions | |
blood | -0.036 |
blown | -0.035 |
Blood | -0.035 |
bitten | -0.033 |
elt | -0.027 |
Token | many |
Token ID | 867 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
destination | +0.040 |
aman | +0.039 |
heit | +0.038 |
isn | +0.037 |
ement | +0.037 |
Neg logit contributions | |
blown | -0.022 |
Blood | -0.021 |
blood | -0.021 |
bitten | -0.020 |
spilled | -0.018 |
Token | ost |
Token ID | 23619 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
blown | +0.025 |
blood | +0.024 |
bitten | +0.023 |
Blood | +0.023 |
spilled | +0.020 |
Neg logit contributions | |
destination | -0.039 |
aman | -0.038 |
heit | -0.036 |
ement | -0.036 |
isn | -0.035 |
Token | ric |
Token ID | 1173 |
Feature activation | -6.19e+00 |
Pos logit contributions | |
destination | +0.018 |
isn | +0.017 |
aman | +0.017 |
heit | +0.016 |
hew | +0.016 |
Neg logit contributions | |
blood | -0.024 |
blown | -0.024 |
Blood | -0.024 |
bitten | -0.024 |
spilled | -0.022 |
Token | hes |
Token ID | 956 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
blood | +0.087 |
blown | +0.087 |
Blood | +0.079 |
bitten | +0.078 |
spilled | +0.069 |
Neg logit contributions | |
isn | -0.204 |
heit | -0.199 |
destination | -0.197 |
ement | -0.193 |
hew | -0.192 |
Token | there |
Token ID | 612 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
blown | +0.055 |
blood | +0.054 |
Blood | +0.053 |
bitten | +0.052 |
spilled | +0.048 |
Neg logit contributions | |
destination | -0.055 |
aman | -0.054 |
heit | -0.053 |
isn | -0.052 |
ement | -0.050 |
Token | are |
Token ID | 389 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
blown | +0.009 |
blood | +0.009 |
Blood | +0.008 |
bitten | +0.008 |
spilled | +0.008 |
Neg logit contributions | |
aman | -0.007 |
destination | -0.007 |
heit | -0.007 |
isn | -0.007 |
ement | -0.007 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
blown | +0.033 |
blood | +0.032 |
Blood | +0.032 |
bitten | +0.032 |
spilled | +0.028 |
Neg logit contributions | |
destination | -0.040 |
aman | -0.039 |
heit | -0.038 |
isn | -0.038 |
ement | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
blown | +0.005 |
blood | +0.004 |
bitten | +0.004 |
Blood | +0.004 |
spilled | +0.004 |
Neg logit contributions | |
isn | -0.005 |
destination | -0.005 |
aman | -0.005 |
heit | -0.005 |
ement | -0.005 |
Token | should |
Token ID | 815 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
isn | +0.006 |
destination | +0.006 |
hew | +0.006 |
heit | +0.005 |
exactly | +0.005 |
Neg logit contributions | |
Blood | -0.008 |
blood | -0.008 |
blown | -0.008 |
bitten | -0.007 |
eh | -0.007 |
Token | not |
Token ID | 407 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
destination | +0.050 |
aman | +0.049 |
heit | +0.048 |
isn | +0.048 |
ement | +0.047 |
Neg logit contributions | |
blown | -0.040 |
blood | -0.040 |
Blood | -0.039 |
bitten | -0.039 |
spilled | -0.035 |
Token | tease |
Token ID | 34691 |
Feature activation | -7.08e-02 |
Pos logit contributions | |
blown | +0.023 |
Blood | +0.023 |
blood | +0.023 |
bitten | +0.022 |
spilled | +0.019 |
Neg logit contributions | |
destination | -0.037 |
isn | -0.036 |
aman | -0.036 |
heit | -0.036 |
hew | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -9.98e-01 |
Pos logit contributions | |
blood | +0.002 |
blown | +0.002 |
Blood | +0.002 |
bitten | +0.002 |
spilled | +0.001 |
Neg logit contributions | |
destination | -0.002 |
aman | -0.002 |
heit | -0.002 |
ement | -0.002 |
isn | -0.002 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
blown | +0.024 |
blood | +0.024 |
bitten | +0.023 |
Blood | +0.023 |
spilled | +0.021 |
Neg logit contributions | |
destination | -0.025 |
heit | -0.024 |
aman | -0.024 |
isn | -0.024 |
ement | -0.023 |
Token | ric |
Token ID | 1173 |
Feature activation | -6.17e+00 |
Pos logit contributions | |
destination | +0.025 |
aman | +0.024 |
isn | +0.024 |
heit | +0.024 |
ement | +0.023 |
Neg logit contributions | |
blown | -0.032 |
blood | -0.032 |
Blood | -0.032 |
bitten | -0.031 |
spilled | -0.029 |
Token | hes |
Token ID | 956 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
blown | +0.063 |
blood | +0.059 |
Blood | +0.056 |
bitten | +0.054 |
spilled | +0.043 |
Neg logit contributions | |
isn | -0.227 |
heit | -0.224 |
destination | -0.222 |
aman | -0.219 |
hew | -0.218 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
blood | +0.041 |
blown | +0.040 |
bitten | +0.039 |
Blood | +0.038 |
spilled | +0.035 |
Neg logit contributions | |
destination | -0.053 |
aman | -0.053 |
heit | -0.052 |
ement | -0.050 |
isn | -0.049 |
Token | They |
Token ID | 1119 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
destination | +0.035 |
aman | +0.033 |
heit | +0.033 |
isn | +0.032 |
ement | +0.031 |
Neg logit contributions | |
Blood | -0.021 |
blood | -0.020 |
blown | -0.020 |
bitten | -0.019 |
spilled | -0.016 |
Token | are |
Token ID | 389 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
blown | +0.003 |
blood | +0.003 |
Blood | +0.003 |
bitten | +0.003 |
spilled | +0.002 |
Neg logit contributions | |
destination | -0.002 |
isn | -0.002 |
aman | -0.002 |
heit | -0.002 |
ement | -0.002 |
Token | not |
Token ID | 407 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
destination | +0.016 |
isn | +0.016 |
heit | +0.016 |
aman | +0.016 |
exactly | +0.015 |
Neg logit contributions | |
Blood | -0.018 |
blown | -0.018 |
blood | -0.018 |
bitten | -0.017 |
spilled | -0.016 |
Token | ostr |
Token ID | 42387 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
heit | +0.023 |
ement | +0.023 |
aman | +0.023 |
isn | +0.022 |
mmm | +0.022 |
Neg logit contributions | |
blood | -0.015 |
blown | -0.014 |
bitten | -0.014 |
Blood | -0.014 |
spilled | -0.013 |
Token | ich |
Token ID | 488 |
Feature activation | +5.82e-02 |
Pos logit contributions | |
destination | +0.005 |
aman | +0.005 |
isn | +0.005 |
heit | +0.005 |
ement | +0.005 |
Neg logit contributions | |
blown | -0.003 |
blood | -0.003 |
Blood | -0.003 |
bitten | -0.003 |
spilled | -0.002 |
Token | pen |
Token ID | 3112 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
heit | +0.002 |
aman | +0.002 |
isn | +0.002 |
destination | +0.002 |
ement | +0.001 |
Neg logit contributions | |
blood | -0.001 |
blown | -0.001 |
bitten | -0.001 |
Blood | -0.001 |
spilled | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
destination | +0.014 |
heit | +0.014 |
aman | +0.014 |
isn | +0.014 |
ement | +0.013 |
Neg logit contributions | |
blown | -0.012 |
blood | -0.012 |
Blood | -0.011 |
bitten | -0.011 |
spilled | -0.010 |
Token | Ost |
Token ID | 38919 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
Blood | +0.005 |
blood | +0.005 |
blown | +0.004 |
bitten | +0.004 |
elt | +0.003 |
Neg logit contributions | |
destination | -0.017 |
heit | -0.017 |
aman | -0.017 |
ement | -0.016 |
hew | -0.016 |
Token | ric |
Token ID | 1173 |
Feature activation | -6.14e+00 |
Pos logit contributions | |
destination | +0.071 |
aman | +0.068 |
isn | +0.067 |
heit | +0.067 |
ement | +0.063 |
Neg logit contributions | |
blown | -0.087 |
blood | -0.086 |
Blood | -0.085 |
bitten | -0.084 |
spilled | -0.077 |
Token | hes |
Token ID | 956 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
blown | +0.070 |
blood | +0.063 |
bitten | +0.059 |
Blood | +0.057 |
spilled | +0.049 |
Neg logit contributions | |
isn | -0.219 |
heit | -0.213 |
hew | -0.210 |
exactly | -0.210 |
destination | -0.209 |
Token | are |
Token ID | 389 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
blood | +0.026 |
blown | +0.026 |
Blood | +0.026 |
bitten | +0.025 |
spilled | +0.023 |
Neg logit contributions | |
destination | -0.024 |
aman | -0.023 |
heit | -0.022 |
isn | -0.022 |
ement | -0.022 |
Token | big |
Token ID | 1263 |
Feature activation | -2.10e-04 |
Pos logit contributions | |
blown | +0.015 |
blood | +0.014 |
Blood | +0.014 |
bitten | +0.014 |
spilled | +0.012 |
Neg logit contributions | |
destination | -0.021 |
aman | -0.020 |
isn | -0.020 |
heit | -0.020 |
ement | -0.019 |
Token | birds |
Token ID | 10087 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
blood | +0.000 |
blown | +0.000 |
bitten | +0.000 |
Blood | +0.000 |
spilled | +0.000 |
Neg logit contributions | |
destination | -0.000 |
aman | -0.000 |
heit | -0.000 |
isn | -0.000 |
ement | -0.000 |
Token | with |
Token ID | 351 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
blown | +0.018 |
blood | +0.018 |
bitten | +0.018 |
Blood | +0.017 |
spilled | +0.016 |
Neg logit contributions | |
destination | -0.026 |
aman | -0.026 |
heit | -0.026 |
isn | -0.024 |
ement | -0.024 |
Token | cried |
Token ID | 16896 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
blown | +0.038 |
Blood | +0.037 |
blood | +0.036 |
bitten | +0.036 |
spilled | +0.031 |
Neg logit contributions | |
destination | -0.048 |
isn | -0.047 |
aman | -0.046 |
heit | -0.046 |
hew | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
blown | +0.118 |
Blood | +0.111 |
bitten | +0.111 |
eh | +0.104 |
spilled | +0.103 |
Neg logit contributions | |
forever | -0.041 |
destination | -0.038 |
exactly | -0.038 |
isn | -0.037 |
ement | -0.035 |
Token | " |
Token ID | 366 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
blown | +0.019 |
bitten | +0.018 |
blood | +0.017 |
eh | +0.016 |
Blood | +0.016 |
Neg logit contributions | |
isn | -0.018 |
destination | -0.017 |
aman | -0.017 |
heit | -0.016 |
ement | -0.016 |
Token | The |
Token ID | 464 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
So | +0.007 |
� | +0.007 |
isn | +0.007 |
hew | +0.007 |
heit | +0.006 |
Neg logit contributions | |
blown | -0.012 |
bitten | -0.011 |
blood | -0.010 |
robbers | -0.010 |
ses | -0.010 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
Blood | +0.008 |
blown | +0.007 |
bitten | +0.007 |
blood | +0.007 |
elt | +0.006 |
Neg logit contributions | |
destination | -0.011 |
isn | -0.011 |
aman | -0.011 |
heit | -0.011 |
ement | -0.010 |
Token | ric |
Token ID | 1173 |
Feature activation | -6.13e+00 |
Pos logit contributions | |
destination | +0.028 |
aman | +0.027 |
heit | +0.027 |
isn | +0.027 |
hew | +0.025 |
Neg logit contributions | |
blown | -0.047 |
Blood | -0.047 |
blood | -0.046 |
bitten | -0.045 |
spilled | -0.043 |
Token | hes |
Token ID | 956 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
blown | +0.078 |
blood | +0.064 |
bitten | +0.064 |
robbers | +0.064 |
Blood | +0.063 |
Neg logit contributions | |
isn | -0.208 |
heit | -0.201 |
exactly | -0.200 |
hew | -0.199 |
ement | -0.195 |
Token | are |
Token ID | 389 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
blown | +0.065 |
blood | +0.064 |
Blood | +0.064 |
bitten | +0.063 |
spilled | +0.057 |
Neg logit contributions | |
destination | -0.047 |
aman | -0.045 |
isn | -0.045 |
heit | -0.045 |
ement | -0.042 |
Token | mean |
Token ID | 1612 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
Blood | +0.007 |
blown | +0.007 |
blood | +0.007 |
bitten | +0.007 |
elt | +0.006 |
Neg logit contributions | |
isn | -0.009 |
heit | -0.009 |
destination | -0.009 |
aman | -0.009 |
exactly | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
blood | +0.054 |
blown | +0.053 |
bitten | +0.053 |
Blood | +0.052 |
spilled | +0.048 |
Neg logit contributions | |
destination | -0.036 |
aman | -0.034 |
heit | -0.033 |
ement | -0.032 |
isn | -0.032 |
Token | They |
Token ID | 1119 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
isn | +0.000 |
destination | +0.000 |
aman | +0.000 |
heit | +0.000 |
ement | +0.000 |
Neg logit contributions | |
blown | -0.000 |
blood | -0.000 |
bitten | -0.000 |
Blood | -0.000 |
spilled | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
blown | +0.039 |
blood | +0.039 |
Blood | +0.039 |
bitten | +0.038 |
spilled | +0.033 |
Neg logit contributions | |
destination | -0.052 |
aman | -0.050 |
heit | -0.050 |
isn | -0.049 |
ement | -0.047 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Blood | +0.012 |
blood | +0.011 |
blown | +0.011 |
bitten | +0.011 |
spilled | +0.009 |
Neg logit contributions | |
destination | -0.022 |
heit | -0.022 |
aman | -0.022 |
isn | -0.021 |
ement | -0.021 |
Token | With |
Token ID | 3152 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
Blood | +0.025 |
blown | +0.024 |
blood | +0.023 |
bitten | +0.023 |
spilled | +0.021 |
Neg logit contributions | |
destination | -0.029 |
heit | -0.028 |
aman | -0.027 |
isn | -0.027 |
ement | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
destination | +0.017 |
aman | +0.016 |
isn | +0.016 |
heit | +0.016 |
ement | +0.016 |
Neg logit contributions | |
blown | -0.008 |
blood | -0.008 |
Blood | -0.008 |
bitten | -0.007 |
spilled | -0.006 |
Token | mis |
Token ID | 2984 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
destination | +0.014 |
aman | +0.014 |
isn | +0.014 |
heit | +0.014 |
ement | +0.014 |
Neg logit contributions | |
blood | -0.008 |
blown | -0.008 |
Blood | -0.008 |
bitten | -0.008 |
spilled | -0.007 |
Token | chie |
Token ID | 3043 |
Feature activation | -5.94e+00 |
Pos logit contributions | |
blown | +0.037 |
bitten | +0.035 |
Blood | +0.035 |
blood | +0.035 |
spilled | +0.028 |
Neg logit contributions | |
destination | -0.065 |
aman | -0.063 |
isn | -0.063 |
heit | -0.062 |
ement | -0.059 |
Token | vous |
Token ID | 31222 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
blown | +0.087 |
blood | +0.085 |
Blood | +0.084 |
bitten | +0.081 |
spilled | +0.068 |
Neg logit contributions | |
destination | -0.201 |
aman | -0.196 |
isn | -0.194 |
heit | -0.194 |
ement | -0.187 |
Token | gl |
Token ID | 1278 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
blood | +0.024 |
blown | +0.024 |
Blood | +0.023 |
bitten | +0.023 |
spilled | +0.021 |
Neg logit contributions | |
destination | -0.032 |
aman | -0.031 |
heit | -0.030 |
isn | -0.030 |
ement | -0.029 |
Token | int |
Token ID | 600 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
destination | +0.009 |
aman | +0.009 |
heit | +0.009 |
isn | +0.008 |
ement | +0.008 |
Neg logit contributions | |
blown | -0.014 |
blood | -0.013 |
Blood | -0.013 |
bitten | -0.013 |
spilled | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
blown | +0.054 |
Blood | +0.054 |
blood | +0.053 |
bitten | +0.051 |
spilled | +0.046 |
Neg logit contributions | |
destination | -0.063 |
isn | -0.062 |
aman | -0.061 |
heit | -0.061 |
ement | -0.059 |
Token | her |
Token ID | 607 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
destination | +0.021 |
aman | +0.021 |
heit | +0.020 |
isn | +0.020 |
hew | +0.020 |
Neg logit contributions | |
blood | -0.009 |
blown | -0.009 |
Blood | -0.009 |
bitten | -0.009 |
spilled | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
blown | +0.042 |
blood | +0.041 |
Blood | +0.041 |
bitten | +0.040 |
spilled | +0.036 |
Neg logit contributions | |
destination | -0.043 |
aman | -0.041 |
isn | -0.041 |
heit | -0.040 |
ement | -0.039 |
Token | They |
Token ID | 1119 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Blood | +0.004 |
blood | +0.003 |
blown | +0.003 |
bitten | +0.003 |
elt | +0.003 |
Neg logit contributions | |
heit | -0.011 |
destination | -0.011 |
aman | -0.010 |
ement | -0.010 |
isn | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
blown | +0.019 |
blood | +0.019 |
Blood | +0.019 |
bitten | +0.018 |
spilled | +0.016 |
Neg logit contributions | |
destination | -0.030 |
aman | -0.029 |
isn | -0.029 |
heit | -0.029 |
ement | -0.028 |
Token | called |
Token ID | 1444 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
blown | +0.003 |
blood | +0.003 |
Blood | +0.003 |
bitten | +0.003 |
spilled | +0.002 |
Neg logit contributions | |
destination | -0.003 |
aman | -0.003 |
heit | -0.003 |
isn | -0.003 |
ement | -0.003 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
blown | +0.028 |
blood | +0.028 |
Blood | +0.027 |
bitten | +0.027 |
spilled | +0.024 |
Neg logit contributions | |
destination | -0.030 |
aman | -0.029 |
heit | -0.029 |
isn | -0.029 |
hew | -0.028 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
destination | +0.033 |
aman | +0.032 |
isn | +0.032 |
heit | +0.032 |
ement | +0.030 |
Neg logit contributions | |
blown | -0.035 |
blood | -0.034 |
Blood | -0.034 |
bitten | -0.034 |
spilled | -0.030 |
Token | hes |
Token ID | 956 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
blood | +0.062 |
blown | +0.062 |
Blood | +0.057 |
bitten | +0.055 |
spilled | +0.044 |
Neg logit contributions | |
isn | -0.211 |
heit | -0.210 |
destination | -0.209 |
ement | -0.205 |
exactly | -0.204 |
Token | . |
Token ID | 13 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
blown | +0.025 |
blood | +0.024 |
Blood | +0.024 |
bitten | +0.024 |
spilled | +0.021 |
Neg logit contributions | |
destination | -0.031 |
aman | -0.030 |
heit | -0.030 |
isn | -0.029 |
ement | -0.028 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
Blood | +0.000 |
blood | +0.000 |
blown | +0.000 |
bitten | +0.000 |
elt | +0.000 |
Neg logit contributions | |
destination | -0.000 |
heit | -0.000 |
aman | -0.000 |
isn | -0.000 |
ement | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
blown | +0.007 |
bitten | +0.006 |
Blood | +0.006 |
spilled | +0.006 |
blood | +0.006 |
Neg logit contributions | |
destination | -0.013 |
heit | -0.012 |
aman | -0.012 |
ement | -0.012 |
mmm | -0.012 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
blown | +0.028 |
Blood | +0.027 |
blood | +0.027 |
bitten | +0.026 |
spilled | +0.023 |
Neg logit contributions | |
destination | -0.031 |
aman | -0.031 |
isn | -0.030 |
heit | -0.030 |
exactly | -0.027 |
Token | shouted |
Token ID | 17293 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
blown | +0.018 |
blood | +0.018 |
Blood | +0.018 |
bitten | +0.017 |
spilled | +0.015 |
Neg logit contributions | |
destination | -0.022 |
aman | -0.021 |
heit | -0.021 |
isn | -0.021 |
ement | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
blown | +0.082 |
blood | +0.080 |
Blood | +0.080 |
bitten | +0.078 |
spilled | +0.071 |
Neg logit contributions | |
destination | -0.066 |
isn | -0.063 |
aman | -0.062 |
heit | -0.061 |
ement | -0.060 |
Token | " |
Token ID | 366 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
blown | +0.044 |
bitten | +0.041 |
blood | +0.039 |
orns | +0.039 |
spilled | +0.037 |
Neg logit contributions | |
isn | -0.025 |
destination | -0.024 |
aman | -0.021 |
So | -0.021 |
So | -0.021 |
Token | The |
Token ID | 464 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
isn | +0.004 |
aman | +0.004 |
destination | +0.004 |
So | +0.004 |
hew | +0.004 |
Neg logit contributions | |
blown | -0.005 |
blood | -0.005 |
bitten | -0.005 |
Blood | -0.005 |
spilled | -0.005 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
blood | +0.009 |
blown | +0.009 |
Blood | +0.008 |
bitten | +0.008 |
spilled | +0.007 |
Neg logit contributions | |
destination | -0.018 |
aman | -0.018 |
heit | -0.018 |
isn | -0.018 |
ement | -0.017 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.91e+00 |
Pos logit contributions | |
destination | +0.034 |
aman | +0.033 |
isn | +0.032 |
heit | +0.032 |
ement | +0.030 |
Neg logit contributions | |
blown | -0.048 |
blood | -0.048 |
Blood | -0.047 |
bitten | -0.047 |
spilled | -0.043 |
Token | hes |
Token ID | 956 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
blown | +0.062 |
blood | +0.056 |
bitten | +0.052 |
Blood | +0.050 |
spilled | +0.042 |
Neg logit contributions | |
isn | -0.216 |
heit | -0.213 |
ement | -0.208 |
destination | -0.208 |
hew | -0.207 |
Token | are |
Token ID | 389 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
blown | +0.059 |
blood | +0.058 |
Blood | +0.057 |
bitten | +0.057 |
spilled | +0.053 |
Neg logit contributions | |
destination | -0.049 |
aman | -0.049 |
heit | -0.047 |
isn | -0.046 |
ement | -0.045 |
Token | so |
Token ID | 523 |
Feature activation | +3.83e-01 |
Pos logit contributions | |
blown | +0.011 |
blood | +0.010 |
Blood | +0.010 |
bitten | +0.010 |
spilled | +0.009 |
Neg logit contributions | |
destination | -0.014 |
aman | -0.014 |
heit | -0.013 |
isn | -0.013 |
ement | -0.013 |
Token | funny |
Token ID | 8258 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
destination | +0.012 |
aman | +0.011 |
heit | +0.011 |
ement | +0.011 |
isn | +0.011 |
Neg logit contributions | |
blown | -0.008 |
Blood | -0.008 |
bitten | -0.007 |
blood | -0.007 |
spilled | -0.006 |
Token | !" |
Token ID | 2474 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
blown | +0.004 |
blood | +0.004 |
bitten | +0.004 |
Blood | +0.004 |
spilled | +0.004 |
Neg logit contributions | |
destination | -0.004 |
aman | -0.004 |
heit | -0.003 |
ement | -0.003 |
bek | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
blown | +0.033 |
Blood | +0.033 |
bitten | +0.031 |
blood | +0.031 |
spilled | +0.028 |
Neg logit contributions | |
destination | -0.038 |
aman | -0.037 |
isn | -0.035 |
heit | -0.035 |
ement | -0.034 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
blown | +0.002 |
blood | +0.002 |
Blood | +0.002 |
bitten | +0.002 |
spilled | +0.002 |
Neg logit contributions | |
destination | -0.003 |
aman | -0.003 |
heit | -0.003 |
isn | -0.003 |
ement | -0.003 |
Token | at |
Token ID | 379 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
aman | +0.050 |
destination | +0.049 |
mmm | +0.047 |
heit | +0.047 |
hew | +0.045 |
Neg logit contributions | |
blood | -0.035 |
blown | -0.034 |
bitten | -0.033 |
spilled | -0.031 |
Blood | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
destination | +0.045 |
aman | +0.044 |
isn | +0.043 |
heit | +0.043 |
ement | +0.041 |
Neg logit contributions | |
blown | -0.037 |
Blood | -0.036 |
bitten | -0.035 |
blood | -0.035 |
spilled | -0.031 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
blown | +0.005 |
blood | +0.004 |
bitten | +0.004 |
Blood | +0.004 |
spilled | +0.004 |
Neg logit contributions | |
destination | -0.006 |
heit | -0.006 |
aman | -0.006 |
isn | -0.006 |
ement | -0.005 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
destination | +0.034 |
aman | +0.032 |
isn | +0.032 |
heit | +0.032 |
ement | +0.030 |
Neg logit contributions | |
blown | -0.040 |
blood | -0.040 |
Blood | -0.040 |
bitten | -0.039 |
spilled | -0.036 |
Token | hes |
Token ID | 956 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
blown | +0.055 |
blood | +0.052 |
bitten | +0.048 |
Blood | +0.047 |
spilled | +0.036 |
Neg logit contributions | |
isn | -0.220 |
heit | -0.218 |
destination | -0.218 |
aman | -0.214 |
ement | -0.214 |
Token | . |
Token ID | 13 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
blown | +0.025 |
blood | +0.025 |
Blood | +0.024 |
bitten | +0.024 |
spilled | +0.022 |
Neg logit contributions | |
destination | -0.030 |
aman | -0.030 |
heit | -0.030 |
isn | -0.029 |
ement | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
blown | +0.010 |
blood | +0.010 |
Blood | +0.010 |
bitten | +0.009 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.020 |
aman | -0.020 |
heit | -0.019 |
isn | -0.019 |
ement | -0.019 |
Token | saw |
Token ID | 2497 |
Feature activation | +1.51e-01 |
Pos logit contributions | |
blown | +0.009 |
blood | +0.009 |
Blood | +0.009 |
bitten | +0.009 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.014 |
aman | -0.014 |
isn | -0.014 |
heit | -0.014 |
ement | -0.013 |
Token | one |
Token ID | 530 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
destination | +0.004 |
isn | +0.004 |
aman | +0.004 |
exactly | +0.004 |
heit | +0.004 |
Neg logit contributions | |
Blood | -0.003 |
blown | -0.003 |
bitten | -0.003 |
blood | -0.003 |
opener | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | +8.62e-01 |
Pos logit contributions | |
aman | +0.018 |
destination | +0.018 |
heit | +0.017 |
isn | +0.017 |
hew | +0.016 |
Neg logit contributions | |
blown | -0.014 |
blood | -0.014 |
Blood | -0.013 |
bitten | -0.013 |
spilled | -0.012 |
Token | that |
Token ID | 326 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
destination | +0.028 |
aman | +0.027 |
heit | +0.027 |
isn | +0.027 |
ement | +0.026 |
Neg logit contributions | |
blown | -0.014 |
blood | -0.014 |
Blood | -0.014 |
bitten | -0.013 |
spilled | -0.011 |
Token | no |
Token ID | 645 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ement | +0.047 |
heit | +0.047 |
aman | +0.046 |
destination | +0.045 |
hew | +0.044 |
Neg logit contributions | |
blown | -0.014 |
blood | -0.013 |
bitten | -0.013 |
spilled | -0.012 |
hurt | -0.011 |
Token | more |
Token ID | 517 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
blood | +0.004 |
blown | +0.004 |
bitten | +0.004 |
Blood | +0.004 |
spilled | +0.004 |
Neg logit contributions | |
heit | -0.006 |
destination | -0.005 |
aman | -0.005 |
isn | -0.005 |
hew | -0.005 |
Token | mis |
Token ID | 2984 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
blood | +0.021 |
blown | +0.021 |
bitten | +0.020 |
Blood | +0.019 |
spilled | +0.018 |
Neg logit contributions | |
aman | -0.026 |
heit | -0.026 |
destination | -0.026 |
hew | -0.025 |
isn | -0.024 |
Token | chie |
Token ID | 3043 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
Blood | +0.055 |
blood | +0.055 |
blown | +0.052 |
spilled | +0.050 |
bitten | +0.050 |
Neg logit contributions | |
destination | -0.053 |
aman | -0.051 |
heit | -0.050 |
hew | -0.050 |
isn | -0.049 |
Token | vous |
Token ID | 31222 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
blown | +0.094 |
blood | +0.092 |
Blood | +0.091 |
bitten | +0.088 |
spilled | +0.075 |
Neg logit contributions | |
destination | -0.190 |
aman | -0.185 |
isn | -0.184 |
heit | -0.183 |
ement | -0.176 |
Token | mice |
Token ID | 10693 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
blood | +0.013 |
blown | +0.013 |
bitten | +0.013 |
Blood | +0.012 |
spilled | +0.011 |
Neg logit contributions | |
destination | -0.017 |
aman | -0.016 |
heit | -0.016 |
isn | -0.016 |
ement | -0.015 |
Token | could |
Token ID | 714 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
blown | +0.009 |
blood | +0.009 |
bitten | +0.009 |
Blood | +0.009 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.012 |
aman | -0.012 |
heit | -0.012 |
ement | -0.011 |
isn | -0.011 |
Token | come |
Token ID | 1282 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
blown | +0.030 |
blood | +0.029 |
Blood | +0.029 |
bitten | +0.028 |
spilled | +0.025 |
Neg logit contributions | |
destination | -0.040 |
aman | -0.039 |
heit | -0.039 |
isn | -0.039 |
ement | -0.037 |
Token | in |
Token ID | 287 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
blown | +0.026 |
blood | +0.025 |
bitten | +0.024 |
Blood | +0.024 |
spilled | +0.021 |
Neg logit contributions | |
heit | -0.032 |
aman | -0.032 |
destination | -0.032 |
isn | -0.031 |
ement | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -7.72e-01 |
Pos logit contributions | |
Blood | +0.008 |
blood | +0.008 |
blown | +0.008 |
bitten | +0.007 |
spilled | +0.006 |
Neg logit contributions | |
destination | -0.013 |
heit | -0.013 |
aman | -0.013 |
isn | -0.013 |
ement | -0.012 |
Token | One |
Token ID | 3198 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
Blood | +0.018 |
blood | +0.017 |
blown | +0.017 |
Tweet | +0.017 |
bitten | +0.016 |
Neg logit contributions | |
destination | -0.021 |
aman | -0.019 |
heit | -0.019 |
isn | -0.019 |
ement | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
destination | +0.025 |
isn | +0.024 |
aman | +0.024 |
heit | +0.023 |
ement | +0.022 |
Neg logit contributions | |
blown | -0.035 |
blood | -0.035 |
Blood | -0.034 |
bitten | -0.034 |
spilled | -0.030 |
Token | a |
Token ID | 257 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
blown | +0.048 |
blood | +0.048 |
Blood | +0.047 |
bitten | +0.047 |
spilled | +0.043 |
Neg logit contributions | |
destination | -0.031 |
aman | -0.030 |
isn | -0.030 |
heit | -0.029 |
ement | -0.027 |
Token | mis |
Token ID | 2984 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
destination | +0.031 |
aman | +0.030 |
isn | +0.030 |
heit | +0.030 |
ement | +0.029 |
Neg logit contributions | |
blown | -0.021 |
blood | -0.021 |
Blood | -0.020 |
bitten | -0.020 |
spilled | -0.018 |
Token | chie |
Token ID | 3043 |
Feature activation | -5.84e+00 |
Pos logit contributions | |
blood | +0.022 |
blown | +0.022 |
Blood | +0.022 |
bitten | +0.021 |
spilled | +0.020 |
Neg logit contributions | |
destination | -0.027 |
aman | -0.027 |
heit | -0.026 |
isn | -0.026 |
hew | -0.026 |
Token | vous |
Token ID | 31222 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
blood | +0.097 |
blown | +0.096 |
Blood | +0.092 |
bitten | +0.088 |
spilled | +0.077 |
Neg logit contributions | |
isn | -0.182 |
destination | -0.182 |
aman | -0.180 |
heit | -0.178 |
ement | -0.172 |
Token | monkey |
Token ID | 21657 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
blown | +0.004 |
Blood | +0.004 |
bitten | +0.004 |
blood | +0.004 |
spilled | +0.003 |
Neg logit contributions | |
isn | -0.009 |
destination | -0.008 |
aman | -0.008 |
heit | -0.008 |
ement | -0.008 |
Token | saw |
Token ID | 2497 |
Feature activation | -8.03e-02 |
Pos logit contributions | |
Blood | +0.016 |
blood | +0.016 |
blown | +0.016 |
bitten | +0.015 |
spilled | +0.012 |
Neg logit contributions | |
destination | -0.026 |
isn | -0.026 |
aman | -0.025 |
heit | -0.025 |
hew | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
blown | +0.002 |
Blood | +0.002 |
blood | +0.002 |
bitten | +0.002 |
spilled | +0.001 |
Neg logit contributions | |
isn | -0.002 |
destination | -0.002 |
aman | -0.002 |
heit | -0.002 |
exactly | -0.002 |
Token | bear |
Token ID | 6842 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
blown | +0.011 |
Blood | +0.011 |
blood | +0.010 |
bitten | +0.010 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.022 |
isn | -0.021 |
aman | -0.020 |
heit | -0.020 |
ement | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
blown | +0.001 |
Blood | +0.001 |
blood | +0.001 |
bitten | +0.001 |
spilled | +0.001 |
Neg logit contributions | |
isn | -0.002 |
destination | -0.002 |
aman | -0.002 |
ement | -0.002 |
heit | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
blown | +0.022 |
blood | +0.021 |
bitten | +0.020 |
Blood | +0.019 |
spilled | +0.018 |
Neg logit contributions | |
isn | -0.029 |
destination | -0.029 |
aman | -0.029 |
heit | -0.027 |
ement | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
blown | +0.036 |
blood | +0.035 |
Blood | +0.034 |
bitten | +0.034 |
elt | +0.031 |
Neg logit contributions | |
isn | -0.024 |
destination | -0.021 |
heit | -0.021 |
aman | -0.020 |
hew | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -5.27e-01 |
Pos logit contributions | |
blood | +0.034 |
blown | +0.034 |
Blood | +0.033 |
bitten | +0.033 |
orns | +0.031 |
Neg logit contributions | |
exactly | -0.021 |
destination | -0.020 |
isn | -0.019 |
forever | -0.018 |
equally | -0.017 |
Token | mis |
Token ID | 2984 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
blown | +0.011 |
blood | +0.010 |
Blood | +0.010 |
bitten | +0.010 |
spilled | +0.009 |
Neg logit contributions | |
destination | -0.015 |
aman | -0.015 |
isn | -0.014 |
heit | -0.014 |
ement | -0.014 |
Token | chie |
Token ID | 3043 |
Feature activation | -5.80e+00 |
Pos logit contributions | |
blood | +0.044 |
Blood | +0.042 |
blown | +0.042 |
bitten | +0.041 |
spilled | +0.038 |
Neg logit contributions | |
destination | -0.052 |
aman | -0.050 |
heit | -0.049 |
isn | -0.048 |
hew | -0.048 |
Token | vous |
Token ID | 31222 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
blood | +0.099 |
blown | +0.098 |
Blood | +0.093 |
bitten | +0.091 |
spilled | +0.078 |
Neg logit contributions | |
isn | -0.179 |
destination | -0.178 |
aman | -0.176 |
heit | -0.173 |
ement | -0.169 |
Token | little |
Token ID | 1310 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
blown | +0.022 |
blood | +0.022 |
Blood | +0.022 |
bitten | +0.021 |
spilled | +0.018 |
Neg logit contributions | |
destination | -0.046 |
aman | -0.045 |
heit | -0.045 |
isn | -0.045 |
ement | -0.043 |
Token | baby |
Token ID | 5156 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
blown | +0.022 |
Blood | +0.022 |
blood | +0.021 |
bitten | +0.021 |
spilled | +0.017 |
Neg logit contributions | |
destination | -0.034 |
isn | -0.033 |
aman | -0.032 |
heit | -0.031 |
ement | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
blood | +0.009 |
blown | +0.009 |
bitten | +0.009 |
Blood | +0.009 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.011 |
heit | -0.011 |
aman | -0.011 |
isn | -0.011 |
ement | -0.010 |
Token | always |
Token ID | 1464 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
blown | +0.006 |
blood | +0.006 |
Blood | +0.006 |
bitten | +0.006 |
spilled | +0.005 |
Neg logit contributions | |
isn | -0.006 |
destination | -0.006 |
heit | -0.006 |
aman | -0.006 |
ement | -0.006 |
Token | One |
Token ID | 3198 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
Blood | +0.018 |
blown | +0.018 |
blood | +0.017 |
bitten | +0.017 |
spilled | +0.016 |
Neg logit contributions | |
destination | -0.015 |
heit | -0.014 |
aman | -0.014 |
isn | -0.013 |
ement | -0.013 |
Token | day |
Token ID | 1110 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
destination | +0.016 |
isn | +0.016 |
aman | +0.016 |
heit | +0.015 |
ement | +0.014 |
Neg logit contributions | |
blown | -0.019 |
blood | -0.019 |
Blood | -0.019 |
bitten | -0.019 |
spilled | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
blown | +0.051 |
blood | +0.050 |
Blood | +0.050 |
bitten | +0.049 |
spilled | +0.045 |
Neg logit contributions | |
destination | -0.031 |
aman | -0.029 |
isn | -0.029 |
heit | -0.029 |
ement | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +6.59e-01 |
Pos logit contributions | |
blown | +0.006 |
bitten | +0.005 |
blood | +0.005 |
Blood | +0.005 |
spilled | +0.004 |
Neg logit contributions | |
isn | -0.008 |
destination | -0.008 |
exactly | -0.008 |
heit | -0.008 |
aman | -0.007 |
Token | mis |
Token ID | 2984 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
destination | +0.020 |
aman | +0.020 |
isn | +0.020 |
heit | +0.020 |
ement | +0.019 |
Neg logit contributions | |
blown | -0.012 |
blood | -0.011 |
Blood | -0.011 |
bitten | -0.011 |
spilled | -0.009 |
Token | chie |
Token ID | 3043 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
blood | +0.023 |
blown | +0.023 |
Blood | +0.023 |
bitten | +0.022 |
spilled | +0.020 |
Neg logit contributions | |
destination | -0.033 |
aman | -0.032 |
heit | -0.032 |
isn | -0.032 |
ement | -0.030 |
Token | vous |
Token ID | 31222 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
blood | +0.102 |
blown | +0.099 |
Blood | +0.095 |
bitten | +0.093 |
spilled | +0.080 |
Neg logit contributions | |
isn | -0.172 |
destination | -0.171 |
aman | -0.169 |
heit | -0.167 |
ement | -0.162 |
Token | young |
Token ID | 1862 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
blown | +0.008 |
Blood | +0.008 |
blood | +0.007 |
bitten | +0.007 |
spilled | +0.006 |
Neg logit contributions | |
isn | -0.019 |
destination | -0.019 |
aman | -0.019 |
heit | -0.019 |
ement | -0.018 |
Token | boy |
Token ID | 2933 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
Blood | +0.025 |
blown | +0.025 |
blood | +0.024 |
bitten | +0.024 |
spilled | +0.021 |
Neg logit contributions | |
destination | -0.037 |
aman | -0.036 |
isn | -0.036 |
heit | -0.034 |
ement | -0.033 |
Token | decided |
Token ID | 3066 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
blood | +0.015 |
blown | +0.015 |
Blood | +0.015 |
bitten | +0.014 |
spilled | +0.012 |
Neg logit contributions | |
isn | -0.022 |
destination | -0.022 |
aman | -0.021 |
heit | -0.021 |
hew | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
destination | +0.057 |
aman | +0.055 |
isn | +0.055 |
heit | +0.055 |
ement | +0.052 |
Neg logit contributions | |
blown | -0.030 |
blood | -0.030 |
Blood | -0.029 |
bitten | -0.028 |
spilled | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
destination | +0.055 |
aman | +0.054 |
heit | +0.053 |
isn | +0.052 |
ement | +0.050 |
Neg logit contributions | |
blown | -0.054 |
blood | -0.054 |
Blood | -0.053 |
bitten | -0.052 |
spilled | -0.047 |
Token | One |
Token ID | 1881 |
Feature activation | +6.91e-02 |
Pos logit contributions | |
blown | +0.014 |
blood | +0.012 |
bitten | +0.012 |
Blood | +0.011 |
spilled | +0.011 |
Neg logit contributions | |
isn | -0.019 |
destination | -0.019 |
aman | -0.019 |
ement | -0.018 |
heit | -0.018 |
Token | of |
Token ID | 286 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
destination | +0.002 |
aman | +0.002 |
isn | +0.002 |
heit | +0.002 |
ement | +0.002 |
Neg logit contributions | |
blown | -0.001 |
blood | -0.001 |
Blood | -0.001 |
bitten | -0.001 |
spilled | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
blown | +0.034 |
Blood | +0.032 |
bitten | +0.032 |
blood | +0.032 |
spilled | +0.029 |
Neg logit contributions | |
destination | -0.042 |
aman | -0.042 |
heit | -0.041 |
isn | -0.041 |
exactly | -0.040 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
blown | +0.007 |
blood | +0.006 |
bitten | +0.006 |
Blood | +0.006 |
spilled | +0.005 |
Neg logit contributions | |
destination | -0.010 |
heit | -0.010 |
aman | -0.010 |
isn | -0.009 |
ement | -0.009 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.70e+00 |
Pos logit contributions | |
destination | +0.026 |
aman | +0.025 |
isn | +0.024 |
heit | +0.024 |
ement | +0.023 |
Neg logit contributions | |
blown | -0.036 |
blood | -0.036 |
Blood | -0.036 |
bitten | -0.035 |
spilled | -0.033 |
Token | hes |
Token ID | 956 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
blown | +0.056 |
blood | +0.052 |
bitten | +0.048 |
Blood | +0.047 |
spilled | +0.037 |
Neg logit contributions | |
isn | -0.210 |
heit | -0.207 |
destination | -0.207 |
ement | -0.206 |
aman | -0.204 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
blood | +0.042 |
blown | +0.042 |
Blood | +0.042 |
bitten | +0.040 |
elt | +0.035 |
Neg logit contributions | |
destination | -0.050 |
isn | -0.049 |
aman | -0.048 |
heit | -0.047 |
ement | -0.047 |
Token | different |
Token ID | 1180 |
Feature activation | -9.20e-01 |
Pos logit contributions | |
aman | +0.029 |
destination | +0.029 |
heit | +0.028 |
hew | +0.027 |
mmm | +0.027 |
Neg logit contributions | |
blood | -0.024 |
blown | -0.023 |
bitten | -0.023 |
Blood | -0.022 |
spilled | -0.021 |
Token | from |
Token ID | 422 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
blown | +0.016 |
blood | +0.016 |
bitten | +0.016 |
Blood | +0.014 |
spilled | +0.014 |
Neg logit contributions | |
aman | -0.028 |
destination | -0.028 |
heit | -0.028 |
hew | -0.027 |
olog | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
destination | +0.007 |
aman | +0.007 |
isn | +0.007 |
heit | +0.007 |
ement | +0.007 |
Neg logit contributions | |
blown | -0.004 |
Blood | -0.004 |
blood | -0.004 |
bitten | -0.004 |
spilled | -0.004 |
Token | ie |
Token ID | 494 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
blown | +0.004 |
blood | +0.004 |
Blood | +0.004 |
bitten | +0.004 |
spilled | +0.004 |
Neg logit contributions | |
destination | -0.004 |
aman | -0.004 |
isn | -0.004 |
heit | -0.004 |
ement | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -8.64e-01 |
Pos logit contributions | |
heit | +0.004 |
destination | +0.004 |
aman | +0.004 |
isn | +0.004 |
ement | +0.004 |
Neg logit contributions | |
blood | -0.002 |
blown | -0.002 |
bitten | -0.002 |
Blood | -0.002 |
cat | -0.002 |
Token | Unlike |
Token ID | 12101 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
Blood | +0.016 |
blown | +0.015 |
blood | +0.015 |
bitten | +0.015 |
spilled | +0.013 |
Neg logit contributions | |
destination | -0.027 |
aman | -0.026 |
heit | -0.026 |
isn | -0.025 |
ement | -0.024 |
Token | other |
Token ID | 584 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
destination | +0.019 |
heit | +0.018 |
isn | +0.018 |
aman | +0.018 |
ement | +0.017 |
Neg logit contributions | |
blown | -0.017 |
blood | -0.017 |
Blood | -0.017 |
bitten | -0.017 |
spilled | -0.015 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
blown | +0.015 |
bitten | +0.015 |
blood | +0.015 |
Blood | +0.013 |
squirrel | +0.011 |
Neg logit contributions | |
ement | -0.032 |
heit | -0.032 |
aman | -0.032 |
destination | -0.031 |
mmm | -0.031 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
destination | +0.037 |
aman | +0.036 |
isn | +0.035 |
heit | +0.035 |
ement | +0.033 |
Neg logit contributions | |
blown | -0.046 |
blood | -0.045 |
Blood | -0.045 |
bitten | -0.044 |
spilled | -0.040 |
Token | hes |
Token ID | 956 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
blown | +0.060 |
blood | +0.059 |
Blood | +0.054 |
bitten | +0.053 |
spilled | +0.043 |
Neg logit contributions | |
isn | -0.205 |
heit | -0.202 |
destination | -0.202 |
exactly | -0.199 |
ement | -0.198 |
Token | , |
Token ID | 11 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
blown | +0.032 |
blood | +0.032 |
Blood | +0.031 |
bitten | +0.031 |
spilled | +0.028 |
Neg logit contributions | |
destination | -0.037 |
aman | -0.036 |
heit | -0.035 |
isn | -0.034 |
ement | -0.034 |
Token | his |
Token ID | 465 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
blown | +0.012 |
blood | +0.012 |
Blood | +0.012 |
bitten | +0.011 |
spilled | +0.010 |
Neg logit contributions | |
destination | -0.015 |
isn | -0.015 |
aman | -0.015 |
heit | -0.015 |
ement | -0.014 |
Token | feathers |
Token ID | 27400 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
heit | +0.032 |
ement | +0.032 |
aman | +0.032 |
isn | +0.031 |
mmm | +0.031 |
Neg logit contributions | |
blown | -0.019 |
blood | -0.018 |
bitten | -0.018 |
Blood | -0.017 |
spilled | -0.014 |
Token | gl |
Token ID | 1278 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Blood | +0.008 |
blown | +0.008 |
blood | +0.008 |
bitten | +0.008 |
spilled | +0.007 |
Neg logit contributions | |
isn | -0.006 |
destination | -0.006 |
aman | -0.006 |
heit | -0.006 |
ement | -0.006 |
Token | did |
Token ID | 750 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
aman | +0.019 |
destination | +0.019 |
heit | +0.019 |
mmm | +0.018 |
ement | +0.018 |
Neg logit contributions | |
blown | -0.008 |
bitten | -0.007 |
Blood | -0.007 |
blood | -0.007 |
spilled | -0.007 |
Token | not |
Token ID | 407 |
Feature activation | -9.17e-01 |
Pos logit contributions | |
aman | +0.010 |
hew | +0.009 |
ement | +0.009 |
heit | +0.009 |
destination | +0.009 |
Neg logit contributions | |
Blood | -0.003 |
blown | -0.003 |
blood | -0.003 |
bitten | -0.003 |
hurt | -0.003 |
Token | know |
Token ID | 760 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
blown | +0.024 |
Blood | +0.024 |
blood | +0.024 |
bitten | +0.023 |
spilled | +0.021 |
Neg logit contributions | |
destination | -0.020 |
isn | -0.019 |
aman | -0.019 |
heit | -0.019 |
hew | -0.018 |
Token | what |
Token ID | 644 |
Feature activation | +5.30e-02 |
Pos logit contributions | |
blood | +0.006 |
blown | +0.005 |
bitten | +0.005 |
spilled | +0.005 |
Blood | +0.005 |
Neg logit contributions | |
destination | -0.007 |
aman | -0.006 |
heit | -0.006 |
bek | -0.006 |
olog | -0.006 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
aman | +0.002 |
heit | +0.002 |
destination | +0.002 |
hew | +0.002 |
ement | +0.002 |
Neg logit contributions | |
Blood | -0.001 |
blood | -0.001 |
blown | -0.001 |
bitten | -0.001 |
spilled | -0.001 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
destination | +0.026 |
aman | +0.025 |
isn | +0.024 |
heit | +0.024 |
ement | +0.023 |
Neg logit contributions | |
blood | -0.037 |
blown | -0.037 |
Blood | -0.036 |
bitten | -0.035 |
spilled | -0.033 |
Token | hes |
Token ID | 956 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
blood | +0.065 |
blown | +0.065 |
Blood | +0.061 |
bitten | +0.059 |
spilled | +0.048 |
Neg logit contributions | |
isn | -0.203 |
destination | -0.203 |
heit | -0.201 |
aman | -0.198 |
ement | -0.194 |
Token | were |
Token ID | 547 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
blown | +0.047 |
blood | +0.046 |
Blood | +0.045 |
bitten | +0.044 |
spilled | +0.041 |
Neg logit contributions | |
destination | -0.067 |
aman | -0.066 |
heit | -0.065 |
hew | -0.062 |
ement | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
blown | +0.035 |
blood | +0.033 |
bitten | +0.033 |
Blood | +0.032 |
spilled | +0.030 |
Neg logit contributions | |
destination | -0.042 |
aman | -0.042 |
heit | -0.041 |
ement | -0.039 |
isn | -0.039 |
Token | They |
Token ID | 1119 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
Blood | +0.007 |
blown | +0.006 |
blood | +0.006 |
bitten | +0.005 |
elt | +0.005 |
Neg logit contributions | |
heit | -0.020 |
destination | -0.020 |
aman | -0.020 |
ement | -0.019 |
hew | -0.019 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
blown | +0.010 |
blood | +0.010 |
Blood | +0.010 |
bitten | +0.009 |
spilled | +0.009 |
Neg logit contributions | |
destination | -0.017 |
aman | -0.017 |
isn | -0.016 |
heit | -0.016 |
ement | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
heit | +0.008 |
aman | +0.008 |
destination | +0.008 |
isn | +0.007 |
hew | +0.007 |
Neg logit contributions | |
blood | -0.005 |
blown | -0.005 |
Blood | -0.005 |
bitten | -0.005 |
spilled | -0.004 |
Token | run |
Token ID | 1057 |
Feature activation | -8.20e-01 |
Pos logit contributions | |
blown | +0.000 |
blood | +0.000 |
Blood | +0.000 |
bitten | +0.000 |
spilled | +0.000 |
Neg logit contributions | |
destination | -0.000 |
aman | -0.000 |
isn | -0.000 |
heit | -0.000 |
ement | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
blown | +0.014 |
bitten | +0.014 |
blood | +0.014 |
Blood | +0.014 |
spilled | +0.012 |
Neg logit contributions | |
aman | -0.026 |
destination | -0.026 |
heit | -0.025 |
isn | -0.025 |
ement | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
aman | +0.049 |
destination | +0.049 |
isn | +0.048 |
heit | +0.048 |
ement | +0.048 |
Neg logit contributions | |
blood | -0.024 |
blown | -0.023 |
Blood | -0.023 |
bitten | -0.022 |
spilled | -0.018 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
destination | +0.010 |
aman | +0.010 |
heit | +0.010 |
isn | +0.010 |
ement | +0.009 |
Neg logit contributions | |
blown | -0.006 |
blood | -0.006 |
Blood | -0.006 |
bitten | -0.006 |
spilled | -0.005 |
Token | ric |
Token ID | 1173 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
destination | +0.041 |
aman | +0.039 |
isn | +0.039 |
heit | +0.039 |
ement | +0.036 |
Neg logit contributions | |
blown | -0.051 |
blood | -0.050 |
Blood | -0.049 |
bitten | -0.049 |
spilled | -0.045 |
Token | hes |
Token ID | 956 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
blown | +0.055 |
blood | +0.052 |
bitten | +0.048 |
Blood | +0.047 |
spilled | +0.038 |
Neg logit contributions | |
isn | -0.206 |
destination | -0.205 |
heit | -0.204 |
aman | -0.201 |
ement | -0.200 |
Token | . |
Token ID | 13 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
blown | +0.020 |
blood | +0.020 |
Blood | +0.020 |
bitten | +0.019 |
spilled | +0.017 |
Neg logit contributions | |
destination | -0.026 |
aman | -0.026 |
heit | -0.026 |
isn | -0.025 |
ement | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
destination | +0.003 |
heit | +0.003 |
aman | +0.003 |
isn | +0.003 |
ement | +0.003 |
Neg logit contributions | |
Blood | -0.002 |
blood | -0.002 |
blown | -0.002 |
bitten | -0.001 |
spilled | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
destination | +0.014 |
aman | +0.014 |
heit | +0.014 |
isn | +0.014 |
ement | +0.013 |
Neg logit contributions | |
Blood | -0.008 |
blood | -0.008 |
blown | -0.008 |
bitten | -0.007 |
spilled | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
destination | +0.003 |
isn | +0.003 |
ement | +0.003 |
aman | +0.003 |
heit | +0.003 |
Neg logit contributions | |
Blood | -0.003 |
blown | -0.003 |
blood | -0.003 |
bitten | -0.003 |
Tweet | -0.003 |
Token | went |
Token ID | 1816 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
Blood | +0.002 |
blood | +0.002 |
blown | +0.002 |
bitten | +0.002 |
spilled | +0.002 |
Neg logit contributions | |
destination | -0.004 |
aman | -0.004 |
heit | -0.004 |
isn | -0.004 |
hew | -0.004 |
Token | home |
Token ID | 1363 |
Feature activation | -8.58e-01 |
Pos logit contributions | |
Blood | +0.019 |
blown | +0.018 |
blood | +0.018 |
bitten | +0.017 |
spilled | +0.016 |
Neg logit contributions | |
destination | -0.017 |
aman | -0.015 |
exactly | -0.015 |
isn | -0.014 |
forever | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
blown | +0.021 |
Blood | +0.021 |
blood | +0.021 |
bitten | +0.020 |
spilled | +0.018 |
Neg logit contributions | |
destination | -0.021 |
aman | -0.020 |
isn | -0.019 |
heit | -0.018 |
exactly | -0.018 |
Token | had |
Token ID | 550 |
Feature activation | -5.28e-01 |
Pos logit contributions | |
destination | +0.015 |
aman | +0.015 |
isn | +0.015 |
heit | +0.015 |
ement | +0.014 |
Neg logit contributions | |
blown | -0.008 |
blood | -0.008 |
Blood | -0.008 |
bitten | -0.008 |
spilled | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
blown | +0.008 |
blood | +0.007 |
bitten | +0.007 |
Blood | +0.007 |
spilled | +0.006 |
Neg logit contributions | |
heit | -0.018 |
destination | -0.018 |
aman | -0.018 |
isn | -0.017 |
ement | -0.017 |
Token | y |
Token ID | 331 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
heit | +0.035 |
ement | +0.033 |
isn | +0.033 |
destination | +0.033 |
aman | +0.033 |
Neg logit contributions | |
blood | -0.029 |
blown | -0.029 |
Blood | -0.028 |
bitten | -0.028 |
spilled | -0.028 |
Token | ummy |
Token ID | 13513 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
isn | +0.093 |
heit | +0.093 |
destination | +0.089 |
aman | +0.086 |
hew | +0.080 |
Neg logit contributions | |
blood | -0.146 |
blown | -0.144 |
Blood | -0.142 |
bitten | -0.141 |
spilled | -0.131 |
Token | dinner |
Token ID | 8073 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
blood | +0.014 |
blown | +0.014 |
Blood | +0.014 |
bitten | +0.014 |
spilled | +0.013 |
Neg logit contributions | |
destination | -0.019 |
heit | -0.019 |
aman | -0.018 |
isn | -0.018 |
hew | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
heit | +0.048 |
destination | +0.046 |
aman | +0.045 |
isn | +0.044 |
hew | +0.043 |
Neg logit contributions | |
blown | -0.032 |
blood | -0.031 |
bitten | -0.030 |
Blood | -0.029 |
spilled | -0.028 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Blood | +0.001 |
blown | +0.001 |
blood | +0.001 |
bitten | +0.001 |
spilled | +0.001 |
Neg logit contributions | |
destination | -0.004 |
heit | -0.004 |
aman | -0.004 |
isn | -0.003 |
ement | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
blown | +0.007 |
blood | +0.007 |
bitten | +0.006 |
spilled | +0.006 |
Blood | +0.006 |
Neg logit contributions | |
destination | -0.010 |
heit | -0.010 |
aman | -0.010 |
ement | -0.010 |
isn | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
destination | +0.077 |
heit | +0.075 |
exactly | +0.072 |
aman | +0.072 |
isn | +0.068 |
Neg logit contributions | |
Blood | -0.083 |
blown | -0.079 |
bitten | -0.075 |
blood | -0.073 |
elt | -0.068 |
Token | � |
Token ID | 129 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
heit | +0.007 |
destination | +0.007 |
aman | +0.007 |
ement | +0.006 |
exactly | +0.006 |
Neg logit contributions | |
Blood | -0.004 |
blown | -0.004 |
bitten | -0.003 |
blood | -0.003 |
spilled | -0.003 |
Token | � |
Token ID | 241 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
destination | +0.064 |
isn | +0.062 |
exactly | +0.062 |
heit | +0.061 |
aman | +0.059 |
Neg logit contributions | |
Blood | -0.077 |
blown | -0.072 |
bitten | -0.069 |
blood | -0.066 |
Tweet | -0.063 |
Token | but |
Token ID | 4360 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
destination | +0.010 |
heit | +0.010 |
aman | +0.009 |
isn | +0.009 |
ement | +0.009 |
Neg logit contributions | |
Blood | -0.007 |
blown | -0.007 |
blood | -0.007 |
bitten | -0.006 |
spilled | -0.006 |
Token | don |
Token ID | 836 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
destination | +0.065 |
aman | +0.065 |
heit | +0.064 |
ement | +0.064 |
hew | +0.061 |
Neg logit contributions | |
blood | -0.048 |
blown | -0.048 |
bitten | -0.044 |
Blood | -0.044 |
spilled | -0.041 |
Token | â |
Token ID | 22940 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
destination | +0.020 |
aman | +0.020 |
heit | +0.019 |
isn | +0.019 |
ement | +0.019 |
Neg logit contributions | |
blown | -0.009 |
Blood | -0.008 |
blood | -0.008 |
bitten | -0.008 |
spilled | -0.007 |
Token | € |
Token ID | 26391 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
destination | +0.099 |
heit | +0.092 |
exactly | +0.092 |
aman | +0.090 |
isn | +0.088 |
Neg logit contributions | |
blown | -0.125 |
Blood | -0.125 |
bitten | -0.122 |
blood | -0.119 |
agged | -0.109 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
Blood | +0.004 |
blown | +0.003 |
bitten | +0.003 |
blood | +0.003 |
elt | +0.003 |
Neg logit contributions | |
heit | -0.004 |
destination | -0.004 |
aman | -0.004 |
ement | -0.004 |
exactly | -0.004 |
Token | t |
Token ID | 83 |
Feature activation | -8.37e-01 |
Pos logit contributions | |
heit | +0.027 |
destination | +0.026 |
aman | +0.025 |
idays | +0.024 |
amaz | +0.024 |
Neg logit contributions | |
Blood | -0.012 |
bitten | -0.011 |
blown | -0.011 |
blood | -0.011 |
spilled | -0.010 |
Token | touch |
Token ID | 3638 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
blown | +0.016 |
blood | +0.016 |
Blood | +0.016 |
bitten | +0.015 |
spilled | +0.014 |
Neg logit contributions | |
destination | -0.024 |
aman | -0.023 |
ement | -0.023 |
heit | -0.023 |
exactly | -0.021 |
Token | it |
Token ID | 340 |
Feature activation | -5.42e-02 |
Pos logit contributions | |
destination | +0.026 |
aman | +0.025 |
bek | +0.025 |
heit | +0.024 |
olog | +0.024 |
Neg logit contributions | |
blood | -0.020 |
blown | -0.019 |
bitten | -0.018 |
Blood | -0.017 |
spilled | -0.016 |
Token | just |
Token ID | 655 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
aman | +0.045 |
destination | +0.045 |
heit | +0.043 |
ement | +0.043 |
isn | +0.039 |
Neg logit contributions | |
blown | -0.052 |
blood | -0.051 |
bitten | -0.050 |
Blood | -0.049 |
spilled | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
destination | +0.030 |
aman | +0.030 |
heit | +0.029 |
ement | +0.028 |
isn | +0.027 |
Neg logit contributions | |
blown | -0.026 |
blood | -0.026 |
bitten | -0.025 |
Blood | -0.025 |
spilled | -0.022 |
Token | big |
Token ID | 1263 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
ement | +0.050 |
heit | +0.049 |
aman | +0.049 |
destination | +0.047 |
hew | +0.047 |
Neg logit contributions | |
blown | -0.029 |
blood | -0.028 |
bitten | -0.028 |
Blood | -0.026 |
spilled | -0.026 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
aman | +0.020 |
heit | +0.020 |
destination | +0.020 |
ement | +0.020 |
hew | +0.020 |
Neg logit contributions | |
blood | -0.013 |
blown | -0.013 |
bitten | -0.012 |
Blood | -0.012 |
spilled | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
blown | +0.003 |
bitten | +0.003 |
blood | +0.003 |
spilled | +0.003 |
Blood | +0.003 |
Neg logit contributions | |
destination | -0.004 |
heit | -0.003 |
aman | -0.003 |
ement | -0.003 |
hew | -0.003 |
Token | â |
Token ID | 22940 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
destination | +0.025 |
heit | +0.024 |
aman | +0.023 |
ement | +0.022 |
isn | +0.022 |
Neg logit contributions | |
Blood | -0.018 |
blood | -0.017 |
blown | -0.017 |
bitten | -0.017 |
elt | -0.015 |
Token | € |
Token ID | 26391 |
Feature activation | -2.69e-02 |
Pos logit contributions | |
destination | +0.100 |
aman | +0.089 |
heit | +0.089 |
exactly | +0.087 |
isn | +0.087 |
Neg logit contributions | |
Blood | -0.130 |
blown | -0.130 |
bitten | -0.129 |
blood | -0.128 |
spilled | -0.115 |
Token |
|
Token ID | 198 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
Blood | +0.001 |
bitten | +0.001 |
blown | +0.001 |
blood | +0.001 |
spilled | +0.001 |
Neg logit contributions | |
destination | -0.001 |
aman | -0.001 |
heit | -0.001 |
ement | -0.001 |
exactly | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
destination | +0.015 |
heit | +0.014 |
aman | +0.014 |
isn | +0.014 |
ement | +0.013 |
Neg logit contributions | |
Blood | -0.008 |
blood | -0.008 |
blown | -0.008 |
bitten | -0.008 |
Tweet | -0.006 |
Token | Tom |
Token ID | 13787 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
Blood | +0.001 |
blown | +0.001 |
blood | +0.001 |
bitten | +0.001 |
Tweet | +0.001 |
Neg logit contributions | |
destination | -0.001 |
isn | -0.001 |
ement | -0.001 |
heit | -0.001 |
aman | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
destination | +0.030 |
heit | +0.029 |
aman | +0.029 |
ement | +0.029 |
isn | +0.028 |
Neg logit contributions | |
blown | -0.020 |
bitten | -0.019 |
blood | -0.019 |
Blood | -0.019 |
spilled | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | -9.26e-01 |
Pos logit contributions | |
blown | +0.010 |
blood | +0.010 |
bitten | +0.010 |
Blood | +0.010 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.021 |
aman | -0.020 |
heit | -0.020 |
isn | -0.020 |
ement | -0.019 |
Token | nap |
Token ID | 25422 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
blown | +0.016 |
blood | +0.016 |
bitten | +0.016 |
Blood | +0.015 |
spilled | +0.014 |
Neg logit contributions | |
aman | -0.029 |
heit | -0.029 |
destination | -0.028 |
isn | -0.028 |
ement | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
destination | +0.029 |
heit | +0.029 |
aman | +0.029 |
isn | +0.028 |
hew | +0.027 |
Neg logit contributions | |
blown | -0.019 |
blood | -0.019 |
bitten | -0.018 |
Blood | -0.018 |
spilled | -0.017 |
Token | had |
Token ID | 550 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
destination | +0.012 |
aman | +0.011 |
heit | +0.011 |
isn | +0.011 |
ement | +0.011 |
Neg logit contributions | |
blown | -0.008 |
blood | -0.008 |
Blood | -0.007 |
bitten | -0.007 |
spilled | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
destination | +0.010 |
heit | +0.009 |
aman | +0.009 |
isn | +0.009 |
ement | +0.009 |
Neg logit contributions | |
blown | -0.006 |
blood | -0.005 |
bitten | -0.005 |
Blood | -0.005 |
spilled | -0.005 |
Token | y |
Token ID | 331 |
Feature activation | +4.98e+00 |
Pos logit contributions | |
heit | +0.043 |
ement | +0.040 |
isn | +0.039 |
aman | +0.039 |
hew | +0.038 |
Neg logit contributions | |
blood | -0.039 |
blown | -0.038 |
spilled | -0.037 |
bitten | -0.037 |
Blood | -0.036 |
Token | ummy |
Token ID | 13513 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
heit | +0.097 |
isn | +0.096 |
destination | +0.091 |
aman | +0.090 |
hew | +0.082 |
Neg logit contributions | |
blood | -0.140 |
blown | -0.139 |
bitten | -0.136 |
Blood | -0.135 |
spilled | -0.126 |
Token | sausage |
Token ID | 31889 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
blood | +0.007 |
blown | +0.006 |
bitten | +0.006 |
Blood | +0.006 |
spilled | +0.006 |
Neg logit contributions | |
destination | -0.009 |
heit | -0.009 |
aman | -0.009 |
isn | -0.009 |
hew | -0.008 |
Token | adventure |
Token ID | 8855 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
destination | +0.030 |
aman | +0.029 |
heit | +0.029 |
isn | +0.028 |
ement | +0.027 |
Neg logit contributions | |
blown | -0.030 |
blood | -0.030 |
Blood | -0.029 |
bitten | -0.029 |
spilled | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
heit | +0.047 |
aman | +0.043 |
destination | +0.042 |
isn | +0.041 |
hew | +0.041 |
Neg logit contributions | |
blown | -0.028 |
bitten | -0.027 |
blood | -0.026 |
Blood | -0.024 |
spilled | -0.023 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
destination | +0.020 |
aman | +0.020 |
heit | +0.019 |
isn | +0.019 |
ement | +0.018 |
Neg logit contributions | |
blown | -0.017 |
blood | -0.017 |
Blood | -0.017 |
bitten | -0.016 |
spilled | -0.015 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
destination | +0.005 |
aman | +0.004 |
heit | +0.004 |
ement | +0.004 |
exactly | +0.004 |
Neg logit contributions | |
Blood | -0.005 |
blown | -0.005 |
bitten | -0.005 |
blood | -0.005 |
spilled | -0.005 |
Token | s |
Token ID | 82 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
destination | +0.043 |
heit | +0.042 |
aman | +0.040 |
isn | +0.038 |
idays | +0.038 |
Neg logit contributions | |
Blood | -0.028 |
blown | -0.027 |
blood | -0.027 |
bitten | -0.027 |
spilled | -0.025 |
Token | OK |
Token ID | 7477 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
destination | +0.058 |
aman | +0.057 |
heit | +0.056 |
ement | +0.054 |
isn | +0.051 |
Neg logit contributions | |
blown | -0.059 |
blood | -0.059 |
bitten | -0.057 |
Blood | -0.055 |
spilled | -0.053 |
Token | , |
Token ID | 11 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
heit | +0.075 |
destination | +0.074 |
aman | +0.071 |
ement | +0.071 |
destinations | +0.067 |
Neg logit contributions | |
blood | -0.053 |
Blood | -0.052 |
bitten | -0.052 |
blown | -0.050 |
elt | -0.047 |
Token | we |
Token ID | 356 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
blood | +0.003 |
blown | +0.003 |
Blood | +0.003 |
bitten | +0.003 |
spilled | +0.003 |
Neg logit contributions | |
destination | -0.006 |
heit | -0.006 |
ement | -0.006 |
aman | -0.006 |
hew | -0.005 |
Token | â |
Token ID | 22940 |
Feature activation | +5.01e+00 |
Pos logit contributions | |
aman | +0.021 |
destination | +0.020 |
heit | +0.020 |
ement | +0.020 |
mmm | +0.019 |
Neg logit contributions | |
blown | -0.020 |
blood | -0.020 |
bitten | -0.020 |
spilled | -0.019 |
Blood | -0.018 |
Token | € |
Token ID | 26391 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
destination | +0.108 |
exactly | +0.100 |
isn | +0.099 |
heit | +0.098 |
aman | +0.097 |
Neg logit contributions | |
blown | -0.133 |
bitten | -0.131 |
Blood | -0.128 |
blood | -0.126 |
spilled | -0.115 |
Token | â„¢ |
Token ID | 8151 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
heit | +0.005 |
aman | +0.005 |
destination | +0.005 |
ement | +0.005 |
exactly | +0.005 |
Neg logit contributions | |
Blood | -0.005 |
blown | -0.005 |
bitten | -0.005 |
spilled | -0.005 |
blood | -0.005 |
Token | ll |
Token ID | 297 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
heit | +0.044 |
destination | +0.043 |
aman | +0.041 |
isn | +0.040 |
idays | +0.039 |
Neg logit contributions | |
Blood | -0.024 |
blown | -0.023 |
blood | -0.023 |
bitten | -0.023 |
spilled | -0.021 |
Token | mention |
Token ID | 3068 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
destination | +0.046 |
aman | +0.046 |
heit | +0.044 |
isn | +0.044 |
ement | +0.044 |
Neg logit contributions | |
blown | -0.034 |
blood | -0.033 |
bitten | -0.032 |
Blood | -0.031 |
spilled | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
destination | +0.089 |
heit | +0.088 |
aman | +0.088 |
bek | +0.085 |
ement | +0.085 |
Neg logit contributions | |
blood | -0.050 |
blown | -0.042 |
bitten | -0.041 |
spilled | -0.037 |
hurt | -0.035 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
destination | +0.018 |
aman | +0.018 |
heit | +0.018 |
isn | +0.017 |
ement | +0.017 |
Neg logit contributions | |
blown | -0.014 |
Blood | -0.014 |
blood | -0.014 |
bitten | -0.013 |
spilled | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
aman | +0.041 |
destination | +0.041 |
heit | +0.039 |
mmm | +0.039 |
hew | +0.038 |
Neg logit contributions | |
blood | -0.030 |
blown | -0.029 |
bitten | -0.028 |
Blood | -0.028 |
spilled | -0.027 |
Token | said |
Token ID | 531 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
destination | +0.039 |
aman | +0.038 |
isn | +0.038 |
heit | +0.037 |
ement | +0.036 |
Neg logit contributions | |
blown | -0.026 |
blood | -0.025 |
Blood | -0.025 |
bitten | -0.025 |
spilled | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +7.57e-02 |
Pos logit contributions | |
Blood | +0.018 |
blood | +0.017 |
bitten | +0.017 |
blown | +0.017 |
spilled | +0.016 |
Neg logit contributions | |
destination | -0.017 |
aman | -0.017 |
heit | -0.016 |
hew | -0.015 |
destinations | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
destination | +0.002 |
isn | +0.002 |
aman | +0.002 |
heit | +0.002 |
ement | +0.002 |
Neg logit contributions | |
blown | -0.002 |
blood | -0.002 |
Blood | -0.002 |
bitten | -0.002 |
spilled | -0.001 |
Token | Wow |
Token ID | 22017 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
destination | +0.018 |
isn | +0.017 |
aman | +0.017 |
heit | +0.017 |
ement | +0.016 |
Neg logit contributions | |
blown | -0.018 |
blood | -0.018 |
Blood | -0.017 |
bitten | -0.017 |
spilled | -0.015 |
Token | , |
Token ID | 11 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
aman | +0.032 |
destination | +0.031 |
destinations | +0.029 |
heit | +0.028 |
ement | +0.028 |
Neg logit contributions | |
Blood | -0.031 |
blood | -0.030 |
blown | -0.029 |
bitten | -0.028 |
spilled | -0.028 |
Token | Lily |
Token ID | 20037 |
Feature activation | +6.28e-01 |
Pos logit contributions | |
destination | +0.014 |
aman | +0.014 |
ement | +0.013 |
heit | +0.013 |
hew | +0.013 |
Neg logit contributions | |
blood | -0.012 |
Blood | -0.011 |
blown | -0.011 |
bitten | -0.011 |
spilled | -0.010 |
Token | ! |
Token ID | 0 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
aman | +0.014 |
destination | +0.014 |
heit | +0.014 |
ement | +0.013 |
destinations | +0.012 |
Neg logit contributions | |
bitten | -0.016 |
blood | -0.016 |
blown | -0.016 |
Blood | -0.016 |
spilled | -0.015 |
Token | Your |
Token ID | 3406 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
destination | +0.031 |
aman | +0.030 |
heit | +0.029 |
isn | +0.028 |
ement | +0.028 |
Neg logit contributions | |
Blood | -0.031 |
blown | -0.031 |
blood | -0.031 |
bitten | -0.030 |
spilled | -0.027 |
Token | dress |
Token ID | 6576 |
Feature activation | -4.71e-03 |
Pos logit contributions | |
aman | +0.013 |
heit | +0.012 |
mmm | +0.012 |
destination | +0.011 |
hew | +0.011 |
Neg logit contributions | |
blood | -0.007 |
blown | -0.007 |
Blood | -0.007 |
bitten | -0.006 |
spilled | -0.006 |
Token | hears |
Token ID | 23180 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
destination | +0.035 |
aman | +0.035 |
heit | +0.034 |
isn | +0.034 |
ement | +0.032 |
Neg logit contributions | |
blood | -0.026 |
blown | -0.026 |
Blood | -0.025 |
bitten | -0.025 |
spilled | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
blown | +0.023 |
bitten | +0.022 |
Blood | +0.021 |
blood | +0.020 |
elt | +0.020 |
Neg logit contributions | |
aman | -0.016 |
isn | -0.016 |
destination | -0.016 |
heit | -0.015 |
ement | -0.015 |
Token | noise |
Token ID | 7838 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
isn | +0.006 |
destination | +0.006 |
difference | +0.005 |
ement | +0.005 |
heit | +0.005 |
Neg logit contributions | |
blown | -0.009 |
bitten | -0.009 |
Blood | -0.009 |
elt | -0.008 |
ashed | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +8.43e-01 |
Pos logit contributions | |
blown | +0.023 |
blood | +0.023 |
Blood | +0.023 |
bitten | +0.022 |
spilled | +0.020 |
Neg logit contributions | |
destination | -0.027 |
aman | -0.026 |
isn | -0.026 |
heit | -0.026 |
ement | -0.025 |
Token | comes |
Token ID | 2058 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
isn | +0.022 |
destination | +0.021 |
heit | +0.021 |
aman | +0.020 |
ement | +0.019 |
Neg logit contributions | |
blown | -0.019 |
Blood | -0.019 |
bitten | -0.018 |
blood | -0.017 |
spilled | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
Blood | +0.025 |
blown | +0.025 |
blood | +0.024 |
bitten | +0.023 |
spilled | +0.021 |
Neg logit contributions | |
destination | -0.035 |
isn | -0.032 |
aman | -0.031 |
heit | -0.031 |
hew | -0.030 |
Token | see |
Token ID | 766 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
destination | +0.063 |
aman | +0.060 |
isn | +0.059 |
heit | +0.056 |
difference | +0.053 |
Neg logit contributions | |
blown | -0.053 |
Blood | -0.050 |
bitten | -0.048 |
blood | -0.047 |
elt | -0.044 |
Token | what |
Token ID | 644 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
destination | +0.028 |
isn | +0.027 |
aman | +0.027 |
heit | +0.027 |
ement | +0.025 |
Neg logit contributions | |
blown | -0.050 |
Blood | -0.049 |
blood | -0.049 |
bitten | -0.049 |
spilled | -0.045 |
Token | is |
Token ID | 318 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
destination | +0.013 |
isn | +0.012 |
aman | +0.012 |
heit | +0.012 |
ement | +0.011 |
Neg logit contributions | |
blown | -0.027 |
blood | -0.027 |
Blood | -0.027 |
bitten | -0.027 |
spilled | -0.025 |
Token | wrong |
Token ID | 2642 |
Feature activation | -8.60e-01 |
Pos logit contributions | |
destination | +0.024 |
aman | +0.024 |
heit | +0.023 |
isn | +0.023 |
ement | +0.022 |
Neg logit contributions | |
blown | -0.032 |
blood | -0.032 |
Blood | -0.032 |
bitten | -0.031 |
spilled | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
blood | +0.017 |
blown | +0.016 |
Blood | +0.016 |
bitten | +0.015 |
spilled | +0.014 |
Neg logit contributions | |
destination | -0.026 |
heit | -0.026 |
aman | -0.025 |
isn | -0.024 |
hew | -0.024 |
Token | day |
Token ID | 1110 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
destination | +0.023 |
aman | +0.023 |
heit | +0.023 |
isn | +0.022 |
ement | +0.021 |
Neg logit contributions | |
blood | -0.019 |
blown | -0.019 |
Blood | -0.019 |
bitten | -0.019 |
spilled | -0.017 |
Token | his |
Token ID | 465 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
Blood | +0.045 |
blown | +0.045 |
blood | +0.045 |
bitten | +0.045 |
spilled | +0.042 |
Neg logit contributions | |
destination | -0.039 |
aman | -0.037 |
heit | -0.036 |
isn | -0.035 |
ement | -0.035 |
Token | dad |
Token ID | 9955 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
heit | +0.015 |
destination | +0.015 |
aman | +0.015 |
isn | +0.015 |
ement | +0.014 |
Neg logit contributions | |
blood | -0.013 |
blown | -0.012 |
Blood | -0.012 |
bitten | -0.012 |
spilled | -0.011 |
Token | gave |
Token ID | 2921 |
Feature activation | +9.80e-01 |
Pos logit contributions | |
destination | +0.007 |
heit | +0.007 |
aman | +0.006 |
ement | +0.006 |
isn | +0.006 |
Neg logit contributions | |
blown | -0.004 |
blood | -0.004 |
bitten | -0.004 |
spilled | -0.003 |
Blood | -0.003 |
Token | him |
Token ID | 683 |
Feature activation | +7.95e-01 |
Pos logit contributions | |
destination | +0.027 |
heit | +0.026 |
aman | +0.026 |
ement | +0.025 |
isn | +0.025 |
Neg logit contributions | |
blood | -0.021 |
blown | -0.021 |
bitten | -0.021 |
Blood | -0.020 |
spilled | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
destination | +0.027 |
aman | +0.026 |
isn | +0.026 |
heit | +0.026 |
ement | +0.025 |
Neg logit contributions | |
blown | -0.012 |
blood | -0.011 |
Blood | -0.011 |
bitten | -0.011 |
spilled | -0.009 |
Token | weapon |
Token ID | 4282 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
destination | +0.049 |
heit | +0.049 |
aman | +0.049 |
isn | +0.048 |
ement | +0.047 |
Neg logit contributions | |
blood | -0.038 |
blown | -0.037 |
Blood | -0.036 |
bitten | -0.036 |
spilled | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
destination | +0.011 |
isn | +0.010 |
aman | +0.010 |
heit | +0.010 |
ement | +0.010 |
Neg logit contributions | |
blown | -0.008 |
Blood | -0.008 |
blood | -0.008 |
bitten | -0.008 |
spilled | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
Blood | +0.007 |
blood | +0.007 |
blown | +0.006 |
bitten | +0.006 |
spilled | +0.005 |
Neg logit contributions | |
destination | -0.017 |
heit | -0.017 |
aman | -0.017 |
isn | -0.016 |
ement | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
aman | +0.012 |
destination | +0.012 |
heit | +0.011 |
ement | +0.011 |
isn | +0.011 |
Neg logit contributions | |
blown | -0.007 |
blood | -0.007 |
bitten | -0.007 |
Blood | -0.007 |
spilled | -0.006 |
Token | really |
Token ID | 1107 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
destination | +0.011 |
isn | +0.011 |
aman | +0.011 |
heit | +0.011 |
ement | +0.010 |
Neg logit contributions | |
blown | -0.013 |
blood | -0.013 |
Blood | -0.013 |
bitten | -0.012 |
spilled | -0.011 |
Token | made |
Token ID | 925 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
blown | +0.002 |
blood | +0.002 |
Blood | +0.002 |
bitten | +0.002 |
spilled | +0.002 |
Neg logit contributions | |
destination | -0.004 |
aman | -0.004 |
isn | -0.004 |
heit | -0.004 |
ement | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
blown | +0.054 |
bitten | +0.051 |
Blood | +0.049 |
blood | +0.048 |
spilled | +0.044 |
Neg logit contributions | |
isn | -0.063 |
destination | -0.063 |
exactly | -0.061 |
aman | -0.060 |
heit | -0.058 |
Token | feel |
Token ID | 1254 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
blown | +0.004 |
Blood | +0.004 |
blood | +0.004 |
bitten | +0.004 |
spilled | +0.004 |
Neg logit contributions | |
destination | -0.008 |
isn | -0.007 |
aman | -0.007 |
heit | -0.007 |
ement | -0.007 |
Token | cool |
Token ID | 3608 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
blown | +0.011 |
Blood | +0.011 |
blood | +0.011 |
bitten | +0.011 |
spilled | +0.010 |
Neg logit contributions | |
destination | -0.013 |
isn | -0.013 |
aman | -0.013 |
heit | -0.013 |
ement | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
destination | +0.003 |
aman | +0.003 |
heit | +0.003 |
isn | +0.003 |
ement | +0.003 |
Neg logit contributions | |
blown | -0.003 |
blood | -0.003 |
Blood | -0.003 |
bitten | -0.003 |
spilled | -0.002 |
Token | But |
Token ID | 887 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
blown | +0.000 |
blood | +0.000 |
bitten | +0.000 |
Blood | +0.000 |
spilled | +0.000 |
Neg logit contributions | |
destination | -0.000 |
isn | -0.000 |
aman | -0.000 |
heit | -0.000 |
ement | -0.000 |
Token | then |
Token ID | 788 |
Feature activation | -9.38e-01 |
Pos logit contributions | |
destination | +0.028 |
aman | +0.027 |
heit | +0.027 |
isn | +0.027 |
ement | +0.025 |
Neg logit contributions | |
blown | -0.026 |
blood | -0.025 |
Blood | -0.025 |
bitten | -0.025 |
spilled | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
blood | +0.019 |
Blood | +0.019 |
blown | +0.018 |
bitten | +0.018 |
spilled | +0.016 |
Neg logit contributions | |
destination | -0.027 |
aman | -0.027 |
heit | -0.026 |
isn | -0.025 |
ement | -0.025 |
Token | fan |
Token ID | 4336 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Blood | +0.015 |
bitten | +0.015 |
blown | +0.015 |
blood | +0.014 |
ked | +0.014 |
Neg logit contributions | |
destination | -0.014 |
isn | -0.014 |
ement | -0.014 |
aman | -0.014 |
heit | -0.013 |
Token | started |
Token ID | 2067 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
Blood | +0.004 |
blood | +0.004 |
blown | +0.004 |
bitten | +0.003 |
spilled | +0.003 |
Neg logit contributions | |
destination | -0.006 |
isn | -0.006 |
aman | -0.006 |
heit | -0.006 |
ement | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
blown | +0.052 |
Blood | +0.052 |
blood | +0.051 |
bitten | +0.050 |
spilled | +0.042 |
Neg logit contributions | |
destination | -0.088 |
aman | -0.084 |
isn | -0.084 |
heit | -0.081 |
ement | -0.079 |
Token | " |
Token ID | 366 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
destination | +0.012 |
heit | +0.012 |
aman | +0.012 |
hew | +0.011 |
ement | +0.011 |
Neg logit contributions | |
blood | -0.006 |
blown | -0.006 |
bitten | -0.005 |
Blood | -0.005 |
spilled | -0.005 |
Token | yes |
Token ID | 8505 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
destination | +0.021 |
isn | +0.020 |
aman | +0.020 |
heit | +0.019 |
ement | +0.019 |
Neg logit contributions | |
blood | -0.017 |
blown | -0.017 |
Blood | -0.016 |
bitten | -0.016 |
spilled | -0.015 |
Token | ." |
Token ID | 526 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
destination | +0.004 |
aman | +0.004 |
heit | +0.004 |
amaz | +0.004 |
destinations | +0.004 |
Neg logit contributions | |
Blood | -0.005 |
bitten | -0.004 |
blown | -0.004 |
blood | -0.004 |
spilled | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -2.81e-01 |
Pos logit contributions | |
blown | +0.006 |
blood | +0.006 |
Blood | +0.006 |
bitten | +0.006 |
spilled | +0.005 |
Neg logit contributions | |
destination | -0.007 |
aman | -0.007 |
isn | -0.007 |
heit | -0.007 |
ement | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
blown | +0.006 |
blood | +0.006 |
Blood | +0.006 |
bitten | +0.006 |
spilled | +0.005 |
Neg logit contributions | |
destination | -0.008 |
aman | -0.007 |
heit | -0.007 |
isn | -0.007 |
ement | -0.007 |
Token | Amy |
Token ID | 40797 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
blown | +0.015 |
Blood | +0.015 |
blood | +0.015 |
bitten | +0.014 |
spilled | +0.013 |
Neg logit contributions | |
destination | -0.014 |
aman | -0.014 |
isn | -0.013 |
heit | -0.013 |
ement | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
destination | +0.032 |
aman | +0.032 |
heit | +0.031 |
isn | +0.031 |
ement | +0.030 |
Neg logit contributions | |
blown | -0.020 |
blood | -0.019 |
bitten | -0.019 |
Blood | -0.019 |
spilled | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
blown | +0.028 |
blood | +0.027 |
Blood | +0.026 |
bitten | +0.026 |
elt | +0.024 |
Neg logit contributions | |
isn | -0.024 |
aman | -0.024 |
destination | -0.024 |
heit | -0.024 |
ph | -0.021 |
Token | cat |
Token ID | 3797 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
blown | +0.050 |
iers | +0.044 |
bitten | +0.043 |
Blood | +0.041 |
agged | +0.041 |
Neg logit contributions | |
isn | -0.070 |
aman | -0.063 |
destination | -0.063 |
So | -0.062 |
promise | -0.061 |
Token | played |
Token ID | 2826 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
blown | +0.017 |
blood | +0.017 |
Blood | +0.017 |
bitten | +0.016 |
spilled | +0.013 |
Neg logit contributions | |
destination | -0.035 |
isn | -0.034 |
aman | -0.034 |
heit | -0.034 |
ement | -0.033 |
Token | all |
Token ID | 477 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
blown | +0.013 |
blood | +0.013 |
Blood | +0.013 |
bitten | +0.013 |
spilled | +0.012 |
Neg logit contributions | |
destination | -0.009 |
isn | -0.009 |
heit | -0.009 |
aman | -0.009 |
ement | -0.008 |
Token | you |
Token ID | 345 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Blood | +0.008 |
blood | +0.008 |
blown | +0.007 |
bitten | +0.007 |
spilled | +0.007 |
Neg logit contributions | |
destination | -0.005 |
aman | -0.005 |
heit | -0.005 |
isn | -0.004 |
ement | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Blood | +0.021 |
blood | +0.020 |
bitten | +0.020 |
mice | +0.019 |
blown | +0.019 |
Neg logit contributions | |
aman | -0.028 |
heit | -0.028 |
destination | -0.026 |
ement | -0.025 |
destinations | -0.025 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
blood | +0.016 |
Blood | +0.014 |
blown | +0.013 |
bitten | +0.012 |
cat | +0.011 |
Neg logit contributions | |
destination | -0.036 |
heit | -0.035 |
aman | -0.035 |
ement | -0.033 |
rd | -0.033 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
destination | +0.034 |
aman | +0.033 |
heit | +0.032 |
ement | +0.031 |
destinations | +0.029 |
Neg logit contributions | |
bitten | -0.034 |
blood | -0.034 |
blown | -0.033 |
Blood | -0.033 |
spilled | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
blood | +0.006 |
blown | +0.006 |
Blood | +0.006 |
bitten | +0.005 |
spilled | +0.005 |
Neg logit contributions | |
destination | -0.009 |
aman | -0.008 |
heit | -0.008 |
isn | -0.008 |
ement | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
destination | +0.005 |
heit | +0.005 |
aman | +0.005 |
isn | +0.005 |
ement | +0.005 |
Neg logit contributions | |
Blood | -0.003 |
blood | -0.003 |
blown | -0.003 |
bitten | -0.003 |
spilled | -0.002 |
Token | From |
Token ID | 4863 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Blood | +0.002 |
blood | +0.002 |
blown | +0.002 |
Tweet | +0.002 |
bitten | +0.002 |
Neg logit contributions | |
destination | -0.003 |
ement | -0.003 |
aman | -0.003 |
heit | -0.003 |
isn | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
destination | +0.060 |
aman | +0.058 |
isn | +0.057 |
heit | +0.057 |
ement | +0.054 |
Neg logit contributions | |
blown | -0.061 |
blood | -0.060 |
Blood | -0.060 |
bitten | -0.058 |
spilled | -0.053 |
Token | day |
Token ID | 1110 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
destination | +0.045 |
heit | +0.044 |
aman | +0.044 |
ement | +0.043 |
isn | +0.042 |
Neg logit contributions | |
Blood | -0.029 |
blown | -0.029 |
blood | -0.028 |
bitten | -0.027 |
spilled | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
blown | +0.043 |
blood | +0.043 |
bitten | +0.040 |
Blood | +0.040 |
spilled | +0.035 |
Neg logit contributions | |
destination | -0.060 |
isn | -0.058 |
heit | -0.058 |
aman | -0.056 |
ement | -0.055 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
blown | +0.013 |
Blood | +0.013 |
blood | +0.013 |
bitten | +0.013 |
spilled | +0.011 |
Neg logit contributions | |
destination | -0.023 |
aman | -0.022 |
heit | -0.022 |
isn | -0.022 |
ement | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
destination | +0.030 |
aman | +0.029 |
heit | +0.029 |
isn | +0.028 |
hew | +0.028 |
Neg logit contributions | |
Blood | -0.018 |
blood | -0.017 |
blown | -0.017 |
bitten | -0.016 |
spilled | -0.014 |
Token | A |
Token ID | 32 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
destination | +0.022 |
aman | +0.021 |
heit | +0.021 |
isn | +0.021 |
ement | +0.020 |
Neg logit contributions | |
blown | -0.020 |
blood | -0.019 |
Blood | -0.019 |
bitten | -0.019 |
spilled | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
destination | +0.020 |
aman | +0.020 |
heit | +0.020 |
ement | +0.019 |
hew | +0.019 |
Neg logit contributions | |
Blood | -0.011 |
blown | -0.011 |
blood | -0.010 |
bitten | -0.010 |
spilled | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
blown | +0.018 |
blood | +0.018 |
Blood | +0.018 |
bitten | +0.018 |
spilled | +0.016 |
Neg logit contributions | |
destination | -0.021 |
aman | -0.020 |
heit | -0.020 |
isn | -0.020 |
ement | -0.019 |
Token | match |
Token ID | 2872 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
aman | +0.011 |
heit | +0.011 |
destination | +0.011 |
hew | +0.011 |
ement | +0.010 |
Neg logit contributions | |
blood | -0.007 |
blown | -0.007 |
Blood | -0.007 |
bitten | -0.007 |
spilled | -0.007 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
aman | +0.006 |
heit | +0.006 |
destination | +0.006 |
hew | +0.006 |
ement | +0.006 |
Neg logit contributions | |
blown | -0.007 |
blood | -0.007 |
bitten | -0.007 |
Blood | -0.006 |
spilled | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -9.11e-02 |
Pos logit contributions | |
blown | +0.018 |
bitten | +0.016 |
blood | +0.015 |
Blood | +0.015 |
spilled | +0.014 |
Neg logit contributions | |
isn | -0.015 |
destination | -0.015 |
aman | -0.015 |
ement | -0.014 |
exactly | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
blown | +0.002 |
blood | +0.002 |
bitten | +0.002 |
Blood | +0.002 |
spilled | +0.002 |
Neg logit contributions | |
destination | -0.002 |
isn | -0.002 |
aman | -0.002 |
heit | -0.002 |
ement | -0.002 |
Token | Mom |
Token ID | 29252 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
blown | +0.004 |
blood | +0.004 |
Blood | +0.004 |
bitten | +0.004 |
spilled | +0.003 |
Neg logit contributions | |
destination | -0.005 |
aman | -0.005 |
isn | -0.005 |
heit | -0.005 |
ement | -0.005 |
Token | smiles |
Token ID | 21845 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
aman | +0.031 |
destination | +0.031 |
heit | +0.031 |
isn | +0.029 |
mmm | +0.028 |
Neg logit contributions | |
blood | -0.029 |
blown | -0.027 |
Blood | -0.027 |
bitten | -0.026 |
spilled | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
blown | +0.044 |
Blood | +0.043 |
blood | +0.042 |
bitten | +0.042 |
spilled | +0.038 |
Neg logit contributions | |
destination | -0.043 |
isn | -0.041 |
aman | -0.040 |
ement | -0.039 |
heit | -0.039 |
Token | going |
Token ID | 1016 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
blown | +0.007 |
blood | +0.007 |
Blood | +0.007 |
bitten | +0.007 |
spilled | +0.006 |
Neg logit contributions | |
destination | -0.011 |
aman | -0.010 |
heit | -0.010 |
isn | -0.010 |
ement | -0.010 |
Token | missing |
Token ID | 4814 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
destination | +0.054 |
aman | +0.052 |
isn | +0.052 |
heit | +0.052 |
ement | +0.050 |
Neg logit contributions | |
blown | -0.031 |
blood | -0.031 |
Blood | -0.030 |
bitten | -0.029 |
spilled | -0.025 |
Token | ! |
Token ID | 0 |
Feature activation | -1.83e-01 |
Pos logit contributions | |
heit | +0.005 |
aman | +0.005 |
destination | +0.004 |
ement | +0.004 |
hew | +0.004 |
Neg logit contributions | |
blown | -0.003 |
blood | -0.003 |
bitten | -0.003 |
spilled | -0.002 |
Blood | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
Blood | +0.003 |
blown | +0.003 |
blood | +0.003 |
bitten | +0.003 |
spilled | +0.002 |
Neg logit contributions | |
destination | -0.006 |
heit | -0.006 |
aman | -0.006 |
isn | -0.006 |
ement | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
Blood | +0.006 |
blood | +0.006 |
blown | +0.005 |
bitten | +0.005 |
spilled | +0.004 |
Neg logit contributions | |
destination | -0.013 |
heit | -0.012 |
aman | -0.012 |
isn | -0.012 |
ement | -0.012 |
Token | The |
Token ID | 464 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Blood | +0.014 |
blown | +0.014 |
blood | +0.013 |
bitten | +0.013 |
spilled | +0.012 |
Neg logit contributions | |
destination | -0.019 |
isn | -0.018 |
ement | -0.018 |
aman | -0.018 |
heit | -0.018 |
Token | mother |
Token ID | 2802 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
blown | +0.024 |
Blood | +0.024 |
blood | +0.024 |
bitten | +0.023 |
elt | +0.019 |
Neg logit contributions | |
destination | -0.035 |
isn | -0.033 |
aman | -0.033 |
heit | -0.032 |
ement | -0.031 |
Token | said |
Token ID | 531 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
blown | +0.023 |
blood | +0.023 |
Blood | +0.023 |
bitten | +0.022 |
spilled | +0.020 |
Neg logit contributions | |
destination | -0.031 |
aman | -0.030 |
isn | -0.030 |
heit | -0.030 |
ement | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
destination | +0.013 |
aman | +0.012 |
heit | +0.012 |
isn | +0.012 |
hew | +0.011 |
Neg logit contributions | |
Blood | -0.012 |
blood | -0.012 |
blown | -0.012 |
bitten | -0.011 |
spilled | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
destination | +0.013 |
aman | +0.013 |
heit | +0.013 |
isn | +0.012 |
ement | +0.012 |
Neg logit contributions | |
Blood | -0.007 |
blood | -0.007 |
blown | -0.007 |
bitten | -0.006 |
spilled | -0.006 |
Token | What |
Token ID | 2061 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
destination | +0.020 |
heit | +0.019 |
isn | +0.019 |
ement | +0.019 |
aman | +0.018 |
Neg logit contributions | |
blown | -0.012 |
blood | -0.012 |
Blood | -0.012 |
bitten | -0.011 |
spilled | -0.010 |
Token | too |
Token ID | 1165 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
blood | +0.000 |
blown | +0.000 |
Blood | +0.000 |
bitten | +0.000 |
spilled | +0.000 |
Neg logit contributions | |
heit | -0.000 |
destination | -0.000 |
aman | -0.000 |
isn | -0.000 |
hew | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
blown | +0.010 |
blood | +0.010 |
Blood | +0.010 |
bitten | +0.009 |
spilled | +0.008 |
Neg logit contributions | |
heit | -0.017 |
aman | -0.016 |
destination | -0.016 |
isn | -0.015 |
hew | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
blown | +0.007 |
blood | +0.007 |
Blood | +0.007 |
bitten | +0.007 |
spilled | +0.006 |
Neg logit contributions | |
destination | -0.021 |
aman | -0.021 |
heit | -0.021 |
isn | -0.020 |
ement | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
destination | +0.006 |
aman | +0.006 |
heit | +0.006 |
ement | +0.006 |
isn | +0.006 |
Neg logit contributions | |
blown | -0.004 |
blood | -0.003 |
bitten | -0.003 |
Blood | -0.003 |
spilled | -0.003 |
Token | restless |
Token ID | 42537 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
destination | +0.012 |
exactly | +0.011 |
isn | +0.011 |
aman | +0.011 |
heit | +0.010 |
Neg logit contributions | |
blood | -0.015 |
Blood | -0.015 |
blown | -0.014 |
bitten | -0.014 |
spilled | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
heit | +0.010 |
aman | +0.010 |
destination | +0.010 |
hew | +0.009 |
mmm | +0.009 |
Neg logit contributions | |
blood | -0.007 |
blown | -0.007 |
bitten | -0.006 |
Blood | -0.006 |
spilled | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
destination | +0.019 |
isn | +0.018 |
aman | +0.018 |
heit | +0.018 |
ement | +0.017 |
Neg logit contributions | |
blown | -0.014 |
blood | -0.014 |
Blood | -0.014 |
bitten | -0.014 |
spilled | -0.012 |
Token | bike |
Token ID | 7161 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
blown | +0.035 |
Blood | +0.034 |
bitten | +0.034 |
blood | +0.033 |
spilled | +0.029 |
Neg logit contributions | |
destination | -0.046 |
aman | -0.045 |
isn | -0.044 |
heit | -0.043 |
ement | -0.042 |
Token | had |
Token ID | 550 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
blown | +0.024 |
blood | +0.023 |
Blood | +0.023 |
bitten | +0.022 |
spilled | +0.020 |
Neg logit contributions | |
destination | -0.029 |
aman | -0.029 |
heit | -0.029 |
isn | -0.028 |
ement | -0.027 |
Token | made |
Token ID | 925 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
Blood | +0.027 |
blown | +0.026 |
blood | +0.026 |
bitten | +0.025 |
spilled | +0.022 |
Neg logit contributions | |
destination | -0.039 |
isn | -0.038 |
aman | -0.037 |
heit | -0.036 |
exactly | -0.035 |
Token | him |
Token ID | 683 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
blood | +0.039 |
blown | +0.039 |
Blood | +0.038 |
bitten | +0.037 |
spilled | +0.032 |
Neg logit contributions | |
destination | -0.069 |
heit | -0.068 |
aman | -0.068 |
isn | -0.066 |
ement | -0.064 |
Token | much |
Token ID | 881 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
destination | +0.020 |
aman | +0.019 |
heit | +0.018 |
isn | +0.016 |
bek | +0.016 |
Neg logit contributions | |
blood | -0.013 |
Blood | -0.013 |
blown | -0.012 |
bitten | -0.012 |
spilled | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
blood | +0.024 |
blown | +0.021 |
bitten | +0.020 |
Blood | +0.019 |
spilled | +0.019 |
Neg logit contributions | |
heit | -0.049 |
destination | -0.047 |
aman | -0.046 |
hew | -0.046 |
bek | -0.043 |
Token | |
Token ID | 220 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
destination | +0.029 |
heit | +0.029 |
aman | +0.028 |
ement | +0.027 |
exactly | +0.026 |
Neg logit contributions | |
Blood | -0.012 |
blood | -0.010 |
blown | -0.010 |
bitten | -0.009 |
elt | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
blown | +0.028 |
blood | +0.028 |
Blood | +0.028 |
bitten | +0.027 |
spilled | +0.024 |
Neg logit contributions | |
destination | -0.037 |
aman | -0.036 |
heit | -0.036 |
isn | -0.035 |
ement | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
destination | +0.016 |
aman | +0.015 |
heit | +0.015 |
isn | +0.015 |
ement | +0.014 |
Neg logit contributions | |
Blood | -0.011 |
blown | -0.011 |
blood | -0.010 |
bitten | -0.010 |
spilled | -0.009 |
Token | Sam |
Token ID | 16305 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
destination | +0.007 |
isn | +0.007 |
ement | +0.006 |
heit | +0.006 |
aman | +0.006 |
Neg logit contributions | |
Blood | -0.005 |
blown | -0.005 |
blood | -0.005 |
bitten | -0.005 |
Tweet | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
destination | +0.025 |
heit | +0.024 |
ement | +0.023 |
aman | +0.023 |
isn | +0.023 |
Neg logit contributions | |
blown | -0.015 |
blood | -0.014 |
bitten | -0.014 |
spilled | -0.014 |
Blood | -0.014 |
Token | his |
Token ID | 465 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
blown | +0.048 |
Blood | +0.044 |
blood | +0.043 |
bitten | +0.043 |
plets | +0.041 |
Neg logit contributions | |
isn | -0.041 |
destination | -0.039 |
heit | -0.038 |
aman | -0.038 |
why | -0.037 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
blown | +0.040 |
Blood | +0.040 |
blood | +0.039 |
bitten | +0.039 |
spilled | +0.034 |
Neg logit contributions | |
destination | -0.044 |
isn | -0.042 |
aman | -0.042 |
heit | -0.041 |
ement | -0.040 |
Token | had |
Token ID | 550 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
blown | +0.013 |
blood | +0.012 |
bitten | +0.012 |
spilled | +0.011 |
Blood | +0.011 |
Neg logit contributions | |
destination | -0.027 |
heit | -0.027 |
isn | -0.026 |
aman | -0.026 |
ement | -0.026 |
Token | discovered |
Token ID | 5071 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
blown | +0.000 |
blood | +0.000 |
bitten | +0.000 |
Blood | +0.000 |
spilled | +0.000 |
Neg logit contributions | |
destination | -0.001 |
heit | -0.001 |
aman | -0.001 |
isn | -0.001 |
ement | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
destination | +0.062 |
aman | +0.062 |
heit | +0.060 |
ement | +0.058 |
hew | +0.057 |
Neg logit contributions | |
blown | -0.046 |
blood | -0.045 |
bitten | -0.044 |
Blood | -0.043 |
spilled | -0.042 |
Token | |
Token ID | 220 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
destination | +0.041 |
heit | +0.040 |
aman | +0.039 |
ement | +0.038 |
isn | +0.036 |
Neg logit contributions | |
Blood | -0.021 |
blood | -0.018 |
blown | -0.017 |
bitten | -0.017 |
elt | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +4.29e-01 |
Pos logit contributions | |
Blood | +0.022 |
blood | +0.021 |
blown | +0.021 |
bitten | +0.020 |
spilled | +0.018 |
Neg logit contributions | |
destination | -0.031 |
heit | -0.030 |
aman | -0.030 |
isn | -0.029 |
ement | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +6.36e-02 |
Pos logit contributions | |
destination | +0.014 |
heit | +0.013 |
isn | +0.013 |
aman | +0.013 |
ement | +0.012 |
Neg logit contributions | |
Blood | -0.008 |
blood | -0.007 |
blown | -0.007 |
bitten | -0.007 |
Tweet | -0.006 |
Token | The |
Token ID | 464 |
Feature activation | -8.21e-01 |
Pos logit contributions | |
destination | +0.002 |
isn | +0.002 |
heit | +0.002 |
ement | +0.002 |
aman | +0.002 |
Neg logit contributions | |
Blood | -0.001 |
Tweet | -0.001 |
blown | -0.001 |
blood | -0.001 |
bitten | -0.001 |
Token | end |
Token ID | 886 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
blood | +0.016 |
blown | +0.015 |
Blood | +0.014 |
bitten | +0.014 |
spilled | +0.013 |
Neg logit contributions | |
destination | -0.024 |
aman | -0.024 |
heit | -0.024 |
isn | -0.024 |
ement | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
blood | +0.035 |
Blood | +0.034 |
bitten | +0.027 |
opener | +0.027 |
cat | +0.026 |
Neg logit contributions | |
heit | -0.128 |
aman | -0.126 |
destination | -0.124 |
hew | -0.116 |
destinations | -0.112 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.03e-03 |
Pos logit contributions | |
heit | +0.001 |
destination | +0.001 |
aman | +0.001 |
ement | +0.001 |
isn | +0.001 |
Neg logit contributions | |
Blood | -0.001 |
blood | -0.001 |
blown | -0.001 |
bitten | -0.001 |
elt | -0.001 |
Token | John |
Token ID | 7554 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
destination | +0.000 |
aman | +0.000 |
heit | +0.000 |
isn | +0.000 |
ement | +0.000 |
Neg logit contributions | |
blown | -0.000 |
blood | -0.000 |
Blood | -0.000 |
bitten | -0.000 |
spilled | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | +9.92e-02 |
Pos logit contributions | |
destination | +0.058 |
heit | +0.056 |
aman | +0.056 |
isn | +0.055 |
ement | +0.054 |
Neg logit contributions | |
blown | -0.039 |
blood | -0.039 |
Blood | -0.038 |
bitten | -0.038 |
spilled | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
destination | +0.003 |
aman | +0.003 |
isn | +0.002 |
heit | +0.002 |
exactly | +0.002 |
Neg logit contributions | |
blood | -0.002 |
blown | -0.002 |
Blood | -0.002 |
bitten | -0.002 |
spilled | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -6.46e-01 |
Pos logit contributions | |
destination | +0.001 |
isn | +0.001 |
aman | +0.001 |
ement | +0.001 |
heit | +0.001 |
Neg logit contributions | |
Blood | -0.001 |
blown | -0.001 |
blood | -0.001 |
bitten | -0.001 |
spilled | -0.001 |
Token | They |
Token ID | 1119 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
blown | +0.018 |
blood | +0.017 |
bitten | +0.017 |
Blood | +0.017 |
spilled | +0.015 |
Neg logit contributions | |
destination | -0.014 |
isn | -0.014 |
aman | -0.014 |
heit | -0.013 |
ement | -0.013 |
Token | had |
Token ID | 550 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
blood | +0.024 |
blown | +0.024 |
Blood | +0.024 |
bitten | +0.023 |
elt | +0.020 |
Neg logit contributions | |
destination | -0.027 |
isn | -0.026 |
heit | -0.025 |
aman | -0.025 |
hew | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
blown | +0.044 |
blood | +0.044 |
Blood | +0.044 |
bitten | +0.042 |
elt | +0.037 |
Neg logit contributions | |
destination | -0.059 |
isn | -0.057 |
aman | -0.055 |
heit | -0.054 |
exactly | -0.053 |
Token | box |
Token ID | 3091 |
Feature activation | +9.50e-01 |
Pos logit contributions | |
aman | +0.006 |
heit | +0.006 |
destination | +0.006 |
isn | +0.006 |
ement | +0.006 |
Neg logit contributions | |
blood | -0.003 |
Blood | -0.003 |
blown | -0.003 |
bitten | -0.003 |
spilled | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
destination | +0.026 |
isn | +0.024 |
aman | +0.024 |
exactly | +0.024 |
forever | +0.023 |
Neg logit contributions | |
blood | -0.020 |
Blood | -0.020 |
blown | -0.020 |
bitten | -0.020 |
spilled | -0.017 |
Token | shapes |
Token ID | 15268 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
blown | +0.061 |
Blood | +0.059 |
blood | +0.059 |
bitten | +0.058 |
spilled | +0.050 |
Neg logit contributions | |
destination | -0.091 |
isn | -0.088 |
aman | -0.088 |
heit | -0.087 |
ement | -0.083 |
Token | that |
Token ID | 326 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
destination | +0.002 |
isn | +0.002 |
ement | +0.002 |
aman | +0.002 |
exactly | +0.002 |
Neg logit contributions | |
Blood | -0.002 |
blown | -0.002 |
blood | -0.002 |
bitten | -0.002 |
spilled | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
blown | +0.007 |
blood | +0.007 |
Blood | +0.007 |
bitten | +0.007 |
spilled | +0.006 |
Neg logit contributions | |
destination | -0.010 |
isn | -0.010 |
aman | -0.010 |
heit | -0.010 |
ement | -0.009 |
Token | circles |
Token ID | 13332 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Blood | +0.062 |
blood | +0.060 |
blown | +0.058 |
bitten | +0.057 |
elt | +0.054 |
Neg logit contributions | |
destination | -0.079 |
isn | -0.077 |
exactly | -0.072 |
forever | -0.069 |
aman | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
destination | +0.008 |
isn | +0.008 |
aman | +0.008 |
heit | +0.007 |
ement | +0.007 |
Neg logit contributions | |
blown | -0.008 |
blood | -0.008 |
Blood | -0.008 |
bitten | -0.008 |
spilled | -0.007 |
Token | 't |
Token ID | 470 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
destination | +0.019 |
isn | +0.019 |
aman | +0.018 |
heit | +0.018 |
!' | +0.017 |
Neg logit contributions | |
blood | -0.014 |
Blood | -0.014 |
blown | -0.014 |
bitten | -0.014 |
elt | -0.012 |
Token | get |
Token ID | 651 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
Blood | +0.040 |
blood | +0.039 |
blown | +0.038 |
bitten | +0.037 |
elt | +0.034 |
Neg logit contributions | |
destination | -0.055 |
isn | -0.053 |
aman | -0.052 |
heit | -0.051 |
forever | -0.048 |
Token | better |
Token ID | 1365 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
Blood | +0.013 |
blood | +0.012 |
blown | +0.012 |
bitten | +0.011 |
spilled | +0.010 |
Neg logit contributions | |
destination | -0.025 |
isn | -0.025 |
aman | -0.024 |
heit | -0.024 |
exactly | -0.023 |
Token | without |
Token ID | 1231 |
Feature activation | -9.06e-01 |
Pos logit contributions | |
blown | +0.019 |
blood | +0.019 |
bitten | +0.018 |
Blood | +0.017 |
spilled | +0.016 |
Neg logit contributions | |
heit | -0.022 |
destination | -0.022 |
aman | -0.022 |
isn | -0.021 |
ement | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
blown | +0.018 |
blood | +0.018 |
bitten | +0.017 |
Blood | +0.017 |
spilled | +0.015 |
Neg logit contributions | |
destination | -0.027 |
isn | -0.026 |
aman | -0.026 |
heit | -0.025 |
ement | -0.025 |
Token | band |
Token ID | 4097 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
destination | +0.010 |
aman | +0.010 |
isn | +0.010 |
heit | +0.010 |
ement | +0.010 |
Neg logit contributions | |
Blood | -0.005 |
blown | -0.005 |
blood | -0.005 |
bitten | -0.005 |
spilled | -0.004 |
Token | age |
Token ID | 496 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
Blood | +0.080 |
blood | +0.079 |
blown | +0.077 |
bitten | +0.072 |
spilled | +0.067 |
Neg logit contributions | |
destination | -0.089 |
isn | -0.088 |
aman | -0.086 |
!' | -0.082 |
hew | -0.081 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
blown | +0.095 |
blood | +0.094 |
Blood | +0.092 |
bitten | +0.091 |
spilled | +0.082 |
Neg logit contributions | |
destination | -0.109 |
aman | -0.107 |
heit | -0.106 |
isn | -0.105 |
ement | -0.100 |
Token | said |
Token ID | 531 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
destination | +0.006 |
aman | +0.006 |
heit | +0.006 |
isn | +0.006 |
ement | +0.006 |
Neg logit contributions | |
blown | -0.005 |
blood | -0.005 |
Blood | -0.004 |
bitten | -0.004 |
spilled | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
destination | +0.012 |
aman | +0.011 |
heit | +0.011 |
hew | +0.011 |
isn | +0.010 |
Neg logit contributions | |
Blood | -0.008 |
blood | -0.008 |
blown | -0.008 |
bitten | -0.008 |
spilled | -0.007 |
Token | would |
Token ID | 561 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
destination | +0.045 |
aman | +0.045 |
heit | +0.044 |
ement | +0.041 |
isn | +0.040 |
Neg logit contributions | |
blown | -0.045 |
blood | -0.044 |
bitten | -0.044 |
Blood | -0.043 |
spilled | -0.042 |
Token | After |
Token ID | 3260 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Blood | +0.005 |
blown | +0.004 |
bitten | +0.004 |
blood | +0.004 |
Tweet | +0.004 |
Neg logit contributions | |
destination | -0.008 |
isn | -0.007 |
heit | -0.007 |
ement | -0.007 |
aman | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
blown | +0.011 |
blood | +0.011 |
Blood | +0.011 |
bitten | +0.011 |
spilled | +0.009 |
Neg logit contributions | |
destination | -0.019 |
aman | -0.019 |
isn | -0.018 |
heit | -0.018 |
ement | -0.018 |
Token | while |
Token ID | 981 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
destination | +0.030 |
aman | +0.029 |
isn | +0.029 |
heit | +0.029 |
ement | +0.028 |
Neg logit contributions | |
blown | -0.021 |
Blood | -0.021 |
blood | -0.021 |
bitten | -0.020 |
spilled | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
blown | +0.033 |
blood | +0.033 |
Blood | +0.032 |
bitten | +0.032 |
spilled | +0.030 |
Neg logit contributions | |
destination | -0.017 |
aman | -0.016 |
isn | -0.015 |
heit | -0.015 |
ement | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
blown | +0.010 |
blood | +0.010 |
Blood | +0.010 |
bitten | +0.009 |
spilled | +0.008 |
Neg logit contributions | |
destination | -0.017 |
aman | -0.016 |
isn | -0.016 |
heit | -0.016 |
ement | -0.015 |
Token | started |
Token ID | 2067 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
blood | +0.016 |
blown | +0.016 |
Blood | +0.016 |
bitten | +0.015 |
spilled | +0.013 |
Neg logit contributions | |
destination | -0.020 |
aman | -0.020 |
isn | -0.019 |
heit | -0.019 |
ement | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
Blood | +0.061 |
blood | +0.058 |
blown | +0.057 |
bitten | +0.055 |
orns | +0.051 |
Neg logit contributions | |
destination | -0.075 |
aman | -0.071 |
exactly | -0.067 |
isn | -0.067 |
int | -0.064 |
Token | rain |
Token ID | 6290 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
destination | +0.014 |
aman | +0.014 |
heit | +0.013 |
isn | +0.013 |
ement | +0.012 |
Neg logit contributions | |
Blood | -0.008 |
blown | -0.007 |
bitten | -0.007 |
blood | -0.007 |
elt | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
destination | +0.007 |
aman | +0.007 |
isn | +0.006 |
ement | +0.006 |
forever | +0.006 |
Neg logit contributions | |
Blood | -0.010 |
blood | -0.009 |
bitten | -0.009 |
blown | -0.009 |
robbers | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
destination | +0.005 |
isn | +0.005 |
aman | +0.005 |
heit | +0.005 |
exactly | +0.004 |
Neg logit contributions | |
blown | -0.003 |
Blood | -0.003 |
blood | -0.003 |
bitten | -0.003 |
spilled | -0.003 |
Token | infant |
Token ID | 11212 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
Blood | +0.021 |
blown | +0.019 |
blood | +0.019 |
bitten | +0.019 |
elt | +0.016 |
Neg logit contributions | |
destination | -0.034 |
isn | -0.033 |
aman | -0.033 |
heit | -0.032 |
ement | -0.031 |
Token | at |
Token ID | 379 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
destination | +0.005 |
aman | +0.004 |
heit | +0.004 |
isn | +0.004 |
ement | +0.004 |
Neg logit contributions | |
blown | -0.005 |
blood | -0.005 |
Blood | -0.005 |
bitten | -0.005 |
spilled | -0.004 |
Token | his |
Token ID | 465 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
destination | +0.064 |
aman | +0.062 |
heit | +0.062 |
isn | +0.062 |
ement | +0.059 |
Neg logit contributions | |
blood | -0.038 |
blown | -0.036 |
Blood | -0.035 |
bitten | -0.034 |
spilled | -0.030 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
aman | +0.007 |
heit | +0.007 |
destination | +0.007 |
isn | +0.007 |
hew | +0.007 |
Neg logit contributions | |
blood | -0.005 |
blown | -0.005 |
Blood | -0.005 |
bitten | -0.005 |
spilled | -0.004 |
Token | with |
Token ID | 351 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
blown | +0.003 |
blood | +0.003 |
bitten | +0.003 |
spilled | +0.003 |
Blood | +0.003 |
Neg logit contributions | |
heit | -0.006 |
destination | -0.006 |
isn | -0.005 |
aman | -0.005 |
virtue | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
destination | +0.043 |
aman | +0.041 |
isn | +0.041 |
heit | +0.041 |
ement | +0.040 |
Neg logit contributions | |
Blood | -0.024 |
blown | -0.024 |
bitten | -0.022 |
blood | -0.022 |
spilled | -0.020 |
Token | smile |
Token ID | 8212 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
destination | +0.061 |
aman | +0.060 |
heit | +0.059 |
isn | +0.059 |
hew | +0.059 |
Neg logit contributions | |
blood | -0.034 |
blown | -0.033 |
Blood | -0.031 |
bitten | -0.031 |
spilled | -0.028 |
Token | and |
Token ID | 290 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
blown | +0.079 |
blood | +0.078 |
Blood | +0.076 |
bitten | +0.075 |
spilled | +0.068 |
Neg logit contributions | |
destination | -0.104 |
heit | -0.101 |
aman | -0.100 |
isn | -0.099 |
hew | -0.095 |
Token | she |
Token ID | 673 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
destination | +0.000 |
aman | +0.000 |
isn | +0.000 |
heit | +0.000 |
ement | +0.000 |
Neg logit contributions | |
blown | -0.000 |
blood | -0.000 |
Blood | -0.000 |
bitten | -0.000 |
spilled | -0.000 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
destination | +0.004 |
aman | +0.004 |
heit | +0.004 |
isn | +0.004 |
ement | +0.004 |
Neg logit contributions | |
blown | -0.003 |
blood | -0.002 |
bitten | -0.002 |
Blood | -0.002 |
spilled | -0.002 |
Token | back |
Token ID | 736 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
blown | +0.025 |
blood | +0.024 |
Blood | +0.024 |
bitten | +0.023 |
elt | +0.021 |
Neg logit contributions | |
heit | -0.033 |
destination | -0.032 |
aman | -0.032 |
isn | -0.032 |
hew | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
blown | +0.009 |
Blood | +0.009 |
blood | +0.009 |
bitten | +0.009 |
elt | +0.008 |
Neg logit contributions | |
destination | -0.017 |
heit | -0.017 |
aman | -0.017 |
isn | -0.016 |
hew | -0.016 |