Token | Lily |
Token ID | 20037 |
Feature activation | +6.25e-02 |
Pos logit contributions | |
means | +0.018 |
Bird | +0.018 |
Fle | +0.017 |
Bees | +0.016 |
calls | +0.016 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.019 |
+. | -0.018 |
THE | -0.017 |
"! | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
pron | +0.004 |
lifetime | +0.004 |
+. | +0.004 |
THE | +0.004 |
"! | +0.004 |
Neg logit contributions | |
means | -0.002 |
Bird | -0.002 |
Fle | -0.002 |
calls | -0.002 |
Bee | -0.002 |
Token | Ben |
Token ID | 3932 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
pron | +0.039 |
lifetime | +0.035 |
+. | +0.032 |
THE | +0.032 |
ouse | +0.031 |
Neg logit contributions | |
means | -0.021 |
Bird | -0.021 |
Fle | -0.020 |
Cro | -0.018 |
Bees | -0.018 |
Token | on |
Token ID | 319 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
pron | +0.037 |
lifetime | +0.032 |
+. | +0.030 |
THE | +0.029 |
possession | +0.029 |
Neg logit contributions | |
means | -0.021 |
Bird | -0.021 |
Fle | -0.019 |
calls | -0.019 |
Bunny | -0.018 |
Token | their |
Token ID | 511 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
pron | +0.147 |
lifetime | +0.135 |
THE | +0.121 |
ouse | +0.121 |
+. | +0.121 |
Neg logit contributions | |
Bird | -0.081 |
means | -0.080 |
Fle | -0.075 |
Bee | -0.070 |
Cro | -0.069 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
pron | +0.056 |
lifetime | +0.049 |
"! | +0.047 |
+. | +0.046 |
THE | +0.045 |
Neg logit contributions | |
Bird | -0.044 |
means | -0.041 |
Fle | -0.040 |
calls | -0.040 |
Bee | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
pron | +0.336 |
lifetime | +0.320 |
+. | +0.285 |
THE | +0.278 |
ileen | +0.269 |
Neg logit contributions | |
means | -0.163 |
Bird | -0.152 |
calls | -0.131 |
Fle | -0.130 |
Bee | -0.130 |
Token |
|
Token ID | 198 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
pron | +0.022 |
lifetime | +0.019 |
THE | +0.018 |
+. | +0.018 |
brand | +0.018 |
Neg logit contributions | |
means | -0.015 |
Bird | -0.014 |
acts | -0.013 |
Fle | -0.013 |
calls | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
pron | +0.023 |
lifetime | +0.021 |
+. | +0.019 |
THE | +0.018 |
ouse | +0.018 |
Neg logit contributions | |
means | -0.012 |
Bird | -0.012 |
Fle | -0.011 |
Cro | -0.010 |
Bee | -0.010 |
Token | " |
Token ID | 1 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
pron | +0.016 |
lifetime | +0.015 |
brand | +0.013 |
+. | +0.013 |
possession | +0.013 |
Neg logit contributions | |
Bird | -0.014 |
means | -0.013 |
Fle | -0.013 |
Bees | -0.012 |
Bee | -0.012 |
Token | O |
Token ID | 46 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
pron | +0.058 |
lifetime | +0.048 |
THE | +0.044 |
+. | +0.044 |
"! | +0.041 |
Neg logit contributions | |
means | -0.056 |
Bird | -0.055 |
Fle | -0.053 |
calls | -0.051 |
Cro | -0.051 |
Token | and |
Token ID | 290 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
pron | +0.132 |
lifetime | +0.127 |
+. | +0.114 |
joy | +0.111 |
Majesty | +0.109 |
Neg logit contributions | |
means | -0.051 |
from | -0.044 |
Bird | -0.041 |
Fle | -0.038 |
Bunny | -0.038 |
Token | his |
Token ID | 465 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
means | +0.015 |
Bird | +0.014 |
Fle | +0.013 |
calls | +0.013 |
Bunny | +0.013 |
Neg logit contributions | |
pron | -0.020 |
lifetime | -0.018 |
+. | -0.016 |
THE | -0.016 |
"! | -0.016 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
pron | +0.020 |
lifetime | +0.019 |
THE | +0.018 |
"! | +0.018 |
arest | +0.017 |
Neg logit contributions | |
Bird | -0.018 |
Fle | -0.018 |
calls | -0.017 |
means | -0.017 |
Bunny | -0.017 |
Token | saw |
Token ID | 2497 |
Feature activation | +7.82e-01 |
Pos logit contributions | |
pron | +0.130 |
lifetime | +0.116 |
THE | +0.112 |
+. | +0.111 |
arest | +0.107 |
Neg logit contributions | |
means | -0.068 |
Bird | -0.063 |
calls | -0.057 |
Bunny | -0.057 |
meant | -0.054 |
Token | his |
Token ID | 465 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
pron | +0.052 |
lifetime | +0.047 |
THE | +0.043 |
ouse | +0.042 |
+. | +0.042 |
Neg logit contributions | |
means | -0.032 |
Bird | -0.030 |
Fle | -0.028 |
calls | -0.026 |
Cro | -0.026 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
pron | +0.059 |
lifetime | +0.052 |
THE | +0.049 |
"! | +0.048 |
+. | +0.047 |
Neg logit contributions | |
means | -0.046 |
Bird | -0.044 |
Fle | -0.043 |
calls | -0.043 |
acts | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
pron | +0.301 |
lifetime | +0.285 |
+. | +0.254 |
THE | +0.252 |
possession | +0.245 |
Neg logit contributions | |
means | -0.186 |
Bird | -0.170 |
calls | -0.154 |
Fle | -0.154 |
Bunny | -0.150 |
Token | All |
Token ID | 1439 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
means | +0.005 |
Bird | +0.004 |
Fle | +0.004 |
Cro | +0.004 |
calls | +0.004 |
Neg logit contributions | |
pron | -0.009 |
lifetime | -0.008 |
+. | -0.008 |
THE | -0.008 |
"! | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -8.84e-01 |
Pos logit contributions | |
Bird | +0.010 |
means | +0.010 |
Fle | +0.010 |
Cro | +0.009 |
Bees | +0.009 |
Neg logit contributions | |
pron | -0.015 |
lifetime | -0.013 |
+. | -0.012 |
THE | -0.012 |
possession | -0.011 |
Token | other |
Token ID | 584 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
means | +0.037 |
Bird | +0.037 |
Fle | +0.035 |
calls | +0.033 |
Cro | +0.032 |
Neg logit contributions | |
pron | -0.056 |
lifetime | -0.049 |
+. | -0.045 |
THE | -0.045 |
ouse | -0.044 |
Token | kids |
Token ID | 3988 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
pron | +0.016 |
lifetime | +0.014 |
+. | +0.013 |
THE | +0.013 |
"! | +0.012 |
Neg logit contributions | |
means | -0.012 |
Bird | -0.012 |
Fle | -0.011 |
Cro | -0.010 |
Bees | -0.010 |
Token | g |
Token ID | 308 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
pron | +0.043 |
lifetime | +0.041 |
THE | +0.040 |
reed | +0.039 |
possession | +0.039 |
Neg logit contributions | |
Bird | -0.030 |
means | -0.027 |
Fle | -0.026 |
Bunny | -0.025 |
Bee | -0.025 |
Token | iggle |
Token ID | 24082 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
pron | +0.054 |
lifetime | +0.049 |
THE | +0.044 |
+. | +0.044 |
"! | +0.041 |
Neg logit contributions | |
means | -0.036 |
Bird | -0.036 |
Fle | -0.035 |
calls | -0.032 |
Cro | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
means | +0.024 |
Bird | +0.023 |
Bunny | +0.020 |
Fle | +0.019 |
Bee | +0.019 |
Neg logit contributions | |
pron | -0.049 |
lifetime | -0.047 |
arest | -0.041 |
+. | -0.040 |
brand | -0.040 |
Token | stuck |
Token ID | 7819 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
pron | +0.054 |
lifetime | +0.048 |
THE | +0.044 |
+. | +0.044 |
ouse | +0.043 |
Neg logit contributions | |
means | -0.031 |
Bird | -0.031 |
Fle | -0.029 |
calls | -0.027 |
Cro | -0.027 |
Token | her |
Token ID | 607 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
pron | +0.055 |
lifetime | +0.050 |
ouse | +0.046 |
+. | +0.045 |
THE | +0.044 |
Neg logit contributions | |
Bird | -0.033 |
means | -0.030 |
Fle | -0.029 |
Bunny | -0.028 |
Cro | -0.028 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
pron | +0.065 |
lifetime | +0.061 |
THE | +0.055 |
+. | +0.054 |
Adam | +0.054 |
Neg logit contributions | |
Bird | -0.050 |
means | -0.046 |
Bunny | -0.045 |
Fle | -0.045 |
calls | -0.044 |
Token | in |
Token ID | 287 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
pron | +0.345 |
lifetime | +0.333 |
ileen | +0.298 |
+. | +0.291 |
THE | +0.286 |
Neg logit contributions | |
means | -0.121 |
from | -0.117 |
Bird | -0.116 |
Bunny | -0.099 |
Bee | -0.094 |
Token | the |
Token ID | 262 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
pron | +0.036 |
lifetime | +0.033 |
ouse | +0.030 |
+. | +0.029 |
THE | +0.029 |
Neg logit contributions | |
means | -0.018 |
Bird | -0.018 |
Fle | -0.017 |
Bee | -0.015 |
Cro | -0.015 |
Token | cool |
Token ID | 3608 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
pron | +0.069 |
lifetime | +0.062 |
+. | +0.057 |
ouse | +0.057 |
"! | +0.056 |
Neg logit contributions | |
Bird | -0.031 |
means | -0.030 |
Fle | -0.028 |
calls | -0.028 |
Cro | -0.026 |
Token | water |
Token ID | 1660 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
pron | +0.087 |
lifetime | +0.078 |
+. | +0.071 |
THE | +0.070 |
arest | +0.069 |
Neg logit contributions | |
means | -0.047 |
Bird | -0.046 |
Fle | -0.043 |
Bunny | -0.041 |
calls | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-03 |
Pos logit contributions | |
pron | +0.075 |
lifetime | +0.068 |
+. | +0.062 |
THE | +0.060 |
ouse | +0.059 |
Neg logit contributions | |
means | -0.042 |
Bird | -0.041 |
Fle | -0.036 |
calls | -0.036 |
Bunny | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
pron | +0.030 |
lifetime | +0.026 |
+. | +0.025 |
THE | +0.024 |
possession | +0.024 |
Neg logit contributions | |
means | -0.016 |
Bird | -0.015 |
Fle | -0.014 |
calls | -0.013 |
Cro | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
means | +0.009 |
Bird | +0.008 |
Fle | +0.008 |
calls | +0.008 |
Cro | +0.007 |
Neg logit contributions | |
pron | -0.012 |
lifetime | -0.010 |
+. | -0.010 |
THE | -0.009 |
ouse | -0.009 |
Token | water |
Token ID | 1660 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
pron | +0.024 |
lifetime | +0.020 |
ouse | +0.020 |
THE | +0.020 |
+. | +0.019 |
Neg logit contributions | |
Bird | -0.016 |
means | -0.015 |
Fle | -0.015 |
calls | -0.014 |
acts | -0.014 |
Token | on |
Token ID | 319 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
pron | +0.106 |
lifetime | +0.092 |
+. | +0.087 |
THE | +0.085 |
ouse | +0.083 |
Neg logit contributions | |
means | -0.066 |
Bird | -0.063 |
Fle | -0.057 |
calls | -0.056 |
Cro | -0.055 |
Token | his |
Token ID | 465 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
pron | +0.086 |
lifetime | +0.076 |
ouse | +0.070 |
+. | +0.069 |
THE | +0.068 |
Neg logit contributions | |
means | -0.052 |
Bird | -0.050 |
Fle | -0.048 |
Cro | -0.045 |
Bee | -0.043 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.51e+00 |
Pos logit contributions | |
pron | +0.041 |
+. | +0.033 |
"! | +0.032 |
THE | +0.031 |
lifetime | +0.031 |
Neg logit contributions | |
Bird | -0.027 |
calls | -0.026 |
Fle | -0.026 |
acts | -0.025 |
Cro | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
pron | +0.340 |
lifetime | +0.304 |
+. | +0.287 |
ileen | +0.282 |
THE | +0.281 |
Neg logit contributions | |
means | -0.122 |
Bird | -0.110 |
calls | -0.098 |
from | -0.097 |
meant | -0.096 |
Token | He |
Token ID | 679 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
means | +0.000 |
Bird | +0.000 |
Fle | +0.000 |
Cro | +0.000 |
calls | +0.000 |
Neg logit contributions | |
pron | -0.001 |
lifetime | -0.001 |
+. | -0.001 |
THE | -0.001 |
"! | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
means | +0.010 |
Bird | +0.010 |
Fle | +0.009 |
Cro | +0.009 |
calls | +0.009 |
Neg logit contributions | |
pron | -0.016 |
lifetime | -0.014 |
+. | -0.013 |
THE | -0.012 |
"! | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
pron | +0.102 |
ouse | +0.087 |
arest | +0.081 |
lifetime | +0.081 |
+. | +0.078 |
Neg logit contributions | |
means | -0.052 |
Bird | -0.051 |
meant | -0.044 |
Fle | -0.044 |
calls | -0.043 |
Token | greatest |
Token ID | 6000 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
pron | +0.002 |
lifetime | +0.002 |
ouse | +0.002 |
+. | +0.002 |
THE | +0.002 |
Neg logit contributions | |
Bird | -0.002 |
means | -0.002 |
Fle | -0.002 |
calls | -0.001 |
Cro | -0.001 |
Token | from |
Token ID | 422 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
means | +0.030 |
Bird | +0.029 |
Fle | +0.027 |
Cro | +0.026 |
calls | +0.025 |
Neg logit contributions | |
pron | -0.045 |
lifetime | -0.040 |
+. | -0.036 |
THE | -0.036 |
ouse | -0.035 |
Token | his |
Token ID | 465 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
means | +0.007 |
Bird | +0.007 |
Fle | +0.006 |
Cro | +0.006 |
calls | +0.006 |
Neg logit contributions | |
pron | -0.011 |
lifetime | -0.010 |
ouse | -0.009 |
THE | -0.009 |
+. | -0.009 |
Token | head |
Token ID | 1182 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
pron | +0.041 |
lifetime | +0.037 |
THE | +0.037 |
"! | +0.035 |
+. | +0.034 |
Neg logit contributions | |
Bird | -0.032 |
means | -0.031 |
calls | -0.030 |
Cro | -0.030 |
Fle | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
pron | +0.092 |
lifetime | +0.085 |
THE | +0.077 |
+. | +0.077 |
arest | +0.075 |
Neg logit contributions | |
means | -0.045 |
Bird | -0.042 |
Fle | -0.037 |
Cro | -0.036 |
calls | -0.035 |
Token | his |
Token ID | 465 |
Feature activation | +7.61e-01 |
Pos logit contributions | |
pron | +0.037 |
lifetime | +0.034 |
ouse | +0.031 |
THE | +0.031 |
+. | +0.030 |
Neg logit contributions | |
means | -0.023 |
Bird | -0.022 |
Fle | -0.021 |
Cro | -0.020 |
calls | -0.019 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
pron | +0.045 |
lifetime | +0.039 |
THE | +0.038 |
+. | +0.037 |
"! | +0.037 |
Neg logit contributions | |
Bird | -0.034 |
means | -0.032 |
calls | -0.031 |
Fle | -0.031 |
Cro | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
pron | +0.319 |
lifetime | +0.304 |
+. | +0.270 |
THE | +0.264 |
arest | +0.262 |
Neg logit contributions | |
means | -0.152 |
Bird | -0.133 |
from | -0.116 |
Fle | -0.116 |
Bee | -0.116 |
Token | They |
Token ID | 1119 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
means | +0.009 |
Bird | +0.009 |
Fle | +0.008 |
Cro | +0.008 |
Bees | +0.007 |
Neg logit contributions | |
pron | -0.020 |
lifetime | -0.018 |
+. | -0.017 |
THE | -0.017 |
"! | -0.016 |
Token | found |
Token ID | 1043 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
means | +0.013 |
Bird | +0.013 |
Fle | +0.012 |
Cro | +0.011 |
calls | +0.011 |
Neg logit contributions | |
pron | -0.020 |
lifetime | -0.018 |
+. | -0.016 |
THE | -0.016 |
"! | -0.016 |
Token | out |
Token ID | 503 |
Feature activation | +7.01e-01 |
Pos logit contributions | |
means | +0.004 |
Bird | +0.004 |
Fle | +0.004 |
Bees | +0.004 |
Cro | +0.004 |
Neg logit contributions | |
pron | -0.005 |
lifetime | -0.005 |
brand | -0.004 |
+. | -0.004 |
THE | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
pron | +0.043 |
lifetime | +0.038 |
ouse | +0.034 |
+. | +0.033 |
THE | +0.033 |
Neg logit contributions | |
means | -0.032 |
Bird | -0.031 |
Fle | -0.029 |
Cro | -0.028 |
Bee | -0.027 |
Token | up |
Token ID | 510 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
means | +0.015 |
Bird | +0.015 |
Fle | +0.014 |
Cro | +0.013 |
calls | +0.013 |
Neg logit contributions | |
pron | -0.019 |
lifetime | -0.017 |
+. | -0.015 |
ouse | -0.015 |
THE | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
means | +0.035 |
Bird | +0.035 |
Fle | +0.033 |
Cro | +0.031 |
Bee | +0.030 |
Neg logit contributions | |
pron | -0.049 |
lifetime | -0.042 |
+. | -0.038 |
ouse | -0.038 |
THE | -0.038 |
Token | tick |
Token ID | 4378 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
pron | +0.017 |
lifetime | +0.015 |
THE | +0.013 |
+. | +0.013 |
ouse | +0.013 |
Neg logit contributions | |
Bird | -0.011 |
means | -0.011 |
Fle | -0.010 |
Cro | -0.010 |
Bunny | -0.010 |
Token | led |
Token ID | 992 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
means | +0.056 |
Bird | +0.055 |
Fle | +0.053 |
Cro | +0.049 |
Bees | +0.049 |
Neg logit contributions | |
pron | -0.077 |
lifetime | -0.067 |
+. | -0.061 |
THE | -0.061 |
"! | -0.060 |
Token | her |
Token ID | 607 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
means | +0.005 |
Bird | +0.005 |
Fle | +0.005 |
Cro | +0.004 |
calls | +0.004 |
Neg logit contributions | |
pron | -0.008 |
lifetime | -0.007 |
+. | -0.006 |
THE | -0.006 |
ouse | -0.006 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
pron | +0.051 |
lifetime | +0.043 |
+. | +0.042 |
THE | +0.042 |
Adam | +0.041 |
Neg logit contributions | |
Bird | -0.035 |
Fle | -0.032 |
Bunny | -0.032 |
means | -0.031 |
Cro | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
pron | +0.317 |
lifetime | +0.292 |
+. | +0.273 |
ileen | +0.266 |
THE | +0.264 |
Neg logit contributions | |
Bird | -0.126 |
means | -0.121 |
from | -0.114 |
Bee | -0.110 |
Bunny | -0.109 |
Token | She |
Token ID | 1375 |
Feature activation | +4.36e-01 |
Pos logit contributions | |
pron | +0.001 |
lifetime | +0.001 |
+. | +0.001 |
ouse | +0.001 |
THE | +0.001 |
Neg logit contributions | |
means | -0.000 |
Bird | -0.000 |
Fle | -0.000 |
Bees | -0.000 |
calls | -0.000 |
Token | had |
Token ID | 550 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
pron | +0.029 |
lifetime | +0.026 |
+. | +0.025 |
THE | +0.024 |
"! | +0.024 |
Neg logit contributions | |
means | -0.016 |
Bird | -0.016 |
Fle | -0.014 |
Bee | -0.013 |
calls | -0.013 |
Token | so |
Token ID | 523 |
Feature activation | -5.23e-01 |
Pos logit contributions | |
pron | +0.110 |
lifetime | +0.094 |
ouse | +0.094 |
arest | +0.090 |
possession | +0.088 |
Neg logit contributions | |
Bird | -0.059 |
means | -0.055 |
Bunny | -0.051 |
meant | -0.050 |
Bee | -0.049 |
Token | much |
Token ID | 881 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
means | +0.034 |
Bird | +0.033 |
Fle | +0.032 |
Cro | +0.031 |
Bees | +0.031 |
Neg logit contributions | |
pron | -0.021 |
lifetime | -0.017 |
+. | -0.015 |
THE | -0.014 |
"! | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
means | +0.016 |
Bird | +0.015 |
Fle | +0.015 |
Bees | +0.014 |
calls | +0.014 |
Neg logit contributions | |
pron | -0.021 |
lifetime | -0.018 |
+. | -0.017 |
THE | -0.017 |
"! | -0.017 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
means | +0.026 |
Bird | +0.025 |
Fle | +0.024 |
calls | +0.022 |
Cro | +0.022 |
Neg logit contributions | |
pron | -0.041 |
lifetime | -0.036 |
+. | -0.034 |
THE | -0.033 |
"! | -0.033 |
Token | noticed |
Token ID | 6810 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
means | +0.003 |
Bird | +0.003 |
Fle | +0.002 |
calls | +0.002 |
Bee | +0.002 |
Neg logit contributions | |
pron | -0.004 |
lifetime | -0.003 |
THE | -0.003 |
+. | -0.003 |
possession | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
pron | +0.075 |
lifetime | +0.064 |
+. | +0.059 |
THE | +0.058 |
"! | +0.056 |
Neg logit contributions | |
means | -0.064 |
Bird | -0.063 |
Fle | -0.060 |
Cro | -0.057 |
Bees | -0.056 |
Token | her |
Token ID | 607 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
pron | +0.061 |
lifetime | +0.054 |
+. | +0.049 |
THE | +0.049 |
"! | +0.048 |
Neg logit contributions | |
means | -0.037 |
Bird | -0.036 |
Fle | -0.034 |
Cro | -0.032 |
calls | -0.032 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
pron | +0.087 |
lifetime | +0.077 |
+. | +0.070 |
THE | +0.070 |
"! | +0.069 |
Neg logit contributions | |
means | -0.055 |
Bird | -0.054 |
Fle | -0.051 |
Cro | -0.048 |
calls | -0.047 |
Token | were |
Token ID | 547 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
pron | +0.309 |
lifetime | +0.285 |
+. | +0.257 |
THE | +0.256 |
"! | +0.249 |
Neg logit contributions | |
means | -0.154 |
Bird | -0.144 |
Fle | -0.134 |
Cro | -0.125 |
calls | -0.123 |
Token | glowing |
Token ID | 21377 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
pron | +0.018 |
lifetime | +0.016 |
+. | +0.015 |
"! | +0.014 |
THE | +0.014 |
Neg logit contributions | |
Bird | -0.013 |
means | -0.013 |
Fle | -0.012 |
Cro | -0.012 |
Bunny | -0.012 |
Token | ! |
Token ID | 0 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
means | +0.029 |
Bird | +0.029 |
Fle | +0.027 |
Cro | +0.026 |
Bees | +0.026 |
Neg logit contributions | |
pron | -0.039 |
lifetime | -0.034 |
+. | -0.031 |
THE | -0.031 |
"! | -0.030 |
Token | She |
Token ID | 1375 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
pron | +0.040 |
lifetime | +0.035 |
+. | +0.034 |
"! | +0.033 |
ouse | +0.033 |
Neg logit contributions | |
means | -0.015 |
Bird | -0.014 |
Fle | -0.012 |
Cro | -0.012 |
acts | -0.011 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
pron | +0.028 |
lifetime | +0.024 |
+. | +0.022 |
THE | +0.022 |
ouse | +0.022 |
Neg logit contributions | |
means | -0.019 |
Bird | -0.019 |
Fle | -0.018 |
Cro | -0.017 |
Bees | -0.017 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
means | +0.022 |
Bird | +0.021 |
Fle | +0.020 |
Cro | +0.019 |
calls | +0.019 |
Neg logit contributions | |
pron | -0.021 |
lifetime | -0.018 |
+. | -0.016 |
THE | -0.016 |
ouse | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
means | +0.005 |
Bird | +0.005 |
calls | +0.004 |
Fle | +0.004 |
Bee | +0.004 |
Neg logit contributions | |
pron | -0.008 |
lifetime | -0.006 |
+. | -0.006 |
ouse | -0.006 |
arest | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
means | +0.009 |
Bird | +0.009 |
Fle | +0.009 |
calls | +0.008 |
Cro | +0.008 |
Neg logit contributions | |
pron | -0.011 |
lifetime | -0.009 |
+. | -0.008 |
THE | -0.008 |
ouse | -0.008 |
Token | made |
Token ID | 925 |
Feature activation | -8.90e-02 |
Pos logit contributions | |
means | +0.010 |
Bird | +0.010 |
Fle | +0.009 |
Cro | +0.009 |
Bees | +0.008 |
Neg logit contributions | |
pron | -0.017 |
lifetime | -0.015 |
+. | -0.013 |
THE | -0.013 |
"! | -0.013 |
Token | her |
Token ID | 607 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
means | +0.004 |
Bird | +0.004 |
Fle | +0.004 |
Cro | +0.003 |
Bees | +0.003 |
Neg logit contributions | |
pron | -0.005 |
lifetime | -0.005 |
+. | -0.004 |
THE | -0.004 |
"! | -0.004 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.40e+00 |
Pos logit contributions | |
pron | +0.062 |
lifetime | +0.053 |
+. | +0.049 |
"! | +0.048 |
arest | +0.047 |
Neg logit contributions | |
Bird | -0.043 |
means | -0.042 |
Fle | -0.040 |
calls | -0.038 |
Bee | -0.037 |
Token | start |
Token ID | 923 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
pron | +0.298 |
lifetime | +0.272 |
+. | +0.254 |
possession | +0.246 |
ileen | +0.243 |
Neg logit contributions | |
means | -0.151 |
Bird | -0.149 |
Fle | -0.133 |
Bee | -0.133 |
calls | -0.132 |
Token | to |
Token ID | 284 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
pron | +0.041 |
lifetime | +0.036 |
+. | +0.034 |
ileen | +0.033 |
ouse | +0.033 |
Neg logit contributions | |
means | -0.024 |
Bird | -0.023 |
Fle | -0.021 |
Bee | -0.020 |
calls | -0.020 |
Token | tap |
Token ID | 9814 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
Bird | +0.001 |
means | +0.001 |
Fle | +0.001 |
Bee | +0.001 |
Cro | +0.001 |
Neg logit contributions | |
pron | -0.002 |
lifetime | -0.002 |
ouse | -0.002 |
+. | -0.002 |
THE | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
means | +0.006 |
Bird | +0.006 |
Fle | +0.005 |
calls | +0.005 |
Bee | +0.005 |
Neg logit contributions | |
pron | -0.010 |
lifetime | -0.010 |
+. | -0.008 |
ouse | -0.008 |
THE | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
means | +0.006 |
Bird | +0.006 |
Fle | +0.005 |
Bees | +0.005 |
Cro | +0.005 |
Neg logit contributions | |
pron | -0.015 |
lifetime | -0.013 |
+. | -0.012 |
THE | -0.012 |
ouse | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
pron | +0.074 |
lifetime | +0.064 |
+. | +0.059 |
ouse | +0.057 |
THE | +0.057 |
Neg logit contributions | |
means | -0.058 |
Bird | -0.057 |
Fle | -0.054 |
Cro | -0.052 |
Bee | -0.050 |
Token | sharp |
Token ID | 7786 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
pron | +0.043 |
lifetime | +0.038 |
+. | +0.035 |
THE | +0.034 |
brand | +0.033 |
Neg logit contributions | |
means | -0.029 |
Bird | -0.027 |
Fle | -0.026 |
Cro | -0.025 |
Bees | -0.024 |
Token | sticks |
Token ID | 16461 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
pron | +0.079 |
lifetime | +0.068 |
+. | +0.063 |
ouse | +0.061 |
"! | +0.061 |
Neg logit contributions | |
means | -0.055 |
Bird | -0.054 |
Fle | -0.051 |
Bees | -0.048 |
calls | -0.048 |
Token | scratched |
Token ID | 37468 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
pron | +0.069 |
lifetime | +0.061 |
+. | +0.056 |
THE | +0.055 |
ouse | +0.054 |
Neg logit contributions | |
means | -0.038 |
Bird | -0.037 |
Fle | -0.034 |
Cro | -0.032 |
calls | -0.031 |
Token | his |
Token ID | 465 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
pron | +0.001 |
lifetime | +0.001 |
THE | +0.001 |
+. | +0.001 |
"! | +0.001 |
Neg logit contributions | |
means | -0.001 |
Bird | -0.001 |
Fle | -0.001 |
Bees | -0.001 |
calls | -0.001 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
pron | +0.034 |
lifetime | +0.030 |
+. | +0.028 |
THE | +0.028 |
"! | +0.027 |
Neg logit contributions | |
Bird | -0.024 |
Fle | -0.022 |
means | -0.022 |
Cro | -0.022 |
Bee | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
pron | +0.295 |
lifetime | +0.273 |
+. | +0.242 |
THE | +0.233 |
ileen | +0.231 |
Neg logit contributions | |
means | -0.169 |
Bird | -0.158 |
Fle | -0.144 |
Cro | -0.140 |
Bee | -0.138 |
Token | He |
Token ID | 679 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
means | +0.005 |
Bird | +0.005 |
Fle | +0.004 |
calls | +0.004 |
acts | +0.004 |
Neg logit contributions | |
pron | -0.007 |
lifetime | -0.006 |
"! | -0.006 |
THE | -0.006 |
+. | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
means | +0.010 |
Bird | +0.010 |
Fle | +0.009 |
Bees | +0.009 |
Cro | +0.009 |
Neg logit contributions | |
pron | -0.013 |
lifetime | -0.011 |
THE | -0.010 |
+. | -0.010 |
ouse | -0.010 |
Token | stuck |
Token ID | 7819 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Bird | +0.016 |
means | +0.015 |
Fle | +0.015 |
Cro | +0.013 |
Bee | +0.013 |
Neg logit contributions | |
pron | -0.024 |
lifetime | -0.022 |
ouse | -0.020 |
+. | -0.019 |
"! | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
pron | +0.011 |
lifetime | +0.010 |
ouse | +0.009 |
+. | +0.009 |
ileen | +0.008 |
Neg logit contributions | |
Bird | -0.005 |
means | -0.004 |
Fle | -0.004 |
Bunny | -0.004 |
Cro | -0.004 |
Token | fishes |
Token ID | 49765 |
Feature activation | -2.87e-01 |
Pos logit contributions | |
pron | +0.056 |
lifetime | +0.045 |
THE | +0.040 |
"! | +0.038 |
ouse | +0.038 |
Neg logit contributions | |
means | -0.084 |
Bird | -0.081 |
Fle | -0.079 |
calls | -0.076 |
Cro | -0.076 |
Token | dart |
Token ID | 35970 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
means | +0.012 |
Bird | +0.011 |
Fle | +0.010 |
Cro | +0.009 |
Bee | +0.009 |
Neg logit contributions | |
pron | -0.020 |
lifetime | -0.017 |
+. | -0.016 |
brand | -0.015 |
ouse | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
means | +0.059 |
Bird | +0.057 |
Fle | +0.054 |
Cro | +0.051 |
calls | +0.050 |
Neg logit contributions | |
pron | -0.083 |
lifetime | -0.073 |
+. | -0.066 |
THE | -0.065 |
ouse | -0.064 |
Token | between |
Token ID | 1022 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Bird | +0.004 |
means | +0.004 |
Fle | +0.004 |
Cro | +0.003 |
Bee | +0.003 |
Neg logit contributions | |
pron | -0.010 |
ouse | -0.009 |
lifetime | -0.009 |
+. | -0.008 |
arest | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | +9.32e-01 |
Pos logit contributions | |
pron | +0.091 |
lifetime | +0.079 |
ouse | +0.074 |
+. | +0.073 |
THE | +0.072 |
Neg logit contributions | |
Bird | -0.048 |
means | -0.047 |
Fle | -0.044 |
Cro | -0.041 |
Bee | -0.041 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.38e+00 |
Pos logit contributions | |
pron | +0.056 |
lifetime | +0.047 |
+. | +0.044 |
THE | +0.044 |
ouse | +0.042 |
Neg logit contributions | |
Bird | -0.043 |
means | -0.043 |
Fle | -0.040 |
Cro | -0.038 |
calls | -0.038 |
Token | and |
Token ID | 290 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
pron | +0.323 |
lifetime | +0.296 |
+. | +0.272 |
ileen | +0.265 |
THE | +0.262 |
Neg logit contributions | |
means | -0.145 |
Bird | -0.137 |
Bee | -0.119 |
calls | -0.118 |
Bunny | -0.112 |
Token | laughed |
Token ID | 13818 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
pron | +0.035 |
lifetime | +0.031 |
+. | +0.028 |
THE | +0.028 |
"! | +0.027 |
Neg logit contributions | |
means | -0.023 |
Bird | -0.023 |
Fle | -0.021 |
Cro | -0.020 |
Bees | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
pron | +0.092 |
lifetime | +0.081 |
+. | +0.074 |
arest | +0.074 |
ouse | +0.073 |
Neg logit contributions | |
Bird | -0.045 |
means | -0.044 |
Fle | -0.040 |
Bunny | -0.038 |
Bee | -0.038 |
Token | He |
Token ID | 679 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
means | +0.003 |
Bird | +0.003 |
Fle | +0.003 |
Cro | +0.002 |
Bees | +0.002 |
Neg logit contributions | |
pron | -0.006 |
lifetime | -0.006 |
+. | -0.005 |
THE | -0.005 |
ouse | -0.005 |
Token | could |
Token ID | 714 |
Feature activation | +2.88e-02 |
Pos logit contributions | |
means | +0.001 |
Bird | +0.001 |
Fle | +0.001 |
Cro | +0.001 |
calls | +0.001 |
Neg logit contributions | |
pron | -0.002 |
lifetime | -0.001 |
THE | -0.001 |
+. | -0.001 |
possession | -0.001 |
Token | collected |
Token ID | 7723 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
pron | +0.019 |
lifetime | +0.017 |
THE | +0.016 |
+. | +0.015 |
possession | +0.015 |
Neg logit contributions | |
Bird | -0.010 |
means | -0.010 |
calls | -0.009 |
Fle | -0.009 |
Cro | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
pron | +0.007 |
lifetime | +0.006 |
+. | +0.006 |
ouse | +0.006 |
THE | +0.006 |
Neg logit contributions | |
means | -0.004 |
Bird | -0.004 |
Fle | -0.004 |
Cro | -0.004 |
Bee | -0.004 |
Token | coins |
Token ID | 10796 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
pron | +0.011 |
THE | +0.011 |
lifetime | +0.011 |
oor | +0.011 |
"! | +0.010 |
Neg logit contributions | |
means | -0.011 |
Bird | -0.009 |
acts | -0.009 |
calls | -0.009 |
meant | -0.009 |
Token | into |
Token ID | 656 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
pron | +0.067 |
lifetime | +0.059 |
+. | +0.057 |
THE | +0.052 |
ouse | +0.052 |
Neg logit contributions | |
means | -0.030 |
Bird | -0.028 |
from | -0.027 |
Cro | -0.024 |
Fle | -0.024 |
Token | his |
Token ID | 465 |
Feature activation | +7.87e-01 |
Pos logit contributions | |
pron | +0.034 |
lifetime | +0.030 |
ouse | +0.028 |
THE | +0.028 |
+. | +0.028 |
Neg logit contributions | |
Bird | -0.019 |
means | -0.019 |
Fle | -0.018 |
Cro | -0.016 |
Bee | -0.016 |
Token | pockets |
Token ID | 16511 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
pron | +0.039 |
"! | +0.037 |
THE | +0.037 |
+. | +0.035 |
lifetime | +0.034 |
Neg logit contributions | |
Bird | -0.036 |
Fle | -0.036 |
means | -0.036 |
calls | -0.034 |
Bunny | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +7.27e-02 |
Pos logit contributions | |
pron | +0.332 |
lifetime | +0.301 |
+. | +0.288 |
THE | +0.272 |
arest | +0.261 |
Neg logit contributions | |
from | -0.113 |
means | -0.110 |
Bird | -0.101 |
Cro | -0.092 |
Fle | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
pron | +0.005 |
lifetime | +0.004 |
+. | +0.004 |
THE | +0.004 |
"! | +0.004 |
Neg logit contributions | |
means | -0.003 |
Bird | -0.003 |
Fle | -0.003 |
Cro | -0.002 |
calls | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
pron | +0.036 |
lifetime | +0.032 |
+. | +0.029 |
possession | +0.029 |
ouse | +0.029 |
Neg logit contributions | |
Bird | -0.016 |
means | -0.015 |
Fle | -0.014 |
Cro | -0.013 |
Bee | -0.013 |
Token | He |
Token ID | 1544 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
pron | +0.026 |
lifetime | +0.023 |
possession | +0.023 |
brand | +0.022 |
ouse | +0.021 |
Neg logit contributions | |
Bird | -0.022 |
means | -0.020 |
Cro | -0.020 |
Fle | -0.020 |
Bee | -0.020 |
Token | ran |
Token ID | 4966 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
pron | +0.001 |
lifetime | +0.001 |
+. | +0.001 |
THE | +0.001 |
"! | +0.001 |
Neg logit contributions | |
means | -0.000 |
Bird | -0.000 |
Fle | -0.000 |
Cro | -0.000 |
calls | -0.000 |
Token | paints |
Token ID | 32281 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
means | +0.087 |
Bird | +0.086 |
Fle | +0.082 |
Cro | +0.078 |
calls | +0.078 |
Neg logit contributions | |
pron | -0.089 |
lifetime | -0.077 |
+. | -0.069 |
THE | -0.068 |
"! | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -4.31e-01 |
Pos logit contributions | |
pron | +0.060 |
lifetime | +0.053 |
+. | +0.048 |
THE | +0.048 |
"! | +0.047 |
Neg logit contributions | |
means | -0.038 |
Bird | -0.037 |
Fle | -0.035 |
Cro | -0.033 |
calls | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
means | +0.019 |
Bird | +0.019 |
Fle | +0.018 |
Cro | +0.017 |
Bees | +0.017 |
Neg logit contributions | |
pron | -0.026 |
lifetime | -0.022 |
+. | -0.020 |
THE | -0.020 |
brand | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
means | +0.012 |
Bird | +0.012 |
Fle | +0.011 |
Cro | +0.011 |
Bees | +0.011 |
Neg logit contributions | |
pron | -0.013 |
lifetime | -0.012 |
+. | -0.010 |
THE | -0.010 |
brand | -0.010 |
Token | huge |
Token ID | 3236 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
pron | +0.027 |
THE | +0.026 |
lifetime | +0.025 |
"! | +0.025 |
reed | +0.025 |
Neg logit contributions | |
Bird | -0.025 |
means | -0.023 |
Fle | -0.023 |
calls | -0.023 |
Bee | -0.022 |
Token | pad |
Token ID | 14841 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
pron | +0.020 |
lifetime | +0.019 |
THE | +0.018 |
+. | +0.017 |
"! | +0.017 |
Neg logit contributions | |
Bird | -0.017 |
means | -0.016 |
Fle | -0.016 |
calls | -0.015 |
Cro | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
pron | +0.214 |
lifetime | +0.199 |
+. | +0.176 |
THE | +0.169 |
"! | +0.162 |
Neg logit contributions | |
Bird | -0.229 |
means | -0.227 |
Fle | -0.210 |
Cro | -0.209 |
calls | -0.204 |
Token | paper |
Token ID | 3348 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
means | +0.039 |
Bird | +0.038 |
Fle | +0.036 |
calls | +0.034 |
Cro | +0.034 |
Neg logit contributions | |
pron | -0.051 |
lifetime | -0.047 |
ouse | -0.043 |
THE | -0.043 |
"! | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
means | +0.012 |
Bird | +0.012 |
calls | +0.011 |
Fle | +0.011 |
Bee | +0.010 |
Neg logit contributions | |
pron | -0.017 |
lifetime | -0.015 |
+. | -0.014 |
THE | -0.014 |
possession | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
means | +0.014 |
Bird | +0.014 |
Fle | +0.013 |
Cro | +0.012 |
calls | +0.012 |
Neg logit contributions | |
pron | -0.032 |
lifetime | -0.028 |
+. | -0.027 |
THE | -0.027 |
"! | -0.026 |
Token | couldn |
Token ID | 3521 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
pron | +0.021 |
lifetime | +0.019 |
+. | +0.017 |
THE | +0.017 |
"! | +0.017 |
Neg logit contributions | |
means | -0.014 |
Bird | -0.013 |
Fle | -0.012 |
Cro | -0.011 |
calls | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
Bird | +0.007 |
Fle | +0.007 |
means | +0.007 |
Bunny | +0.006 |
calls | +0.006 |
Neg logit contributions | |
pron | -0.017 |
lifetime | -0.016 |
ouse | -0.015 |
arest | -0.014 |
inations | -0.014 |
Token | sand |
Token ID | 6450 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
pron | +0.007 |
lifetime | +0.006 |
inations | +0.006 |
"! | +0.006 |
vel | +0.006 |
Neg logit contributions | |
Bird | -0.004 |
Fle | -0.004 |
means | -0.004 |
Cro | -0.004 |
calls | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
pron | +0.149 |
lifetime | +0.132 |
+. | +0.125 |
arest | +0.119 |
THE | +0.118 |
Neg logit contributions | |
Bird | -0.092 |
means | -0.090 |
Fle | -0.086 |
Bee | -0.081 |
calls | -0.081 |
Token | digging |
Token ID | 18894 |
Feature activation | -6.85e-01 |
Pos logit contributions | |
Bird | +0.007 |
Fle | +0.007 |
Bunny | +0.007 |
means | +0.007 |
calls | +0.006 |
Neg logit contributions | |
pron | -0.010 |
lifetime | -0.010 |
arest | -0.009 |
"! | -0.009 |
+. | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
means | +0.025 |
Bird | +0.025 |
Fle | +0.023 |
Bee | +0.022 |
calls | +0.021 |
Neg logit contributions | |
pron | -0.046 |
lifetime | -0.042 |
+. | -0.038 |
ouse | -0.037 |
THE | -0.037 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
pron | +0.025 |
"! | +0.022 |
lifetime | +0.021 |
+. | +0.021 |
seven | +0.020 |
Neg logit contributions | |
Fle | -0.020 |
Bird | -0.020 |
Cro | -0.019 |
calls | -0.019 |
Bunny | -0.019 |
Token | in |
Token ID | 287 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
pron | +0.304 |
lifetime | +0.292 |
+. | +0.264 |
ileen | +0.255 |
arest | +0.253 |
Neg logit contributions | |
Bird | -0.126 |
means | -0.125 |
from | -0.115 |
Bunny | -0.108 |
Fle | -0.108 |
Token | to |
Token ID | 284 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
pron | +0.013 |
lifetime | +0.012 |
ouse | +0.011 |
arest | +0.011 |
+. | +0.011 |
Neg logit contributions | |
Bird | -0.005 |
means | -0.005 |
Fle | -0.005 |
Bunny | -0.004 |
Bee | -0.004 |
Token | feel |
Token ID | 1254 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
pron | +0.033 |
lifetime | +0.029 |
ouse | +0.026 |
+. | +0.026 |
THE | +0.026 |
Neg logit contributions | |
Bird | -0.023 |
means | -0.022 |
Fle | -0.022 |
Cro | -0.021 |
Bee | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e-02 |
Pos logit contributions | |
pron | +0.016 |
lifetime | +0.014 |
ouse | +0.013 |
+. | +0.012 |
"! | +0.012 |
Neg logit contributions | |
means | -0.010 |
Bird | -0.010 |
Fle | -0.010 |
Bunny | -0.009 |
Bees | -0.009 |
Token | sand |
Token ID | 6450 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
pron | +0.001 |
lifetime | +0.001 |
+. | +0.001 |
"! | +0.001 |
ouse | +0.001 |
Neg logit contributions | |
Bird | -0.001 |
Fle | -0.000 |
means | -0.000 |
calls | -0.000 |
Bunny | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
pron | +0.040 |
lifetime | +0.038 |
+. | +0.034 |
possession | +0.033 |
THE | +0.033 |
Neg logit contributions | |
means | -0.016 |
Bird | -0.014 |
Fle | -0.013 |
calls | -0.012 |
from | -0.012 |
Token | toys |
Token ID | 14958 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
means | +0.024 |
Bird | +0.024 |
Fle | +0.022 |
Cro | +0.021 |
calls | +0.021 |
Neg logit contributions | |
pron | -0.029 |
lifetime | -0.026 |
+. | -0.023 |
THE | -0.023 |
"! | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
pron | +0.008 |
lifetime | +0.007 |
+. | +0.007 |
THE | +0.007 |
ouse | +0.007 |
Neg logit contributions | |
means | -0.003 |
Bird | -0.003 |
Fle | -0.003 |
calls | -0.003 |
Cro | -0.002 |
Token | even |
Token ID | 772 |
Feature activation | +8.13e-01 |
Pos logit contributions | |
means | +0.027 |
Bird | +0.026 |
Fle | +0.025 |
calls | +0.024 |
Cro | +0.024 |
Neg logit contributions | |
pron | -0.031 |
lifetime | -0.027 |
+. | -0.024 |
THE | -0.024 |
"! | -0.024 |
Token | his |
Token ID | 465 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
pron | +0.044 |
lifetime | +0.038 |
+. | +0.034 |
brand | +0.034 |
THE | +0.032 |
Neg logit contributions | |
Bird | -0.039 |
means | -0.038 |
Fle | -0.037 |
Bees | -0.036 |
Cro | -0.036 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
pron | +0.013 |
lifetime | +0.011 |
THE | +0.011 |
"! | +0.010 |
+. | +0.010 |
Neg logit contributions | |
Bird | -0.010 |
means | -0.010 |
Fle | -0.009 |
calls | -0.009 |
Cro | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
pron | +0.312 |
lifetime | +0.301 |
THE | +0.277 |
+. | +0.262 |
joy | +0.257 |
Neg logit contributions | |
means | -0.144 |
calls | -0.113 |
meant | -0.112 |
Bird | -0.104 |
from | -0.100 |
Token |
|
Token ID | 198 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
pron | +0.009 |
lifetime | +0.008 |
+. | +0.008 |
THE | +0.008 |
"! | +0.008 |
Neg logit contributions | |
means | -0.004 |
Bird | -0.004 |
Fle | -0.004 |
calls | -0.004 |
Bees | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
pron | +0.018 |
lifetime | +0.016 |
+. | +0.014 |
THE | +0.014 |
ouse | +0.014 |
Neg logit contributions | |
means | -0.009 |
Bird | -0.009 |
Fle | -0.008 |
Cro | -0.008 |
Bee | -0.008 |
Token | He |
Token ID | 1544 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
pron | +0.014 |
lifetime | +0.012 |
possession | +0.012 |
joy | +0.012 |
ouse | +0.012 |
Neg logit contributions | |
Bird | -0.012 |
means | -0.012 |
Fle | -0.011 |
Bees | -0.011 |
Cro | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
means | +0.020 |
Bird | +0.019 |
Fle | +0.018 |
Cro | +0.017 |
calls | +0.017 |
Neg logit contributions | |
pron | -0.033 |
lifetime | -0.030 |
+. | -0.027 |
THE | -0.027 |
"! | -0.027 |
Token | up |
Token ID | 510 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
pron | +0.059 |
lifetime | +0.052 |
+. | +0.048 |
THE | +0.047 |
"! | +0.046 |
Neg logit contributions | |
means | -0.037 |
Bird | -0.037 |
Fle | -0.034 |
Cro | -0.032 |
Bee | -0.031 |
Token | high |
Token ID | 1029 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
means | +0.063 |
Bird | +0.060 |
Bees | +0.058 |
Fle | +0.058 |
calls | +0.056 |
Neg logit contributions | |
pron | -0.066 |
lifetime | -0.055 |
+. | -0.051 |
THE | -0.050 |
brand | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
pron | +0.020 |
lifetime | +0.018 |
+. | +0.016 |
THE | +0.016 |
"! | +0.016 |
Neg logit contributions | |
means | -0.013 |
Bird | -0.013 |
Fle | -0.013 |
Cro | -0.012 |
Bees | -0.012 |
Token | touched |
Token ID | 12615 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
pron | +0.018 |
lifetime | +0.016 |
+. | +0.014 |
THE | +0.014 |
ouse | +0.014 |
Neg logit contributions | |
means | -0.015 |
Bird | -0.014 |
Fle | -0.014 |
Cro | -0.013 |
Bees | -0.013 |
Token | their |
Token ID | 511 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
pron | +0.067 |
lifetime | +0.058 |
+. | +0.054 |
THE | +0.054 |
"! | +0.053 |
Neg logit contributions | |
Bird | -0.047 |
means | -0.046 |
Fle | -0.045 |
Cro | -0.043 |
Bees | -0.042 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
pron | +0.021 |
lifetime | +0.019 |
+. | +0.017 |
THE | +0.017 |
"! | +0.016 |
Neg logit contributions | |
means | -0.016 |
Bird | -0.015 |
Fle | -0.014 |
calls | -0.014 |
acts | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
pron | +0.277 |
lifetime | +0.256 |
+. | +0.228 |
THE | +0.223 |
possession | +0.221 |
Neg logit contributions | |
means | -0.172 |
Bird | -0.163 |
Fle | -0.149 |
Bee | -0.145 |
calls | -0.142 |
Token |
|
Token ID | 198 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
means | +0.010 |
Bird | +0.010 |
Fle | +0.009 |
Cro | +0.009 |
calls | +0.009 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.019 |
THE | -0.018 |
+. | -0.018 |
"! | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
pron | +0.003 |
lifetime | +0.003 |
possession | +0.002 |
+. | +0.002 |
ouse | +0.002 |
Neg logit contributions | |
Bird | -0.001 |
means | -0.001 |
Fle | -0.001 |
Bee | -0.001 |
Bunny | -0.001 |
Token | After |
Token ID | 3260 |
Feature activation | +7.74e-01 |
Pos logit contributions | |
pron | +0.001 |
lifetime | +0.001 |
possession | +0.001 |
joy | +0.001 |
brand | +0.001 |
Neg logit contributions | |
Bird | -0.001 |
means | -0.001 |
Fle | -0.001 |
Bees | -0.001 |
Cro | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
pron | +0.052 |
lifetime | +0.046 |
ouse | +0.043 |
+. | +0.042 |
possession | +0.042 |
Neg logit contributions | |
Bird | -0.030 |
means | -0.029 |
Fle | -0.028 |
Bee | -0.026 |
Cro | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +1.95e-01 |
Pos logit contributions | |
means | +0.023 |
Bird | +0.021 |
Fle | +0.021 |
calls | +0.019 |
Bunny | +0.019 |
Neg logit contributions | |
pron | -0.039 |
lifetime | -0.036 |
+. | -0.030 |
ouse | -0.030 |
arest | -0.030 |
Token | play |
Token ID | 711 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
pron | +0.012 |
lifetime | +0.011 |
+. | +0.010 |
THE | +0.010 |
ouse | +0.010 |
Neg logit contributions | |
means | -0.008 |
Bird | -0.008 |
Fle | -0.007 |
Cro | -0.007 |
calls | -0.007 |
Token | without |
Token ID | 1231 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
pron | +0.053 |
lifetime | +0.051 |
ouse | +0.045 |
+. | +0.044 |
possession | +0.044 |
Neg logit contributions | |
means | -0.022 |
Bird | -0.021 |
Fle | -0.020 |
Bunny | -0.017 |
Tweet | -0.017 |
Token | hurting |
Token ID | 21530 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
Bird | +0.019 |
means | +0.019 |
Fle | +0.018 |
calls | +0.017 |
Cro | +0.017 |
Neg logit contributions | |
pron | -0.032 |
lifetime | -0.029 |
THE | -0.026 |
ouse | -0.026 |
+. | -0.026 |
Token | her |
Token ID | 607 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
pron | +0.025 |
lifetime | +0.022 |
+. | +0.020 |
THE | +0.020 |
ouse | +0.020 |
Neg logit contributions | |
means | -0.016 |
Bird | -0.016 |
Fle | -0.015 |
Cro | -0.014 |
calls | -0.013 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
pron | +0.074 |
lifetime | +0.068 |
arest | +0.060 |
THE | +0.060 |
+. | +0.060 |
Neg logit contributions | |
means | -0.050 |
Fle | -0.046 |
Bird | -0.046 |
calls | -0.044 |
acts | -0.043 |
Token | again |
Token ID | 757 |
Feature activation | -7.51e-01 |
Pos logit contributions | |
pron | +0.302 |
lifetime | +0.298 |
joy | +0.259 |
+. | +0.253 |
THE | +0.253 |
Neg logit contributions | |
means | -0.145 |
Bird | -0.113 |
from | -0.109 |
meant | -0.108 |
calls | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
means | +0.028 |
Bird | +0.026 |
Fle | +0.024 |
calls | +0.023 |
Bunny | +0.022 |
Neg logit contributions | |
pron | -0.052 |
lifetime | -0.046 |
THE | -0.042 |
ouse | -0.042 |
+. | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | -5.54e-02 |
Pos logit contributions | |
means | +0.015 |
Bird | +0.014 |
Fle | +0.013 |
Cro | +0.013 |
calls | +0.013 |
Neg logit contributions | |
pron | -0.021 |
lifetime | -0.018 |
THE | -0.017 |
+. | -0.016 |
"! | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
Bird | +0.002 |
means | +0.002 |
Fle | +0.002 |
Bee | +0.002 |
Bunny | +0.002 |
Neg logit contributions | |
pron | -0.004 |
lifetime | -0.004 |
+. | -0.003 |
ouse | -0.003 |
possession | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
Bird | +0.001 |
means | +0.001 |
Bees | +0.001 |
Fle | +0.001 |
Bee | +0.001 |
Neg logit contributions | |
pron | -0.001 |
lifetime | -0.001 |
brand | -0.001 |
possession | -0.001 |
ouse | -0.001 |
Token | out |
Token ID | 503 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
pron | +0.042 |
lifetime | +0.037 |
arest | +0.034 |
inations | +0.033 |
pounds | +0.033 |
Neg logit contributions | |
means | -0.017 |
from | -0.017 |
calls | -0.017 |
Bird | -0.016 |
Bunny | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
pron | +0.040 |
lifetime | +0.035 |
ouse | +0.033 |
THE | +0.032 |
+. | +0.032 |
Neg logit contributions | |
means | -0.020 |
Bird | -0.020 |
calls | -0.018 |
Fle | -0.018 |
Bee | -0.017 |
Token | door |
Token ID | 3420 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
pron | +0.033 |
lifetime | +0.028 |
+. | +0.026 |
"! | +0.026 |
THE | +0.026 |
Neg logit contributions | |
Bird | -0.026 |
means | -0.025 |
calls | -0.024 |
Fle | -0.024 |
Cro | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
pron | +0.011 |
lifetime | +0.010 |
+. | +0.009 |
THE | +0.009 |
ouse | +0.009 |
Neg logit contributions | |
means | -0.006 |
Bird | -0.006 |
calls | -0.005 |
Fle | -0.005 |
Cro | -0.005 |
Token | His |
Token ID | 2399 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
pron | +0.020 |
lifetime | +0.018 |
+. | +0.017 |
THE | +0.016 |
ouse | +0.016 |
Neg logit contributions | |
means | -0.009 |
Bird | -0.009 |
Fle | -0.008 |
Cro | -0.007 |
Bees | -0.007 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
Bird | +0.034 |
means | +0.033 |
Fle | +0.032 |
calls | +0.030 |
Cro | +0.029 |
Neg logit contributions | |
pron | -0.055 |
lifetime | -0.048 |
"! | -0.046 |
THE | -0.046 |
+. | -0.045 |
Token | tapped |
Token ID | 22499 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
pron | +0.309 |
lifetime | +0.282 |
+. | +0.259 |
THE | +0.259 |
"! | +0.250 |
Neg logit contributions | |
means | -0.144 |
Bird | -0.133 |
Fle | -0.122 |
calls | -0.114 |
Cro | -0.113 |
Token | with |
Token ID | 351 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
means | +0.004 |
Bird | +0.004 |
Fle | +0.004 |
Cro | +0.003 |
Bunny | +0.003 |
Neg logit contributions | |
pron | -0.007 |
lifetime | -0.007 |
+. | -0.006 |
ouse | -0.006 |
THE | -0.006 |
Token | excitement |
Token ID | 14067 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
means | +0.005 |
Bird | +0.005 |
Fle | +0.005 |
Cro | +0.005 |
calls | +0.005 |
Neg logit contributions | |
pron | -0.009 |
lifetime | -0.008 |
THE | -0.007 |
ouse | -0.007 |
+. | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +9.36e-02 |
Pos logit contributions | |
pron | +0.107 |
lifetime | +0.096 |
+. | +0.091 |
THE | +0.091 |
ouse | +0.086 |
Neg logit contributions | |
means | -0.045 |
Bird | -0.042 |
calls | -0.037 |
from | -0.037 |
Fle | -0.036 |
Token | |
Token ID | 220 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
pron | +0.007 |
lifetime | +0.006 |
+. | +0.005 |
THE | +0.005 |
ouse | +0.005 |
Neg logit contributions | |
means | -0.003 |
Bird | -0.003 |
Fle | -0.003 |
Cro | -0.003 |
Bees | -0.003 |
Token | tw |
Token ID | 665 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
pron | +0.021 |
lifetime | +0.018 |
+. | +0.016 |
ouse | +0.016 |
THE | +0.016 |
Neg logit contributions | |
Bird | -0.017 |
means | -0.017 |
Fle | -0.017 |
Cro | -0.016 |
Bee | -0.015 |
Token | irling |
Token ID | 24297 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
means | +0.059 |
Bird | +0.057 |
Fle | +0.056 |
Cro | +0.054 |
Bee | +0.053 |
Neg logit contributions | |
pron | -0.049 |
lifetime | -0.043 |
+. | -0.036 |
reminder | -0.035 |
pad | -0.034 |
Token | around |
Token ID | 1088 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
pron | +0.140 |
lifetime | +0.125 |
ouse | +0.113 |
arest | +0.111 |
+. | +0.109 |
Neg logit contributions | |
Bird | -0.059 |
means | -0.059 |
Fle | -0.057 |
Cro | -0.052 |
Tweet | -0.051 |
Token | on |
Token ID | 319 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
pron | +0.090 |
lifetime | +0.078 |
ouse | +0.074 |
+. | +0.071 |
THE | +0.069 |
Neg logit contributions | |
Bird | -0.052 |
means | -0.051 |
Fle | -0.049 |
Cro | -0.046 |
Bee | -0.046 |
Token | his |
Token ID | 465 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
pron | +0.094 |
lifetime | +0.084 |
ouse | +0.077 |
+. | +0.076 |
THE | +0.075 |
Neg logit contributions | |
Bird | -0.044 |
means | -0.044 |
Fle | -0.042 |
Cro | -0.039 |
Bee | -0.038 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
pron | +0.029 |
"! | +0.024 |
+. | +0.024 |
lifetime | +0.023 |
THE | +0.023 |
Neg logit contributions | |
Bird | -0.019 |
Fle | -0.019 |
Cro | -0.018 |
calls | -0.018 |
Bunny | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
pron | +0.333 |
lifetime | +0.314 |
ileen | +0.280 |
+. | +0.280 |
THE | +0.272 |
Neg logit contributions | |
Bird | -0.101 |
means | -0.094 |
Bee | -0.091 |
Fle | -0.089 |
from | -0.084 |
Token | He |
Token ID | 679 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
means | +0.006 |
Bird | +0.006 |
Fle | +0.005 |
Bees | +0.005 |
Cro | +0.005 |
Neg logit contributions | |
pron | -0.013 |
lifetime | -0.012 |
+. | -0.011 |
THE | -0.011 |
ouse | -0.011 |
Token | laughed |
Token ID | 13818 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
means | +0.010 |
Bird | +0.010 |
Fle | +0.009 |
Cro | +0.008 |
calls | +0.008 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.019 |
+. | -0.018 |
THE | -0.018 |
possession | -0.018 |
Token | as |
Token ID | 355 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
pron | +0.058 |
lifetime | +0.054 |
arest | +0.049 |
ouse | +0.049 |
+. | +0.049 |
Neg logit contributions | |
Bird | -0.019 |
means | -0.017 |
Fle | -0.016 |
Bunny | -0.016 |
from | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
pron | +0.055 |
lifetime | +0.048 |
+. | +0.043 |
THE | +0.043 |
ouse | +0.043 |
Neg logit contributions | |
means | -0.039 |
Bird | -0.039 |
Fle | -0.037 |
Cro | -0.035 |
Bee | -0.034 |
Token | their |
Token ID | 511 |
Feature activation | +3.95e-01 |
Pos logit contributions | |
pron | +0.025 |
lifetime | +0.022 |
+. | +0.020 |
THE | +0.020 |
"! | +0.020 |
Neg logit contributions | |
means | -0.016 |
Bird | -0.016 |
Fle | -0.015 |
Cro | -0.014 |
Bees | -0.014 |
Token | mouths |
Token ID | 28552 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
pron | +0.019 |
lifetime | +0.017 |
+. | +0.015 |
"! | +0.015 |
THE | +0.015 |
Neg logit contributions | |
Bird | -0.022 |
means | -0.021 |
Fle | -0.021 |
Cro | -0.020 |
calls | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
pron | +0.128 |
lifetime | +0.113 |
+. | +0.103 |
THE | +0.102 |
"! | +0.100 |
Neg logit contributions | |
means | -0.085 |
Bird | -0.083 |
Fle | -0.079 |
Cro | -0.074 |
Bees | -0.072 |
Token | in |
Token ID | 287 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
means | +0.001 |
Bird | +0.001 |
Fle | +0.001 |
Bees | +0.001 |
Cro | +0.001 |
Neg logit contributions | |
pron | -0.001 |
lifetime | -0.001 |
pad | -0.001 |
THE | -0.001 |
brand | -0.001 |
Token | their |
Token ID | 511 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
pron | +0.049 |
lifetime | +0.044 |
+. | +0.040 |
THE | +0.039 |
ouse | +0.039 |
Neg logit contributions | |
means | -0.031 |
Bird | -0.031 |
Fle | -0.029 |
Cro | -0.027 |
calls | -0.026 |
Token | pockets |
Token ID | 16511 |
Feature activation | +4.23e+00 |
Pos logit contributions | |
pron | +0.030 |
lifetime | +0.026 |
+. | +0.024 |
"! | +0.024 |
THE | +0.023 |
Neg logit contributions | |
Bird | -0.029 |
means | -0.029 |
Fle | -0.028 |
calls | -0.027 |
Cro | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
pron | +0.294 |
lifetime | +0.268 |
+. | +0.247 |
THE | +0.241 |
possession | +0.235 |
Neg logit contributions | |
means | -0.150 |
Bird | -0.145 |
Fle | -0.135 |
Cro | -0.128 |
calls | -0.128 |
Token | They |
Token ID | 1119 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
means | +0.007 |
Bird | +0.006 |
Fle | +0.005 |
acts | +0.005 |
calls | +0.005 |
Neg logit contributions | |
pron | -0.019 |
lifetime | -0.017 |
THE | -0.016 |
+. | -0.016 |
brand | -0.016 |
Token | were |
Token ID | 547 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
means | +0.009 |
Bird | +0.009 |
Fle | +0.009 |
Bees | +0.008 |
Cro | +0.008 |
Neg logit contributions | |
pron | -0.012 |
lifetime | -0.010 |
+. | -0.010 |
THE | -0.009 |
ouse | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
Bird | +0.012 |
means | +0.011 |
Fle | +0.011 |
Cro | +0.011 |
Bee | +0.010 |
Neg logit contributions | |
pron | -0.013 |
lifetime | -0.012 |
+. | -0.011 |
"! | -0.011 |
ouse | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
pron | +0.017 |
lifetime | +0.015 |
+. | +0.014 |
THE | +0.013 |
ouse | +0.013 |
Neg logit contributions | |
means | -0.010 |
Bird | -0.010 |
Fle | -0.009 |
Cro | -0.009 |
calls | -0.009 |
Token | felt |
Token ID | 2936 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
pron | +0.021 |
lifetime | +0.018 |
THE | +0.017 |
+. | +0.016 |
arest | +0.016 |
Neg logit contributions | |
means | -0.013 |
Bird | -0.013 |
Fle | -0.012 |
calls | -0.011 |
Cro | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +6.55e-02 |
Pos logit contributions | |
pron | +0.030 |
lifetime | +0.026 |
ouse | +0.023 |
pad | +0.022 |
+. | +0.022 |
Neg logit contributions | |
means | -0.022 |
Bird | -0.022 |
Fle | -0.021 |
Cro | -0.020 |
calls | -0.019 |
Token | sand |
Token ID | 6450 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
pron | +0.004 |
lifetime | +0.004 |
ouse | +0.003 |
+. | +0.003 |
THE | +0.003 |
Neg logit contributions | |
Bird | -0.003 |
means | -0.003 |
Fle | -0.003 |
calls | -0.002 |
Cro | -0.002 |
Token | between |
Token ID | 1022 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
pron | +0.134 |
lifetime | +0.117 |
+. | +0.107 |
THE | +0.105 |
"! | +0.103 |
Neg logit contributions | |
means | -0.104 |
Bird | -0.103 |
Fle | -0.097 |
Cro | -0.092 |
calls | -0.091 |
Token | her |
Token ID | 607 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
pron | +0.088 |
lifetime | +0.079 |
+. | +0.072 |
THE | +0.072 |
"! | +0.070 |
Neg logit contributions | |
means | -0.055 |
Bird | -0.052 |
Fle | -0.049 |
Bees | -0.046 |
Cro | -0.046 |
Token | toes |
Token ID | 23932 |
Feature activation | +4.22e+00 |
Pos logit contributions | |
pron | +0.035 |
lifetime | +0.029 |
+. | +0.027 |
"! | +0.027 |
THE | +0.027 |
Neg logit contributions | |
Bird | -0.028 |
Fle | -0.027 |
means | -0.026 |
Cro | -0.025 |
calls | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
pron | +0.305 |
lifetime | +0.269 |
+. | +0.250 |
THE | +0.246 |
ileen | +0.239 |
Neg logit contributions | |
means | -0.132 |
Bird | -0.130 |
calls | -0.117 |
Fle | -0.114 |
from | -0.112 |
Token | She |
Token ID | 1375 |
Feature activation | +2.76e-01 |
Pos logit contributions | |
means | +0.003 |
Bird | +0.003 |
Fle | +0.003 |
Cro | +0.002 |
calls | +0.002 |
Neg logit contributions | |
pron | -0.010 |
lifetime | -0.009 |
+. | -0.009 |
THE | -0.008 |
ouse | -0.008 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
pron | +0.019 |
lifetime | +0.017 |
+. | +0.015 |
THE | +0.015 |
possession | +0.015 |
Neg logit contributions | |
means | -0.010 |
Bird | -0.010 |
Fle | -0.009 |
Cro | -0.009 |
calls | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
pron | +0.018 |
lifetime | +0.016 |
+. | +0.014 |
arest | +0.014 |
THE | +0.014 |
Neg logit contributions | |
Bird | -0.008 |
means | -0.008 |
Fle | -0.008 |
Bunny | -0.007 |
Cro | -0.007 |
Token | knew |
Token ID | 2993 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
pron | +0.028 |
lifetime | +0.025 |
+. | +0.023 |
THE | +0.023 |
"! | +0.023 |
Neg logit contributions | |
means | -0.014 |
Bird | -0.014 |
Fle | -0.013 |
Cro | -0.012 |
calls | -0.012 |
Token | shore |
Token ID | 15191 |
Feature activation | +9.64e-01 |
Pos logit contributions | |
means | +0.028 |
calls | +0.027 |
craw | +0.026 |
zo | +0.025 |
Bird | +0.024 |
Neg logit contributions | |
pron | -0.040 |
lifetime | -0.033 |
ouse | -0.031 |
vel | -0.031 |
joy | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -6.55e-02 |
Pos logit contributions | |
pron | +0.067 |
lifetime | +0.059 |
+. | +0.055 |
THE | +0.054 |
ouse | +0.053 |
Neg logit contributions | |
means | -0.036 |
Bird | -0.035 |
Fle | -0.032 |
calls | -0.030 |
Cro | -0.030 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
means | +0.003 |
Bird | +0.003 |
Fle | +0.003 |
Cro | +0.003 |
Bee | +0.003 |
Neg logit contributions | |
pron | -0.004 |
lifetime | -0.003 |
+. | -0.003 |
THE | -0.003 |
"! | -0.003 |
Token | lots |
Token ID | 6041 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
pron | +0.027 |
lifetime | +0.023 |
+. | +0.021 |
THE | +0.021 |
brand | +0.020 |
Neg logit contributions | |
means | -0.026 |
Bird | -0.025 |
Fle | -0.024 |
Cro | -0.023 |
Bees | -0.023 |
Token | of |
Token ID | 286 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
pron | +0.150 |
lifetime | +0.134 |
+. | +0.124 |
THE | +0.124 |
"! | +0.120 |
Neg logit contributions | |
means | -0.091 |
Bird | -0.091 |
Fle | -0.085 |
Cro | -0.079 |
Bees | -0.078 |
Token | se |
Token ID | 384 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
means | +0.124 |
Bird | +0.121 |
Fle | +0.117 |
Cro | +0.112 |
calls | +0.111 |
Neg logit contributions | |
pron | -0.139 |
lifetime | -0.119 |
ouse | -0.105 |
THE | -0.105 |
+. | -0.105 |
Token | ag |
Token ID | 363 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
means | +0.287 |
Bird | +0.284 |
Fle | +0.271 |
Cro | +0.258 |
Bees | +0.255 |
Neg logit contributions | |
pron | -0.291 |
lifetime | -0.250 |
+. | -0.222 |
THE | -0.220 |
ouse | -0.216 |
Token | ull |
Token ID | 724 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
means | +0.022 |
Bird | +0.022 |
Fle | +0.020 |
Cro | +0.019 |
calls | +0.019 |
Neg logit contributions | |
pron | -0.029 |
lifetime | -0.026 |
THE | -0.024 |
+. | -0.024 |
"! | -0.023 |
Token | s |
Token ID | 82 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
means | +0.106 |
Bird | +0.099 |
Fle | +0.097 |
Bees | +0.091 |
Cro | +0.090 |
Neg logit contributions | |
pron | -0.120 |
lifetime | -0.109 |
THE | -0.097 |
ouse | -0.096 |
+. | -0.095 |
Token | flying |
Token ID | 7348 |
Feature activation | -8.07e-01 |
Pos logit contributions | |
Bird | +0.070 |
means | +0.067 |
Fle | +0.063 |
Cro | +0.060 |
calls | +0.059 |
Neg logit contributions | |
pron | -0.123 |
lifetime | -0.106 |
+. | -0.098 |
THE | -0.095 |
possession | -0.095 |
Token | in |
Token ID | 287 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
means | +0.033 |
Bird | +0.033 |
Fle | +0.031 |
Cro | +0.029 |
Bee | +0.028 |
Neg logit contributions | |
pron | -0.053 |
lifetime | -0.046 |
+. | -0.042 |
ouse | -0.042 |
THE | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
means | +0.020 |
Bird | +0.020 |
Fle | +0.018 |
Bunny | +0.018 |
calls | +0.017 |
Neg logit contributions | |
pron | -0.045 |
lifetime | -0.039 |
arest | -0.037 |
+. | -0.035 |
ouse | -0.035 |
Token | learned |
Token ID | 4499 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
pron | +0.001 |
lifetime | +0.001 |
+. | +0.001 |
THE | +0.001 |
"! | +0.001 |
Neg logit contributions | |
means | -0.001 |
Bird | -0.001 |
Fle | -0.001 |
calls | -0.001 |
Cro | -0.001 |
Token | something |
Token ID | 1223 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
pron | +0.040 |
lifetime | +0.036 |
pad | +0.032 |
ouse | +0.032 |
arest | +0.031 |
Neg logit contributions | |
means | -0.024 |
Bird | -0.022 |
Fle | -0.020 |
calls | -0.019 |
from | -0.019 |
Token | new |
Token ID | 649 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
means | +0.033 |
Bird | +0.031 |
Fle | +0.030 |
calls | +0.028 |
Cro | +0.028 |
Neg logit contributions | |
pron | -0.035 |
lifetime | -0.030 |
THE | -0.026 |
ouse | -0.026 |
pad | -0.026 |
Token | about |
Token ID | 546 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
means | +0.100 |
Bird | +0.076 |
from | +0.072 |
Fle | +0.072 |
calls | +0.069 |
Neg logit contributions | |
pron | -0.206 |
lifetime | -0.176 |
aults | -0.164 |
arest | -0.160 |
Adam | -0.155 |
Token | se |
Token ID | 384 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
pron | +0.022 |
lifetime | +0.020 |
+. | +0.018 |
ouse | +0.018 |
THE | +0.017 |
Neg logit contributions | |
means | -0.015 |
Bird | -0.015 |
Fle | -0.014 |
Cro | -0.013 |
Bee | -0.013 |
Token | ag |
Token ID | 363 |
Feature activation | -6.65e-01 |
Pos logit contributions | |
means | +0.256 |
Bird | +0.246 |
Fle | +0.237 |
Cro | +0.221 |
calls | +0.220 |
Neg logit contributions | |
pron | -0.307 |
lifetime | -0.269 |
+. | -0.243 |
THE | -0.240 |
"! | -0.236 |
Token | ull |
Token ID | 724 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
means | +0.025 |
Bird | +0.024 |
Fle | +0.021 |
Bee | +0.021 |
Cro | +0.020 |
Neg logit contributions | |
pron | -0.045 |
lifetime | -0.043 |
brand | -0.037 |
+. | -0.037 |
arest | -0.036 |
Token | s |
Token ID | 82 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
means | +0.099 |
Bird | +0.097 |
Fle | +0.091 |
Cro | +0.085 |
Bees | +0.084 |
Neg logit contributions | |
pron | -0.154 |
lifetime | -0.135 |
+. | -0.124 |
THE | -0.123 |
"! | -0.120 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
means | +0.060 |
Bird | +0.058 |
Fle | +0.048 |
from | +0.047 |
acts | +0.046 |
Neg logit contributions | |
pron | -0.136 |
lifetime | -0.118 |
+. | -0.117 |
arest | -0.113 |
ileen | -0.111 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.70e-01 |
Pos logit contributions | |
means | +0.006 |
Bird | +0.006 |
Fle | +0.005 |
Cro | +0.005 |
Bees | +0.005 |
Neg logit contributions | |
pron | -0.011 |
lifetime | -0.010 |
+. | -0.009 |
ouse | -0.009 |
THE | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
pron | +0.005 |
lifetime | +0.004 |
THE | +0.004 |
+. | +0.004 |
"! | +0.004 |
Neg logit contributions | |
means | -0.002 |
Bird | -0.002 |
Fle | -0.001 |
Cro | -0.001 |
acts | -0.001 |
Token | told |
Token ID | 1297 |
Feature activation | +4.56e-01 |
Pos logit contributions | |
pron | +0.016 |
lifetime | +0.014 |
THE | +0.013 |
+. | +0.013 |
"! | +0.012 |
Neg logit contributions | |
means | -0.011 |
Bird | -0.011 |
Fle | -0.010 |
calls | -0.010 |
Cro | -0.009 |
Token | him |
Token ID | 683 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
pron | +0.023 |
brand | +0.018 |
+. | +0.018 |
mine | +0.018 |
THE | +0.017 |
Neg logit contributions | |
means | -0.022 |
Bird | -0.020 |
Bees | -0.020 |
Cro | -0.019 |
Fle | -0.019 |
Token | how |
Token ID | 703 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
means | +0.025 |
Bird | +0.025 |
Fle | +0.023 |
calls | +0.022 |
Bee | +0.022 |
Neg logit contributions | |
pron | -0.033 |
lifetime | -0.030 |
+. | -0.026 |
THE | -0.026 |
"! | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | -9.56e-02 |
Pos logit contributions | |
pron | +0.076 |
lifetime | +0.070 |
pad | +0.064 |
THE | +0.063 |
"! | +0.063 |
Neg logit contributions | |
means | -0.048 |
Bird | -0.046 |
Fle | -0.044 |
Cro | -0.042 |
Bees | -0.042 |
Token | se |
Token ID | 384 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
Bird | +0.005 |
Fle | +0.005 |
Cro | +0.005 |
Bees | +0.005 |
Bee | +0.005 |
Neg logit contributions | |
pron | -0.005 |
lifetime | -0.004 |
ouse | -0.004 |
+. | -0.004 |
brand | -0.003 |
Token | wed |
Token ID | 19103 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
Bird | +0.298 |
means | +0.290 |
Fle | +0.282 |
Cro | +0.273 |
Bees | +0.269 |
Neg logit contributions | |
pron | -0.266 |
lifetime | -0.219 |
+. | -0.196 |
ouse | -0.195 |
THE | -0.194 |
Token | , |
Token ID | 11 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
pron | +0.023 |
lifetime | +0.020 |
+. | +0.018 |
THE | +0.018 |
ouse | +0.018 |
Neg logit contributions | |
means | -0.019 |
Bird | -0.019 |
Fle | -0.018 |
Bees | -0.017 |
Cro | -0.017 |
Token | glued |
Token ID | 39783 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
means | +0.001 |
Bird | +0.001 |
Fle | +0.000 |
Cro | +0.000 |
Bees | +0.000 |
Neg logit contributions | |
pron | -0.001 |
lifetime | -0.001 |
+. | -0.001 |
THE | -0.001 |
ouse | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
means | +0.033 |
Bird | +0.032 |
Fle | +0.030 |
Cro | +0.028 |
calls | +0.027 |
Neg logit contributions | |
pron | -0.051 |
lifetime | -0.046 |
+. | -0.041 |
THE | -0.040 |
ouse | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
Bird | +0.009 |
means | +0.009 |
Fle | +0.009 |
Cro | +0.008 |
Bees | +0.008 |
Neg logit contributions | |
pron | -0.013 |
lifetime | -0.011 |
THE | -0.010 |
+. | -0.010 |
brand | -0.010 |
Token | got |
Token ID | 1392 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
pron | +0.010 |
lifetime | +0.008 |
ouse | +0.008 |
+. | +0.008 |
THE | +0.008 |
Neg logit contributions | |
Bird | -0.007 |
means | -0.007 |
Fle | -0.007 |
Cro | -0.007 |
Bees | -0.007 |
Token | some |
Token ID | 617 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Bird | +0.007 |
means | +0.007 |
Fle | +0.006 |
Bees | +0.006 |
Cro | +0.006 |
Neg logit contributions | |
pron | -0.008 |
lifetime | -0.007 |
+. | -0.006 |
THE | -0.006 |
brand | -0.006 |
Token | colorful |
Token ID | 20239 |
Feature activation | -7.43e-01 |
Pos logit contributions | |
means | +0.047 |
Bird | +0.046 |
Fle | +0.044 |
Cro | +0.041 |
Bees | +0.040 |
Neg logit contributions | |
pron | -0.065 |
lifetime | -0.057 |
+. | -0.051 |
THE | -0.051 |
ouse | -0.050 |
Token | fabric |
Token ID | 9664 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
means | +0.036 |
Bird | +0.035 |
Fle | +0.034 |
Cro | +0.032 |
Bees | +0.031 |
Neg logit contributions | |
pron | -0.042 |
lifetime | -0.036 |
+. | -0.033 |
THE | -0.033 |
ouse | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
means | +0.007 |
Bird | +0.006 |
Fle | +0.006 |
Cro | +0.006 |
calls | +0.005 |
Neg logit contributions | |
pron | -0.012 |
lifetime | -0.011 |
+. | -0.010 |
THE | -0.010 |
"! | -0.010 |
Token | se |
Token ID | 384 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
means | +0.032 |
Bird | +0.031 |
Fle | +0.030 |
Cro | +0.028 |
Bees | +0.028 |
Neg logit contributions | |
pron | -0.046 |
lifetime | -0.040 |
+. | -0.037 |
THE | -0.036 |
ouse | -0.036 |
Token | wed |
Token ID | 19103 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
means | +0.295 |
Bird | +0.290 |
Fle | +0.279 |
Cro | +0.265 |
calls | +0.263 |
Neg logit contributions | |
pron | -0.261 |
lifetime | -0.222 |
+. | -0.196 |
THE | -0.194 |
"! | -0.188 |
Token | a |
Token ID | 257 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
pron | +0.035 |
lifetime | +0.030 |
+. | +0.027 |
THE | +0.027 |
"! | +0.026 |
Neg logit contributions | |
means | -0.035 |
Bird | -0.034 |
Fle | -0.033 |
Cro | -0.031 |
Bees | -0.031 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
lifetime | +0.005 |
joy | +0.005 |
Adam | +0.005 |
oor | +0.004 |
pron | +0.004 |
Neg logit contributions | |
Bird | -0.003 |
means | -0.003 |
Fle | -0.003 |
Bunny | -0.003 |
Panda | -0.003 |
Token | dress |
Token ID | 6576 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
lifetime | +0.016 |
Adam | +0.016 |
pron | +0.015 |
oor | +0.015 |
reed | +0.015 |
Neg logit contributions | |
means | -0.011 |
Bird | -0.011 |
Fle | -0.010 |
spr | -0.010 |
Bunny | -0.010 |
Token | for |
Token ID | 329 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
means | +0.015 |
Bird | +0.014 |
Fle | +0.013 |
calls | +0.012 |
Cro | +0.012 |
Neg logit contributions | |
pron | -0.023 |
lifetime | -0.022 |
+. | -0.019 |
THE | -0.019 |
possession | -0.018 |
Token | watched |
Token ID | 7342 |
Feature activation | +1.67e+00 |
Pos logit contributions | |
Bird | +0.027 |
means | +0.027 |
Fle | +0.026 |
Cro | +0.025 |
Bees | +0.025 |
Neg logit contributions | |
pron | -0.037 |
lifetime | -0.031 |
ouse | -0.029 |
+. | -0.028 |
THE | -0.028 |
Token | as |
Token ID | 355 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
pron | +0.079 |
till | +0.061 |
brand | +0.057 |
hours | +0.056 |
satisfied | +0.054 |
Neg logit contributions | |
means | -0.094 |
acts | -0.087 |
Bees | -0.087 |
Fle | -0.083 |
Cro | -0.083 |
Token | her |
Token ID | 607 |
Feature activation | -7.73e-01 |
Pos logit contributions | |
pron | +0.066 |
lifetime | +0.053 |
+. | +0.053 |
THE | +0.053 |
possession | +0.051 |
Neg logit contributions | |
means | -0.049 |
Bird | -0.045 |
Fle | -0.044 |
calls | -0.042 |
Bees | -0.041 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
means | +0.040 |
Bird | +0.038 |
Fle | +0.036 |
Bees | +0.035 |
Cro | +0.035 |
Neg logit contributions | |
pron | -0.043 |
lifetime | -0.036 |
+. | -0.033 |
ouse | -0.033 |
brand | -0.032 |
Token | carefully |
Token ID | 7773 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
Fle | +0.069 |
means | +0.069 |
Bees | +0.067 |
Cro | +0.066 |
Bird | +0.065 |
Neg logit contributions | |
pron | -0.059 |
lifetime | -0.047 |
pad | -0.043 |
brand | -0.043 |
ouse | -0.042 |
Token | se |
Token ID | 384 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
Bird | +0.050 |
means | +0.049 |
Bees | +0.048 |
Fle | +0.048 |
Bee | +0.047 |
Neg logit contributions | |
pron | -0.053 |
lifetime | -0.042 |
+. | -0.039 |
brand | -0.039 |
ouse | -0.038 |
Token | wed |
Token ID | 19103 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
Bird | +0.292 |
means | +0.289 |
Fle | +0.278 |
Cro | +0.267 |
Bees | +0.265 |
Neg logit contributions | |
pron | -0.259 |
lifetime | -0.215 |
+. | -0.192 |
THE | -0.190 |
ouse | -0.188 |
Token | Ted |
Token ID | 11396 |
Feature activation | -7.81e-01 |
Pos logit contributions | |
pron | +0.025 |
till | +0.019 |
brand | +0.019 |
THE | +0.018 |
possession | +0.018 |
Neg logit contributions | |
Bees | -0.027 |
Bird | -0.026 |
means | -0.026 |
Ask | -0.025 |
calls | -0.025 |
Token | 's |
Token ID | 338 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
means | +0.032 |
Bird | +0.032 |
Fle | +0.031 |
Cro | +0.029 |
Bees | +0.028 |
Neg logit contributions | |
pron | -0.049 |
lifetime | -0.043 |
+. | -0.039 |
THE | -0.039 |
ouse | -0.038 |
Token | arm |
Token ID | 3211 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
means | +0.046 |
Bird | +0.046 |
Fle | +0.043 |
Cro | +0.040 |
calls | +0.040 |
Neg logit contributions | |
pron | -0.062 |
lifetime | -0.055 |
+. | -0.050 |
THE | -0.050 |
"! | -0.049 |
Token | back |
Token ID | 736 |
Feature activation | +9.35e-02 |
Pos logit contributions | |
pron | +0.023 |
lifetime | +0.019 |
+. | +0.017 |
brand | +0.017 |
ouse | +0.017 |
Neg logit contributions | |
Bird | -0.022 |
means | -0.022 |
Fle | -0.021 |
Cro | -0.020 |
Bees | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
means | +0.061 |
Bird | +0.060 |
Fle | +0.056 |
Cro | +0.052 |
Bee | +0.051 |
Neg logit contributions | |
pron | -0.096 |
lifetime | -0.085 |
+. | -0.078 |
THE | -0.076 |
"! | -0.075 |
Token | white |
Token ID | 2330 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
means | +0.021 |
Bird | +0.020 |
Fle | +0.020 |
Cro | +0.019 |
Bees | +0.019 |
Neg logit contributions | |
pron | -0.026 |
lifetime | -0.023 |
+. | -0.020 |
brand | -0.020 |
ouse | -0.020 |
Token | cloth |
Token ID | 16270 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
means | +0.068 |
Bird | +0.066 |
Fle | +0.064 |
Cro | +0.060 |
Bees | +0.060 |
Neg logit contributions | |
pron | -0.085 |
lifetime | -0.074 |
+. | -0.067 |
THE | -0.067 |
"! | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
means | +0.032 |
Bird | +0.032 |
Fle | +0.030 |
Cro | +0.028 |
Bees | +0.028 |
Neg logit contributions | |
pron | -0.042 |
lifetime | -0.037 |
+. | -0.033 |
THE | -0.033 |
ouse | -0.033 |
Token | carefully |
Token ID | 7773 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
means | +0.018 |
Bird | +0.017 |
Fle | +0.017 |
Cro | +0.016 |
Bees | +0.016 |
Neg logit contributions | |
pron | -0.024 |
lifetime | -0.021 |
+. | -0.018 |
brand | -0.018 |
THE | -0.018 |
Token | se |
Token ID | 384 |
Feature activation | -5.21e+00 |
Pos logit contributions | |
means | +0.026 |
Bird | +0.026 |
Fle | +0.024 |
Cro | +0.023 |
Bees | +0.022 |
Neg logit contributions | |
pron | -0.035 |
lifetime | -0.030 |
+. | -0.027 |
THE | -0.027 |
"! | -0.027 |
Token | wed |
Token ID | 19103 |
Feature activation | +9.36e-01 |
Pos logit contributions | |
means | +0.264 |
Bird | +0.250 |
Fle | +0.241 |
calls | +0.226 |
Cro | +0.226 |
Neg logit contributions | |
pron | -0.286 |
lifetime | -0.250 |
+. | -0.223 |
THE | -0.221 |
"! | -0.214 |
Token | them |
Token ID | 606 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
pron | +0.052 |
lifetime | +0.045 |
THE | +0.042 |
+. | +0.041 |
brand | +0.041 |
Neg logit contributions | |
means | -0.044 |
Bird | -0.042 |
Fle | -0.041 |
Bees | -0.040 |
calls | -0.039 |
Token | together |
Token ID | 1978 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
means | +0.017 |
Bird | +0.017 |
Fle | +0.016 |
Cro | +0.015 |
calls | +0.015 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.020 |
+. | -0.018 |
THE | -0.018 |
"! | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
means | +0.007 |
Bird | +0.007 |
Fle | +0.006 |
Bee | +0.006 |
Cro | +0.006 |
Neg logit contributions | |
pron | -0.013 |
lifetime | -0.012 |
+. | -0.011 |
ouse | -0.011 |
THE | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
means | +0.024 |
Bird | +0.023 |
Fle | +0.023 |
Cro | +0.021 |
calls | +0.021 |
Neg logit contributions | |
pron | -0.045 |
lifetime | -0.041 |
THE | -0.037 |
+. | -0.037 |
ouse | -0.036 |
Token | She |
Token ID | 1375 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
means | +0.008 |
Bird | +0.007 |
acts | +0.007 |
Fle | +0.006 |
calls | +0.006 |
Neg logit contributions | |
pron | -0.011 |
lifetime | -0.010 |
THE | -0.010 |
"! | -0.010 |
+. | -0.009 |
Token | cut |
Token ID | 2005 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
pron | +0.024 |
lifetime | +0.021 |
+. | +0.019 |
THE | +0.019 |
ouse | +0.018 |
Neg logit contributions | |
means | -0.020 |
Bird | -0.020 |
Fle | -0.019 |
Cro | -0.018 |
Bees | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
Bird | +0.028 |
means | +0.028 |
Fle | +0.027 |
Bees | +0.026 |
Cro | +0.026 |
Neg logit contributions | |
pron | -0.036 |
lifetime | -0.028 |
ouse | -0.027 |
brand | -0.027 |
+. | -0.027 |
Token | glued |
Token ID | 39783 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
pron | +0.013 |
lifetime | +0.011 |
+. | +0.010 |
THE | +0.010 |
ouse | +0.009 |
Neg logit contributions | |
Bird | -0.011 |
means | -0.011 |
Fle | -0.010 |
Cro | -0.010 |
Bees | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
means | +0.052 |
Bird | +0.051 |
Fle | +0.048 |
Cro | +0.045 |
calls | +0.044 |
Neg logit contributions | |
pron | -0.082 |
lifetime | -0.072 |
+. | -0.066 |
THE | -0.065 |
"! | -0.064 |
Token | se |
Token ID | 384 |
Feature activation | -5.19e+00 |
Pos logit contributions | |
Bird | +0.023 |
means | +0.022 |
Fle | +0.022 |
Bees | +0.020 |
Cro | +0.020 |
Neg logit contributions | |
pron | -0.025 |
lifetime | -0.021 |
+. | -0.019 |
THE | -0.019 |
brand | -0.018 |
Token | wed |
Token ID | 19103 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
means | +0.280 |
Bird | +0.277 |
Fle | +0.266 |
Cro | +0.253 |
Bees | +0.250 |
Neg logit contributions | |
pron | -0.262 |
lifetime | -0.223 |
+. | -0.198 |
THE | -0.196 |
ouse | -0.191 |
Token | different |
Token ID | 1180 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
pron | +0.034 |
lifetime | +0.029 |
THE | +0.026 |
+. | +0.026 |
brand | +0.025 |
Neg logit contributions | |
means | -0.033 |
Bird | -0.033 |
Fle | -0.031 |
Bees | -0.030 |
Cro | -0.030 |
Token | fabrics |
Token ID | 39533 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
pron | +0.027 |
lifetime | +0.023 |
THE | +0.021 |
+. | +0.021 |
"! | +0.020 |
Neg logit contributions | |
means | -0.024 |
Bird | -0.023 |
Fle | -0.022 |
calls | -0.021 |
acts | -0.021 |
Token | together |
Token ID | 1978 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
pron | +0.020 |
lifetime | +0.018 |
+. | +0.017 |
THE | +0.016 |
"! | +0.016 |
Neg logit contributions | |
means | -0.014 |
Bird | -0.013 |
Fle | -0.012 |
calls | -0.012 |
Cro | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
means | +0.032 |
Bird | +0.031 |
Fle | +0.029 |
Bee | +0.027 |
calls | +0.027 |
Neg logit contributions | |
pron | -0.050 |
lifetime | -0.045 |
+. | -0.041 |
THE | -0.041 |
ouse | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
Bees | +0.038 |
Bird | +0.037 |
means | +0.037 |
acts | +0.034 |
Fle | +0.034 |
Neg logit contributions | |
pron | -0.035 |
mine | -0.028 |
+. | -0.028 |
till | -0.027 |
brand | -0.027 |
Token | needle |
Token ID | 17598 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
means | +0.039 |
Bird | +0.037 |
Fle | +0.036 |
calls | +0.035 |
Cro | +0.033 |
Neg logit contributions | |
pron | -0.039 |
lifetime | -0.036 |
THE | -0.032 |
"! | -0.031 |
+. | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | -6.32e-01 |
Pos logit contributions | |
means | +0.069 |
Bird | +0.068 |
Fle | +0.068 |
Bees | +0.066 |
Cro | +0.063 |
Neg logit contributions | |
pron | -0.075 |
lifetime | -0.060 |
THE | -0.060 |
ouse | -0.058 |
pad | -0.058 |
Token | thread |
Token ID | 4704 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
means | +0.030 |
Fle | +0.029 |
Bird | +0.029 |
Bees | +0.027 |
Cro | +0.026 |
Neg logit contributions | |
pron | -0.036 |
lifetime | -0.028 |
+. | -0.027 |
brand | -0.026 |
THE | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
means | +0.031 |
Bird | +0.031 |
Fle | +0.031 |
Bees | +0.030 |
Cro | +0.028 |
Neg logit contributions | |
pron | -0.036 |
lifetime | -0.029 |
THE | -0.029 |
+. | -0.028 |
ouse | -0.027 |
Token | se |
Token ID | 384 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
means | +0.028 |
Fle | +0.027 |
Bird | +0.027 |
Bees | +0.025 |
Cro | +0.025 |
Neg logit contributions | |
pron | -0.034 |
lifetime | -0.028 |
+. | -0.026 |
brand | -0.025 |
THE | -0.025 |
Token | wed |
Token ID | 19103 |
Feature activation | +7.85e-01 |
Pos logit contributions | |
means | +0.268 |
Bird | +0.262 |
Fle | +0.251 |
Cro | +0.238 |
calls | +0.236 |
Neg logit contributions | |
pron | -0.273 |
lifetime | -0.236 |
+. | -0.210 |
THE | -0.208 |
"! | -0.202 |
Token | the |
Token ID | 262 |
Feature activation | -1.65e-01 |
Pos logit contributions | |
pron | +0.041 |
lifetime | +0.035 |
+. | +0.032 |
THE | +0.032 |
"! | +0.031 |
Neg logit contributions | |
means | -0.040 |
Bird | -0.040 |
Fle | -0.038 |
Bees | -0.036 |
Cro | -0.036 |
Token | hole |
Token ID | 7604 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
means | +0.007 |
Bird | +0.007 |
Fle | +0.006 |
calls | +0.006 |
Cro | +0.006 |
Neg logit contributions | |
pron | -0.010 |
lifetime | -0.010 |
THE | -0.009 |
"! | -0.008 |
+. | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
pron | +0.064 |
lifetime | +0.055 |
+. | +0.050 |
THE | +0.050 |
ouse | +0.049 |
Neg logit contributions | |
means | -0.055 |
Bird | -0.054 |
Fle | -0.052 |
Cro | -0.049 |
Bees | -0.049 |
Token | She |
Token ID | 1375 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
pron | +0.022 |
lifetime | +0.020 |
+. | +0.019 |
THE | +0.019 |
"! | +0.018 |
Neg logit contributions | |
means | -0.007 |
Bird | -0.007 |
Fle | -0.006 |
Cro | -0.005 |
Bees | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
Bees | +0.044 |
Bird | +0.041 |
fly | +0.041 |
Cro | +0.041 |
means | +0.040 |
Neg logit contributions | |
pron | -0.028 |
brand | -0.025 |
hours | -0.024 |
till | -0.023 |
THE | -0.022 |
Token | needle |
Token ID | 17598 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
Bird | +0.026 |
means | +0.025 |
Fle | +0.024 |
Bee | +0.023 |
calls | +0.023 |
Neg logit contributions | |
pron | -0.029 |
lifetime | -0.026 |
THE | -0.024 |
"! | -0.023 |
+. | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
means | +0.073 |
Bird | +0.071 |
Fle | +0.067 |
Cro | +0.063 |
Bees | +0.062 |
Neg logit contributions | |
pron | -0.110 |
lifetime | -0.097 |
+. | -0.088 |
THE | -0.087 |
"! | -0.085 |
Token | thread |
Token ID | 4704 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
means | +0.031 |
Fle | +0.030 |
Bird | +0.029 |
Cro | +0.028 |
Bees | +0.028 |
Neg logit contributions | |
pron | -0.039 |
lifetime | -0.032 |
brand | -0.030 |
+. | -0.030 |
ouse | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
means | +0.032 |
Bird | +0.032 |
Fle | +0.030 |
Cro | +0.028 |
calls | +0.028 |
Neg logit contributions | |
pron | -0.040 |
lifetime | -0.035 |
+. | -0.031 |
THE | -0.031 |
"! | -0.030 |
Token | se |
Token ID | 384 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
means | +0.026 |
Bird | +0.025 |
Fle | +0.025 |
Cro | +0.024 |
Bees | +0.023 |
Neg logit contributions | |
pron | -0.035 |
lifetime | -0.030 |
+. | -0.027 |
brand | -0.027 |
THE | -0.027 |
Token | wed |
Token ID | 19103 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
means | +0.279 |
Bird | +0.278 |
Fle | +0.266 |
Cro | +0.255 |
Bees | +0.253 |
Neg logit contributions | |
pron | -0.254 |
lifetime | -0.214 |
+. | -0.190 |
THE | -0.188 |
ouse | -0.185 |
Token | Teddy |
Token ID | 29345 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
pron | +0.047 |
lifetime | +0.038 |
THE | +0.037 |
+. | +0.036 |
brand | +0.035 |
Neg logit contributions | |
means | -0.052 |
Bird | -0.051 |
Bees | -0.050 |
Fle | -0.049 |
calls | -0.048 |
Token | 's |
Token ID | 338 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
means | +0.023 |
Bird | +0.022 |
Fle | +0.021 |
calls | +0.019 |
Bee | +0.019 |
Neg logit contributions | |
pron | -0.041 |
lifetime | -0.038 |
+. | -0.035 |
THE | -0.034 |
"! | -0.033 |
Token | eye |
Token ID | 4151 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
means | +0.047 |
Bird | +0.047 |
Fle | +0.044 |
Cro | +0.041 |
calls | +0.041 |
Neg logit contributions | |
pron | -0.070 |
lifetime | -0.062 |
+. | -0.056 |
THE | -0.056 |
"! | -0.055 |
Token | back |
Token ID | 736 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
pron | +0.058 |
lifetime | +0.053 |
THE | +0.048 |
+. | +0.047 |
"! | +0.046 |
Neg logit contributions | |
means | -0.043 |
Bird | -0.042 |
Fle | -0.039 |
calls | -0.037 |
Cro | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
means | +0.018 |
Bird | +0.018 |
Fle | +0.017 |
calls | +0.015 |
Cro | +0.015 |
Neg logit contributions | |
pron | -0.039 |
lifetime | -0.035 |
ouse | -0.032 |
+. | -0.031 |
possession | -0.031 |
Token | waves |
Token ID | 9813 |
Feature activation | -8.25e-01 |
Pos logit contributions | |
means | +0.103 |
Bird | +0.101 |
Fle | +0.096 |
Cro | +0.091 |
Bees | +0.091 |
Neg logit contributions | |
pron | -0.106 |
lifetime | -0.092 |
+. | -0.082 |
THE | -0.081 |
"! | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | -8.14e-01 |
Pos logit contributions | |
means | +0.029 |
Bird | +0.027 |
Fle | +0.026 |
Cro | +0.024 |
calls | +0.024 |
Neg logit contributions | |
pron | -0.059 |
lifetime | -0.053 |
+. | -0.049 |
THE | -0.048 |
possession | -0.047 |
Token | wind |
Token ID | 2344 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
means | +0.037 |
Bird | +0.037 |
Fle | +0.035 |
calls | +0.033 |
Cro | +0.033 |
Neg logit contributions | |
pron | -0.048 |
lifetime | -0.042 |
+. | -0.038 |
THE | -0.038 |
ouse | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | -6.24e-01 |
Pos logit contributions | |
means | +0.036 |
Bird | +0.035 |
Fle | +0.032 |
Cro | +0.031 |
calls | +0.030 |
Neg logit contributions | |
pron | -0.056 |
lifetime | -0.050 |
+. | -0.046 |
THE | -0.045 |
possession | -0.044 |
Token | se |
Token ID | 384 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
means | +0.027 |
Bird | +0.027 |
Fle | +0.025 |
calls | +0.024 |
Cro | +0.024 |
Neg logit contributions | |
pron | -0.038 |
lifetime | -0.034 |
+. | -0.031 |
THE | -0.031 |
"! | -0.030 |
Token | ag |
Token ID | 363 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
means | +0.271 |
Bird | +0.264 |
Fle | +0.254 |
Cro | +0.240 |
calls | +0.239 |
Neg logit contributions | |
pron | -0.265 |
lifetime | -0.228 |
+. | -0.202 |
THE | -0.200 |
"! | -0.194 |
Token | ull |
Token ID | 724 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
means | +0.016 |
Bird | +0.016 |
Fle | +0.014 |
Bee | +0.014 |
Cro | +0.013 |
Neg logit contributions | |
pron | -0.029 |
lifetime | -0.026 |
+. | -0.024 |
brand | -0.023 |
THE | -0.023 |
Token | s |
Token ID | 82 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
means | +0.075 |
Bird | +0.075 |
Fle | +0.068 |
Cro | +0.064 |
calls | +0.063 |
Neg logit contributions | |
pron | -0.141 |
lifetime | -0.123 |
+. | -0.115 |
THE | -0.113 |
"! | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -7.12e-01 |
Pos logit contributions | |
Bird | +0.059 |
means | +0.058 |
Fle | +0.054 |
calls | +0.051 |
Cro | +0.049 |
Neg logit contributions | |
pron | -0.116 |
lifetime | -0.100 |
THE | -0.093 |
+. | -0.093 |
possession | -0.092 |
Token |
|
Token ID | 198 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
means | +0.027 |
Bird | +0.027 |
Fle | +0.025 |
Cro | +0.024 |
calls | +0.023 |
Neg logit contributions | |
pron | -0.047 |
lifetime | -0.041 |
+. | -0.038 |
THE | -0.038 |
"! | -0.037 |
Token | needle |
Token ID | 17598 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
Bird | +0.052 |
means | +0.052 |
Fle | +0.050 |
Cro | +0.049 |
Bees | +0.047 |
Neg logit contributions | |
pron | -0.063 |
lifetime | -0.053 |
+. | -0.049 |
brand | -0.049 |
THE | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
means | +0.100 |
Bird | +0.097 |
Fle | +0.094 |
Bees | +0.088 |
Cro | +0.088 |
Neg logit contributions | |
pron | -0.134 |
lifetime | -0.117 |
+. | -0.106 |
THE | -0.106 |
ouse | -0.104 |
Token | thread |
Token ID | 4704 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
means | +0.013 |
Bird | +0.013 |
Fle | +0.013 |
Cro | +0.012 |
Bees | +0.012 |
Neg logit contributions | |
pron | -0.018 |
lifetime | -0.016 |
brand | -0.014 |
+. | -0.014 |
THE | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
means | +0.029 |
Bird | +0.029 |
Fle | +0.027 |
Cro | +0.026 |
calls | +0.025 |
Neg logit contributions | |
pron | -0.038 |
lifetime | -0.033 |
+. | -0.030 |
THE | -0.030 |
"! | -0.029 |
Token | carefully |
Token ID | 7773 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
means | +0.012 |
Bird | +0.011 |
Fle | +0.011 |
Cro | +0.010 |
Bees | +0.010 |
Neg logit contributions | |
pron | -0.017 |
lifetime | -0.015 |
+. | -0.013 |
THE | -0.013 |
brand | -0.013 |
Token | se |
Token ID | 384 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
means | +0.014 |
Bird | +0.014 |
Fle | +0.013 |
Cro | +0.013 |
Bees | +0.013 |
Neg logit contributions | |
pron | -0.020 |
lifetime | -0.017 |
+. | -0.016 |
THE | -0.015 |
ouse | -0.015 |
Token | wed |
Token ID | 19103 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
means | +0.258 |
Bird | +0.247 |
Fle | +0.238 |
Cro | +0.224 |
calls | +0.223 |
Neg logit contributions | |
pron | -0.277 |
lifetime | -0.242 |
+. | -0.215 |
THE | -0.213 |
"! | -0.207 |
Token | the |
Token ID | 262 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
pron | +0.060 |
lifetime | +0.052 |
+. | +0.048 |
THE | +0.047 |
brand | +0.046 |
Neg logit contributions | |
means | -0.051 |
Bird | -0.051 |
Fle | -0.048 |
Bees | -0.047 |
calls | -0.046 |
Token | hole |
Token ID | 7604 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
pron | +0.002 |
lifetime | +0.002 |
"! | +0.002 |
THE | +0.002 |
Adam | +0.002 |
Neg logit contributions | |
means | -0.002 |
Bird | -0.002 |
Fle | -0.002 |
calls | -0.002 |
Bunny | -0.002 |
Token | shut |
Token ID | 4423 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
pron | +0.092 |
lifetime | +0.082 |
+. | +0.075 |
THE | +0.073 |
"! | +0.071 |
Neg logit contributions | |
means | -0.061 |
Bird | -0.059 |
Fle | -0.055 |
Cro | -0.052 |
Bee | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
pron | +0.034 |
lifetime | +0.030 |
+. | +0.027 |
ouse | +0.027 |
arest | +0.027 |
Neg logit contributions | |
means | -0.019 |
Bird | -0.018 |
Fle | -0.017 |
Cro | -0.016 |
Bunny | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
pron | +0.021 |
lifetime | +0.019 |
+. | +0.017 |
THE | +0.017 |
"! | +0.017 |
Neg logit contributions | |
means | -0.013 |
Bird | -0.012 |
Fle | -0.011 |
Bee | -0.011 |
Cro | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -6.76e-02 |
Pos logit contributions | |
means | +0.082 |
Bird | +0.081 |
Fle | +0.077 |
Cro | +0.072 |
Bees | +0.071 |
Neg logit contributions | |
pron | -0.123 |
lifetime | -0.107 |
+. | -0.099 |
THE | -0.097 |
brand | -0.095 |
Token | box |
Token ID | 3091 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
means | +0.003 |
Bird | +0.003 |
Fle | +0.003 |
calls | +0.003 |
acts | +0.003 |
Neg logit contributions | |
pron | -0.004 |
lifetime | -0.003 |
"! | -0.003 |
THE | -0.003 |
+. | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +4.28e-02 |
Pos logit contributions | |
means | +0.063 |
Bird | +0.062 |
Fle | +0.058 |
Cro | +0.055 |
calls | +0.054 |
Neg logit contributions | |
pron | -0.089 |
lifetime | -0.078 |
+. | -0.072 |
THE | -0.071 |
"! | -0.069 |
Token | then |
Token ID | 788 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
pron | +0.003 |
lifetime | +0.002 |
+. | +0.002 |
THE | +0.002 |
"! | +0.002 |
Neg logit contributions | |
means | -0.002 |
Bird | -0.002 |
Fle | -0.002 |
Cro | -0.002 |
calls | -0.002 |
Token | se |
Token ID | 384 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
means | +0.015 |
Bird | +0.015 |
Fle | +0.014 |
Cro | +0.013 |
calls | +0.013 |
Neg logit contributions | |
pron | -0.026 |
lifetime | -0.023 |
THE | -0.021 |
+. | -0.021 |
"! | -0.021 |
Token | wed |
Token ID | 19103 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
means | +0.266 |
Bird | +0.261 |
Fle | +0.251 |
Cro | +0.238 |
Bees | +0.235 |
Neg logit contributions | |
pron | -0.266 |
lifetime | -0.228 |
+. | -0.203 |
THE | -0.201 |
"! | -0.196 |
Token | them |
Token ID | 606 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
pron | +0.051 |
lifetime | +0.044 |
THE | +0.041 |
+. | +0.041 |
"! | +0.040 |
Neg logit contributions | |
means | -0.040 |
Bird | -0.040 |
Fle | -0.038 |
Bees | -0.037 |
calls | -0.036 |
Token | back |
Token ID | 736 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
means | +0.014 |
Bird | +0.014 |
Fle | +0.013 |
Cro | +0.012 |
calls | +0.012 |
Neg logit contributions | |
pron | -0.019 |
lifetime | -0.017 |
+. | -0.016 |
THE | -0.015 |
"! | -0.015 |
Token | together |
Token ID | 1978 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
means | +0.011 |
Bird | +0.011 |
Fle | +0.010 |
Cro | +0.010 |
calls | +0.010 |
Neg logit contributions | |
pron | -0.015 |
lifetime | -0.013 |
+. | -0.012 |
THE | -0.011 |
"! | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
means | +0.008 |
Bird | +0.008 |
Fle | +0.007 |
from | +0.007 |
Bee | +0.007 |
Neg logit contributions | |
pron | -0.017 |
lifetime | -0.016 |
+. | -0.015 |
arest | -0.014 |
ouse | -0.014 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.72e-01 |
Pos logit contributions | |
means | +0.018 |
Bird | +0.017 |
Fle | +0.016 |
Cro | +0.015 |
Bees | +0.015 |
Neg logit contributions | |
pron | -0.023 |
lifetime | -0.020 |
+. | -0.018 |
THE | -0.018 |
ouse | -0.018 |
Token | found |
Token ID | 1043 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
Fle | +0.043 |
means | +0.043 |
Bees | +0.042 |
Bird | +0.041 |
Cro | +0.040 |
Neg logit contributions | |
pron | -0.048 |
lifetime | -0.038 |
ouse | -0.036 |
brand | -0.035 |
+. | -0.034 |
Token | some |
Token ID | 617 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
Bees | +0.016 |
Fle | +0.016 |
calls | +0.015 |
means | +0.015 |
Cro | +0.015 |
Neg logit contributions | |
pron | -0.015 |
possession | -0.013 |
brand | -0.013 |
+. | -0.012 |
lifetime | -0.012 |
Token | fabric |
Token ID | 9664 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
means | +0.022 |
Bird | +0.022 |
Fle | +0.021 |
Cro | +0.020 |
Bees | +0.020 |
Neg logit contributions | |
pron | -0.027 |
lifetime | -0.024 |
+. | -0.021 |
brand | -0.021 |
THE | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -3.91e-01 |
Pos logit contributions | |
pron | +0.018 |
lifetime | +0.017 |
+. | +0.015 |
THE | +0.015 |
"! | +0.015 |
Neg logit contributions | |
means | -0.012 |
Bird | -0.011 |
Fle | -0.010 |
Cro | -0.010 |
calls | -0.010 |
Token | se |
Token ID | 384 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
means | +0.018 |
Bird | +0.017 |
Fle | +0.017 |
Cro | +0.016 |
Bees | +0.016 |
Neg logit contributions | |
pron | -0.023 |
lifetime | -0.020 |
brand | -0.018 |
+. | -0.018 |
THE | -0.017 |
Token | wed |
Token ID | 19103 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
means | +0.273 |
Bird | +0.271 |
Fle | +0.260 |
Cro | +0.248 |
Bees | +0.245 |
Neg logit contributions | |
pron | -0.256 |
lifetime | -0.218 |
+. | -0.193 |
THE | -0.191 |
ouse | -0.187 |
Token | the |
Token ID | 262 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
pron | +0.045 |
lifetime | +0.038 |
+. | +0.035 |
THE | +0.035 |
brand | +0.034 |
Neg logit contributions | |
Bird | -0.043 |
means | -0.043 |
Fle | -0.042 |
Bees | -0.041 |
calls | -0.040 |
Token | costume |
Token ID | 16569 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
means | +0.001 |
Bird | +0.001 |
Fle | +0.001 |
calls | +0.001 |
acts | +0.001 |
Neg logit contributions | |
pron | -0.001 |
lifetime | -0.001 |
+. | -0.001 |
THE | -0.001 |
"! | -0.001 |
Token | back |
Token ID | 736 |
Feature activation | +5.64e-02 |
Pos logit contributions | |
pron | +0.014 |
lifetime | +0.013 |
+. | +0.011 |
THE | +0.011 |
"! | +0.011 |
Neg logit contributions | |
means | -0.010 |
Bird | -0.010 |
Fle | -0.009 |
calls | -0.009 |
Cro | -0.009 |
Token | together |
Token ID | 1978 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
pron | +0.003 |
lifetime | +0.003 |
+. | +0.003 |
THE | +0.003 |
"! | +0.003 |
Neg logit contributions | |
means | -0.003 |
Bird | -0.003 |
Fle | -0.002 |
Cro | -0.002 |
calls | -0.002 |
Token | needle |
Token ID | 17598 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Bird | +0.010 |
means | +0.010 |
Fle | +0.009 |
Bunny | +0.009 |
calls | +0.009 |
Neg logit contributions | |
lifetime | -0.013 |
pron | -0.013 |
THE | -0.012 |
"! | -0.012 |
oor | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
means | +0.056 |
Bird | +0.055 |
Fle | +0.051 |
Cro | +0.048 |
Bee | +0.046 |
Neg logit contributions | |
pron | -0.096 |
lifetime | -0.087 |
+. | -0.078 |
THE | -0.077 |
"! | -0.076 |
Token | thread |
Token ID | 4704 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
means | +0.025 |
Bird | +0.025 |
Fle | +0.025 |
Cro | +0.023 |
Bees | +0.023 |
Neg logit contributions | |
pron | -0.035 |
lifetime | -0.029 |
+. | -0.027 |
brand | -0.027 |
THE | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
means | +0.025 |
Bird | +0.024 |
Fle | +0.023 |
Cro | +0.022 |
calls | +0.021 |
Neg logit contributions | |
pron | -0.036 |
lifetime | -0.032 |
+. | -0.029 |
THE | -0.029 |
"! | -0.028 |
Token | carefully |
Token ID | 7773 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
means | +0.028 |
Bird | +0.028 |
Fle | +0.027 |
Cro | +0.025 |
Bees | +0.025 |
Neg logit contributions | |
pron | -0.039 |
lifetime | -0.033 |
+. | -0.030 |
THE | -0.030 |
brand | -0.030 |
Token | se |
Token ID | 384 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
means | +0.018 |
Bird | +0.018 |
Fle | +0.017 |
Cro | +0.016 |
calls | +0.016 |
Neg logit contributions | |
pron | -0.025 |
lifetime | -0.022 |
+. | -0.020 |
THE | -0.020 |
"! | -0.019 |
Token | wed |
Token ID | 19103 |
Feature activation | +9.68e-01 |
Pos logit contributions | |
means | +0.269 |
Bird | +0.264 |
Fle | +0.254 |
Cro | +0.241 |
calls | +0.238 |
Neg logit contributions | |
pron | -0.259 |
lifetime | -0.222 |
+. | -0.197 |
THE | -0.195 |
"! | -0.190 |
Token | Mr |
Token ID | 1770 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
pron | +0.053 |
lifetime | +0.046 |
+. | +0.041 |
THE | +0.041 |
"! | +0.040 |
Neg logit contributions | |
means | -0.047 |
Bird | -0.046 |
Fle | -0.044 |
Bees | -0.043 |
calls | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
pron | +0.018 |
lifetime | +0.015 |
ouse | +0.014 |
possession | +0.014 |
pad | +0.013 |
Neg logit contributions | |
means | -0.023 |
Fle | -0.023 |
Bird | -0.022 |
Bees | -0.022 |
calls | -0.021 |
Token | Fl |
Token ID | 1610 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
pron | +0.101 |
lifetime | +0.093 |
+. | +0.087 |
THE | +0.086 |
ouse | +0.085 |
Neg logit contributions | |
Bird | -0.036 |
Fle | -0.032 |
means | -0.032 |
Cro | -0.029 |
Bee | -0.028 |
Token | uffy |
Token ID | 15352 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
pron | +0.027 |
lifetime | +0.024 |
+. | +0.022 |
ouse | +0.022 |
THE | +0.022 |
Neg logit contributions | |
means | -0.017 |
Bird | -0.017 |
Fle | -0.016 |
Cro | -0.015 |
calls | -0.015 |
Token | gently |
Token ID | 15165 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Fle | +0.011 |
Bird | +0.011 |
means | +0.011 |
Bees | +0.011 |
Cro | +0.011 |
Neg logit contributions | |
pron | -0.015 |
lifetime | -0.012 |
ouse | -0.012 |
+. | -0.012 |
brand | -0.012 |
Token | took |
Token ID | 1718 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
Bird | +0.061 |
means | +0.060 |
Bees | +0.060 |
Fle | +0.060 |
Cro | +0.057 |
Neg logit contributions | |
pron | -0.064 |
+. | -0.048 |
brand | -0.047 |
lifetime | -0.047 |
ouse | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
Bees | +0.050 |
means | +0.048 |
Bird | +0.047 |
Cro | +0.046 |
acts | +0.045 |
Neg logit contributions | |
pron | -0.036 |
brand | -0.028 |
+. | -0.028 |
hours | -0.028 |
possession | -0.027 |
Token | shirt |
Token ID | 10147 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
means | +0.039 |
Bird | +0.035 |
calls | +0.032 |
meant | +0.031 |
says | +0.031 |
Neg logit contributions | |
lifetime | -0.050 |
pron | -0.043 |
THE | -0.042 |
ouse | -0.041 |
"! | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
means | +0.008 |
Bird | +0.008 |
Fle | +0.007 |
Cro | +0.007 |
calls | +0.007 |
Neg logit contributions | |
pron | -0.014 |
lifetime | -0.012 |
+. | -0.011 |
THE | -0.011 |
"! | -0.011 |
Token | se |
Token ID | 384 |
Feature activation | -5.03e+00 |
Pos logit contributions | |
means | +0.021 |
Bird | +0.021 |
Fle | +0.021 |
Bees | +0.020 |
Cro | +0.019 |
Neg logit contributions | |
pron | -0.027 |
lifetime | -0.022 |
+. | -0.021 |
brand | -0.021 |
ouse | -0.020 |
Token | wed |
Token ID | 19103 |
Feature activation | +7.37e-01 |
Pos logit contributions | |
means | +0.266 |
Bird | +0.263 |
Fle | +0.252 |
Cro | +0.240 |
Bees | +0.237 |
Neg logit contributions | |
pron | -0.260 |
lifetime | -0.222 |
+. | -0.198 |
THE | -0.196 |
ouse | -0.191 |
Token | it |
Token ID | 340 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
pron | +0.037 |
lifetime | +0.032 |
+. | +0.028 |
THE | +0.028 |
ouse | +0.027 |
Neg logit contributions | |
means | -0.040 |
Bird | -0.040 |
Fle | -0.038 |
Cro | -0.036 |
calls | -0.035 |
Token | back |
Token ID | 736 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
means | +0.018 |
Bird | +0.017 |
Fle | +0.016 |
Cro | +0.016 |
Bees | +0.015 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.019 |
+. | -0.017 |
THE | -0.017 |
ouse | -0.017 |
Token | together |
Token ID | 1978 |
Feature activation | -3.42e-01 |
Pos logit contributions | |
means | +0.022 |
Bird | +0.022 |
Fle | +0.020 |
Cro | +0.019 |
Bee | +0.019 |
Neg logit contributions | |
pron | -0.031 |
lifetime | -0.027 |
+. | -0.025 |
THE | -0.024 |
ouse | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
means | +0.011 |
Bird | +0.011 |
Fle | +0.009 |
from | +0.009 |
Bee | +0.009 |
Neg logit contributions | |
pron | -0.025 |
lifetime | -0.023 |
+. | -0.021 |
arest | -0.020 |
ouse | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
pron | +0.038 |
lifetime | +0.033 |
THE | +0.030 |
+. | +0.030 |
brand | +0.029 |
Neg logit contributions | |
means | -0.029 |
Bird | -0.029 |
Fle | -0.028 |
Bees | -0.026 |
Cro | -0.026 |
Token | sand |
Token ID | 6450 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
means | +0.029 |
Bird | +0.028 |
Fle | +0.027 |
Cro | +0.026 |
Bees | +0.026 |
Neg logit contributions | |
pron | -0.024 |
lifetime | -0.020 |
+. | -0.018 |
THE | -0.018 |
brand | -0.017 |
Token | cast |
Token ID | 2701 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
pron | +0.083 |
lifetime | +0.073 |
THE | +0.066 |
ouse | +0.065 |
+. | +0.065 |
Neg logit contributions | |
means | -0.066 |
Bird | -0.065 |
Fle | -0.062 |
Bees | -0.059 |
Cro | -0.057 |
Token | les |
Token ID | 829 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
pron | +0.054 |
lifetime | +0.052 |
reminder | +0.046 |
brand | +0.045 |
ouse | +0.044 |
Neg logit contributions | |
means | -0.028 |
Bird | -0.023 |
Fle | -0.021 |
calls | -0.021 |
acts | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
means | +0.013 |
Bird | +0.013 |
Fle | +0.012 |
calls | +0.011 |
Cro | +0.011 |
Neg logit contributions | |
pron | -0.023 |
lifetime | -0.020 |
+. | -0.019 |
THE | -0.018 |
ouse | -0.018 |
Token | se |
Token ID | 384 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
means | +0.007 |
Bird | +0.007 |
Fle | +0.006 |
Cro | +0.006 |
Bees | +0.006 |
Neg logit contributions | |
pron | -0.007 |
lifetime | -0.006 |
+. | -0.006 |
THE | -0.006 |
"! | -0.006 |
Token | ag |
Token ID | 363 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
means | +0.258 |
Bird | +0.248 |
Fle | +0.239 |
calls | +0.225 |
Cro | +0.224 |
Neg logit contributions | |
pron | -0.267 |
lifetime | -0.231 |
+. | -0.206 |
THE | -0.202 |
"! | -0.197 |
Token | ull |
Token ID | 724 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
means | +0.005 |
Bird | +0.005 |
Fle | +0.005 |
Bee | +0.004 |
Cro | +0.004 |
Neg logit contributions | |
pron | -0.008 |
lifetime | -0.007 |
+. | -0.006 |
brand | -0.006 |
THE | -0.006 |
Token | s |
Token ID | 82 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
Bird | +0.068 |
means | +0.067 |
Fle | +0.063 |
Cro | +0.059 |
Bee | +0.058 |
Neg logit contributions | |
pron | -0.124 |
lifetime | -0.108 |
+. | -0.101 |
THE | -0.099 |
"! | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
Bird | +0.054 |
means | +0.050 |
Fle | +0.047 |
Cro | +0.046 |
calls | +0.046 |
Neg logit contributions | |
pron | -0.107 |
lifetime | -0.091 |
+. | -0.087 |
THE | -0.085 |
"! | -0.083 |
Token | Jane |
Token ID | 12091 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
means | +0.021 |
Bird | +0.021 |
Fle | +0.020 |
Cro | +0.018 |
calls | +0.018 |
Neg logit contributions | |
pron | -0.038 |
lifetime | -0.034 |
+. | -0.031 |
THE | -0.031 |
"! | -0.030 |
Token | fix |
Token ID | 4259 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
means | +0.028 |
Bird | +0.027 |
Fle | +0.026 |
Bees | +0.026 |
Cro | +0.025 |
Neg logit contributions | |
pron | -0.037 |
lifetime | -0.030 |
+. | -0.029 |
brand | -0.028 |
ouse | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -8.06e-02 |
Pos logit contributions | |
Bird | +0.039 |
means | +0.036 |
Bees | +0.036 |
Fle | +0.036 |
Cro | +0.035 |
Neg logit contributions | |
pron | -0.045 |
lifetime | -0.036 |
+. | -0.036 |
possession | -0.036 |
brand | -0.035 |
Token | dress |
Token ID | 6576 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
means | +0.004 |
Bird | +0.004 |
Fle | +0.003 |
calls | +0.003 |
Cro | +0.003 |
Neg logit contributions | |
pron | -0.005 |
lifetime | -0.004 |
"! | -0.004 |
+. | -0.004 |
THE | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +6.24e-02 |
Pos logit contributions | |
means | +0.017 |
Bird | +0.017 |
Fle | +0.017 |
Cro | +0.016 |
Bees | +0.016 |
Neg logit contributions | |
pron | -0.021 |
lifetime | -0.018 |
+. | -0.017 |
THE | -0.016 |
ouse | -0.016 |
Token | They |
Token ID | 1119 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
pron | +0.004 |
lifetime | +0.004 |
+. | +0.004 |
brand | +0.004 |
THE | +0.004 |
Neg logit contributions | |
Bird | -0.002 |
means | -0.002 |
Fle | -0.002 |
Cro | -0.002 |
acts | -0.001 |
Token | se |
Token ID | 384 |
Feature activation | -4.97e+00 |
Pos logit contributions | |
Bird | +0.022 |
means | +0.022 |
Fle | +0.021 |
Bees | +0.020 |
Cro | +0.020 |
Neg logit contributions | |
pron | -0.027 |
lifetime | -0.023 |
+. | -0.021 |
THE | -0.021 |
ouse | -0.021 |
Token | wed |
Token ID | 19103 |
Feature activation | +4.22e-01 |
Pos logit contributions | |
means | +0.265 |
Bird | +0.263 |
Fle | +0.252 |
Cro | +0.239 |
Bees | +0.237 |
Neg logit contributions | |
pron | -0.255 |
lifetime | -0.217 |
+. | -0.193 |
THE | -0.192 |
ouse | -0.187 |
Token | the |
Token ID | 262 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
pron | +0.023 |
lifetime | +0.020 |
THE | +0.018 |
+. | +0.018 |
brand | +0.018 |
Neg logit contributions | |
Bird | -0.020 |
means | -0.020 |
Fle | -0.019 |
Bees | -0.019 |
calls | -0.018 |
Token | rip |
Token ID | 18344 |
Feature activation | -2.94e-01 |
Pos logit contributions | |
means | +0.025 |
Bird | +0.024 |
Fle | +0.023 |
calls | +0.023 |
acts | +0.021 |
Neg logit contributions | |
pron | -0.029 |
lifetime | -0.028 |
"! | -0.025 |
+. | -0.024 |
THE | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +9.31e-02 |
Pos logit contributions | |
Bird | +0.013 |
means | +0.013 |
Fle | +0.013 |
Bees | +0.012 |
Cro | +0.012 |
Neg logit contributions | |
pron | -0.017 |
lifetime | -0.014 |
+. | -0.014 |
THE | -0.013 |
ouse | -0.013 |
Token | made |
Token ID | 925 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
pron | +0.006 |
lifetime | +0.005 |
+. | +0.004 |
THE | +0.004 |
ouse | +0.004 |
Neg logit contributions | |
means | -0.004 |
Bird | -0.004 |
Fle | -0.004 |
Cro | -0.004 |
Bees | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
means | +0.014 |
Bird | +0.013 |
Fle | +0.013 |
Bees | +0.012 |
Cro | +0.012 |
Neg logit contributions | |
pron | -0.018 |
lifetime | -0.015 |
+. | -0.015 |
THE | -0.014 |
brand | -0.014 |
Token | needle |
Token ID | 17598 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
means | +0.007 |
Bird | +0.007 |
Fle | +0.006 |
calls | +0.006 |
Bee | +0.006 |
Neg logit contributions | |
pron | -0.008 |
lifetime | -0.007 |
THE | -0.007 |
"! | -0.007 |
+. | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
means | +0.067 |
Bird | +0.065 |
Fle | +0.063 |
Cro | +0.059 |
Bees | +0.058 |
Neg logit contributions | |
pron | -0.098 |
lifetime | -0.085 |
+. | -0.078 |
THE | -0.078 |
ouse | -0.076 |
Token | thread |
Token ID | 4704 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
Fle | +0.016 |
means | +0.015 |
Bird | +0.015 |
Bees | +0.015 |
Cro | +0.015 |
Neg logit contributions | |
pron | -0.018 |
lifetime | -0.015 |
brand | -0.014 |
+. | -0.014 |
ouse | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
means | +0.022 |
Bird | +0.022 |
Fle | +0.021 |
Bees | +0.020 |
Cro | +0.020 |
Neg logit contributions | |
pron | -0.028 |
lifetime | -0.024 |
+. | -0.022 |
THE | -0.022 |
ouse | -0.021 |
Token | se |
Token ID | 384 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
means | +0.015 |
Fle | +0.015 |
Bird | +0.015 |
Bees | +0.014 |
Cro | +0.014 |
Neg logit contributions | |
pron | -0.019 |
lifetime | -0.016 |
brand | -0.014 |
+. | -0.014 |
ouse | -0.014 |
Token | wed |
Token ID | 19103 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
means | +0.259 |
Bird | +0.253 |
Fle | +0.243 |
Cro | +0.230 |
calls | +0.228 |
Neg logit contributions | |
pron | -0.260 |
lifetime | -0.225 |
+. | -0.199 |
THE | -0.197 |
"! | -0.192 |
Token | the |
Token ID | 262 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
pron | +0.051 |
lifetime | +0.042 |
THE | +0.039 |
+. | +0.038 |
"! | +0.037 |
Neg logit contributions | |
means | -0.059 |
Bird | -0.059 |
Fle | -0.057 |
Bees | -0.055 |
calls | -0.055 |
Token | t |
Token ID | 256 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
means | +0.005 |
Bird | +0.005 |
Fle | +0.005 |
calls | +0.004 |
Cro | +0.004 |
Neg logit contributions | |
pron | -0.008 |
lifetime | -0.007 |
THE | -0.006 |
+. | -0.006 |
"! | -0.006 |
Token | eddy |
Token ID | 21874 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
pron | +0.011 |
lifetime | +0.009 |
+. | +0.008 |
THE | +0.008 |
ouse | +0.008 |
Neg logit contributions | |
means | -0.009 |
Bird | -0.009 |
Fle | -0.009 |
Cro | -0.008 |
calls | -0.008 |
Token | bear |
Token ID | 6842 |
Feature activation | -8.88e-01 |
Pos logit contributions | |
means | +0.006 |
Bird | +0.006 |
Fle | +0.005 |
Cro | +0.005 |
Bees | +0.005 |
Neg logit contributions | |
pron | -0.016 |
lifetime | -0.014 |
+. | -0.013 |
THE | -0.013 |
ouse | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
pron | +0.005 |
brand | +0.005 |
+. | +0.004 |
possession | +0.004 |
mine | +0.004 |
Neg logit contributions | |
Bees | -0.010 |
Bird | -0.009 |
acts | -0.009 |
means | -0.009 |
fly | -0.009 |
Token | needle |
Token ID | 17598 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
pron | +0.003 |
lifetime | +0.003 |
THE | +0.002 |
"! | +0.002 |
+. | +0.002 |
Neg logit contributions | |
means | -0.003 |
Bird | -0.003 |
Fle | -0.003 |
Cro | -0.002 |
calls | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -6.37e-01 |
Pos logit contributions | |
means | +0.060 |
Bird | +0.059 |
Fle | +0.058 |
Bees | +0.055 |
Cro | +0.054 |
Neg logit contributions | |
pron | -0.078 |
lifetime | -0.066 |
+. | -0.061 |
THE | -0.060 |
ouse | -0.060 |
Token | thread |
Token ID | 4704 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Fle | +0.029 |
Bird | +0.029 |
means | +0.029 |
Cro | +0.028 |
Bees | +0.027 |
Neg logit contributions | |
pron | -0.036 |
lifetime | -0.029 |
brand | -0.028 |
+. | -0.028 |
possession | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
means | +0.022 |
Bird | +0.022 |
Fle | +0.021 |
Bees | +0.020 |
Cro | +0.020 |
Neg logit contributions | |
pron | -0.028 |
lifetime | -0.024 |
+. | -0.022 |
THE | -0.022 |
ouse | -0.021 |
Token | se |
Token ID | 384 |
Feature activation | -4.92e+00 |
Pos logit contributions | |
Bird | +0.022 |
means | +0.022 |
Fle | +0.022 |
Cro | +0.021 |
Bees | +0.020 |
Neg logit contributions | |
pron | -0.028 |
lifetime | -0.024 |
+. | -0.022 |
brand | -0.022 |
THE | -0.021 |
Token | wed |
Token ID | 19103 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
means | +0.268 |
Bird | +0.267 |
Fle | +0.256 |
Cro | +0.244 |
Bees | +0.242 |
Neg logit contributions | |
pron | -0.245 |
lifetime | -0.207 |
+. | -0.184 |
THE | -0.182 |
ouse | -0.178 |
Token | a |
Token ID | 257 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
pron | +0.054 |
lifetime | +0.045 |
THE | +0.042 |
+. | +0.042 |
"! | +0.040 |
Neg logit contributions | |
means | -0.053 |
Bird | -0.052 |
Fle | -0.050 |
Bees | -0.049 |
calls | -0.048 |
Token | patch |
Token ID | 8529 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
pron | +0.015 |
lifetime | +0.014 |
"! | +0.013 |
Adam | +0.013 |
THE | +0.013 |
Neg logit contributions | |
Bird | -0.011 |
means | -0.010 |
Fle | -0.010 |
Bee | -0.009 |
Cro | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
pron | +0.069 |
lifetime | +0.063 |
+. | +0.057 |
THE | +0.056 |
ouse | +0.055 |
Neg logit contributions | |
means | -0.041 |
Bird | -0.040 |
Fle | -0.038 |
Cro | -0.035 |
calls | -0.035 |
Token | Patch |
Token ID | 17106 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
pron | +0.091 |
lifetime | +0.080 |
+. | +0.072 |
THE | +0.071 |
ouse | +0.070 |
Neg logit contributions | |
means | -0.068 |
Bird | -0.067 |
Fle | -0.063 |
Cro | -0.059 |
Bees | -0.058 |
Token | make |
Token ID | 787 |
Feature activation | -8.62e-01 |
Pos logit contributions | |
means | +0.013 |
Bird | +0.012 |
Fle | +0.012 |
calls | +0.011 |
Cro | +0.011 |
Neg logit contributions | |
pron | -0.024 |
lifetime | -0.021 |
+. | -0.019 |
THE | -0.019 |
possession | -0.019 |
Token | noises |
Token ID | 26782 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
means | +0.037 |
Bird | +0.036 |
Fle | +0.034 |
Cro | +0.032 |
calls | +0.031 |
Neg logit contributions | |
pron | -0.054 |
lifetime | -0.048 |
+. | -0.043 |
THE | -0.043 |
ouse | -0.042 |
Token | like |
Token ID | 588 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
means | +0.048 |
Bird | +0.047 |
Fle | +0.044 |
calls | +0.041 |
Cro | +0.041 |
Neg logit contributions | |
pron | -0.074 |
lifetime | -0.066 |
+. | -0.060 |
THE | -0.059 |
ouse | -0.058 |
Token | waves |
Token ID | 9813 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
pron | +0.082 |
lifetime | +0.072 |
+. | +0.066 |
THE | +0.065 |
ouse | +0.065 |
Neg logit contributions | |
means | -0.051 |
Bird | -0.051 |
Fle | -0.047 |
Cro | -0.045 |
calls | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
means | +0.019 |
Bird | +0.019 |
Fle | +0.018 |
Cro | +0.017 |
calls | +0.016 |
Neg logit contributions | |
pron | -0.033 |
lifetime | -0.029 |
+. | -0.026 |
THE | -0.026 |
ouse | -0.026 |
Token | se |
Token ID | 384 |
Feature activation | -4.91e+00 |
Pos logit contributions | |
means | +0.014 |
Bird | +0.014 |
Fle | +0.013 |
Cro | +0.012 |
calls | +0.012 |
Neg logit contributions | |
pron | -0.021 |
lifetime | -0.019 |
+. | -0.017 |
THE | -0.017 |
ouse | -0.017 |
Token | ag |
Token ID | 363 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
means | +0.270 |
Bird | +0.264 |
Fle | +0.254 |
Cro | +0.241 |
calls | +0.239 |
Neg logit contributions | |
pron | -0.247 |
lifetime | -0.211 |
+. | -0.186 |
THE | -0.184 |
"! | -0.178 |
Token | ull |
Token ID | 724 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
means | +0.011 |
Bird | +0.011 |
Fle | +0.010 |
Bee | +0.009 |
Cro | +0.009 |
Neg logit contributions | |
pron | -0.017 |
lifetime | -0.015 |
+. | -0.013 |
brand | -0.013 |
THE | -0.013 |
Token | s |
Token ID | 82 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
means | +0.089 |
Bird | +0.086 |
Fle | +0.083 |
Cro | +0.078 |
Bees | +0.077 |
Neg logit contributions | |
pron | -0.117 |
lifetime | -0.104 |
THE | -0.094 |
+. | -0.093 |
ouse | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
Bird | +0.063 |
means | +0.062 |
Fle | +0.057 |
calls | +0.054 |
Cro | +0.052 |
Neg logit contributions | |
pron | -0.112 |
lifetime | -0.098 |
+. | -0.089 |
possession | -0.088 |
ouse | -0.087 |
Token | They |
Token ID | 1119 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
means | +0.012 |
Bird | +0.012 |
Fle | +0.011 |
Cro | +0.011 |
calls | +0.010 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.019 |
THE | -0.018 |
+. | -0.018 |
"! | -0.018 |
Token | feels |
Token ID | 5300 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
Bird | +0.012 |
means | +0.011 |
Fle | +0.011 |
Cro | +0.010 |
Bunny | +0.010 |
Neg logit contributions | |
pron | -0.020 |
lifetime | -0.018 |
+. | -0.017 |
THE | -0.017 |
"! | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
means | +0.029 |
Bird | +0.029 |
Fle | +0.028 |
calls | +0.025 |
Cro | +0.025 |
Neg logit contributions | |
pron | -0.045 |
lifetime | -0.040 |
ouse | -0.035 |
"! | -0.034 |
+. | -0.034 |
Token | wind |
Token ID | 2344 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
Bird | +0.018 |
means | +0.017 |
Fle | +0.016 |
calls | +0.016 |
Cro | +0.015 |
Neg logit contributions | |
pron | -0.030 |
lifetime | -0.027 |
"! | -0.025 |
THE | -0.025 |
ouse | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
means | +0.001 |
Bird | +0.001 |
Fle | +0.000 |
Bees | +0.000 |
Cro | +0.000 |
Neg logit contributions | |
pron | -0.001 |
lifetime | -0.001 |
THE | -0.000 |
+. | -0.000 |
"! | -0.000 |
Token | his |
Token ID | 465 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
means | +0.013 |
Bird | +0.013 |
Fle | +0.013 |
Cro | +0.012 |
calls | +0.011 |
Neg logit contributions | |
pron | -0.019 |
lifetime | -0.017 |
+. | -0.015 |
THE | -0.015 |
ouse | -0.015 |
Token | hair |
Token ID | 4190 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
pron | +0.005 |
lifetime | +0.004 |
THE | +0.004 |
+. | +0.004 |
"! | +0.004 |
Neg logit contributions | |
Bird | -0.004 |
means | -0.004 |
Fle | -0.004 |
calls | -0.004 |
Cro | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -4.75e-02 |
Pos logit contributions | |
pron | +0.149 |
lifetime | +0.139 |
+. | +0.123 |
possession | +0.122 |
THE | +0.122 |
Neg logit contributions | |
means | -0.081 |
Bird | -0.072 |
Fle | -0.070 |
calls | -0.068 |
Cro | -0.063 |
Token | He |
Token ID | 679 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
means | +0.002 |
Bird | +0.002 |
Fle | +0.001 |
acts | +0.001 |
calls | +0.001 |
Neg logit contributions | |
pron | -0.003 |
lifetime | -0.003 |
+. | -0.003 |
THE | -0.003 |
"! | -0.003 |
Token | laughs |
Token ID | 22051 |
Feature activation | +3.88e-01 |
Pos logit contributions | |
Bird | +0.011 |
means | +0.010 |
Fle | +0.010 |
Cro | +0.009 |
Bee | +0.009 |
Neg logit contributions | |
pron | -0.019 |
lifetime | -0.016 |
+. | -0.016 |
THE | -0.015 |
ouse | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
pron | +0.030 |
lifetime | +0.027 |
ouse | +0.024 |
possession | +0.024 |
+. | +0.024 |
Neg logit contributions | |
means | -0.013 |
Bird | -0.013 |
Fle | -0.012 |
calls | -0.011 |
Bee | -0.011 |
Token | sings |
Token ID | 33041 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
pron | +0.007 |
lifetime | +0.007 |
+. | +0.007 |
"! | +0.006 |
THE | +0.006 |
Neg logit contributions | |
Bird | -0.003 |
means | -0.003 |
Fle | -0.002 |
Cro | -0.002 |
Bees | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +9.27e-02 |
Pos logit contributions | |
means | +0.037 |
Bird | +0.036 |
Fle | +0.034 |
Bees | +0.033 |
Cro | +0.033 |
Neg logit contributions | |
pron | -0.042 |
lifetime | -0.034 |
+. | -0.032 |
THE | -0.031 |
brand | -0.031 |
Token | went |
Token ID | 1816 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
pron | +0.006 |
lifetime | +0.005 |
+. | +0.005 |
THE | +0.005 |
ouse | +0.005 |
Neg logit contributions | |
means | -0.004 |
Bird | -0.004 |
Fle | -0.003 |
Cro | -0.003 |
Bees | -0.003 |
Token | back |
Token ID | 736 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
Bird | +0.016 |
calls | +0.015 |
means | +0.015 |
Fle | +0.014 |
Bunny | +0.014 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.020 |
"! | -0.018 |
+. | -0.018 |
arest | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
means | +0.011 |
Bird | +0.011 |
Fle | +0.010 |
calls | +0.010 |
Cro | +0.010 |
Neg logit contributions | |
pron | -0.012 |
lifetime | -0.010 |
+. | -0.009 |
THE | -0.009 |
"! | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
Bird | +0.003 |
means | +0.003 |
Fle | +0.003 |
calls | +0.003 |
Bee | +0.002 |
Neg logit contributions | |
pron | -0.004 |
lifetime | -0.004 |
ouse | -0.003 |
arest | -0.003 |
THE | -0.003 |
Token | porch |
Token ID | 33179 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Bird | +0.004 |
calls | +0.004 |
means | +0.004 |
Bees | +0.003 |
Fle | +0.003 |
Neg logit contributions | |
pron | -0.004 |
lifetime | -0.003 |
"! | -0.003 |
arest | -0.003 |
ouse | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +9.74e-02 |
Pos logit contributions | |
pron | +0.142 |
lifetime | +0.129 |
+. | +0.119 |
arest | +0.119 |
THE | +0.118 |
Neg logit contributions | |
Bird | -0.086 |
means | -0.081 |
Fle | -0.078 |
calls | -0.078 |
Bee | -0.073 |
Token | play |
Token ID | 711 |
Feature activation | +9.28e-01 |
Pos logit contributions | |
pron | +0.006 |
lifetime | +0.005 |
+. | +0.005 |
THE | +0.004 |
"! | +0.004 |
Neg logit contributions | |
means | -0.005 |
Bird | -0.004 |
Fle | -0.004 |
Cro | -0.004 |
Bees | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
lifetime | +0.066 |
pron | +0.065 |
arest | +0.056 |
ouse | +0.055 |
+. | +0.055 |
Neg logit contributions | |
means | -0.028 |
Bird | -0.028 |
Fle | -0.027 |
Bee | -0.024 |
Bunny | -0.024 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
means | +0.018 |
Bird | +0.017 |
Fle | +0.016 |
Bees | +0.014 |
calls | +0.014 |
Neg logit contributions | |
pron | -0.044 |
lifetime | -0.040 |
THE | -0.037 |
+. | -0.037 |
"! | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -3.27e-01 |
Pos logit contributions | |
means | +0.024 |
Bird | +0.023 |
Fle | +0.022 |
Cro | +0.020 |
Bees | +0.020 |
Neg logit contributions | |
pron | -0.040 |
lifetime | -0.035 |
+. | -0.032 |
THE | -0.032 |
"! | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
means | +0.019 |
Bird | +0.018 |
Fle | +0.017 |
Cro | +0.016 |
calls | +0.015 |
Neg logit contributions | |
pron | -0.026 |
lifetime | -0.024 |
+. | -0.021 |
THE | -0.021 |
"! | -0.020 |
Token | but |
Token ID | 475 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
pron | +0.044 |
lifetime | +0.042 |
THE | +0.037 |
ouse | +0.036 |
arest | +0.036 |
Neg logit contributions | |
means | -0.029 |
Bird | -0.028 |
Fle | -0.027 |
calls | -0.025 |
Cro | -0.025 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
pron | +0.107 |
lifetime | +0.099 |
arest | +0.089 |
+. | +0.089 |
"! | +0.088 |
Neg logit contributions | |
means | -0.048 |
Bird | -0.043 |
Fle | -0.042 |
Cro | -0.039 |
Bunny | -0.039 |
Token | my |
Token ID | 1820 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
pron | +0.078 |
lifetime | +0.070 |
THE | +0.064 |
+. | +0.063 |
"! | +0.062 |
Neg logit contributions | |
means | -0.046 |
Bird | -0.045 |
Fle | -0.042 |
Cro | -0.039 |
calls | -0.039 |
Token | said |
Token ID | 531 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
pron | +0.015 |
lifetime | +0.013 |
+. | +0.012 |
ouse | +0.012 |
"! | +0.011 |
Neg logit contributions | |
Bird | -0.011 |
means | -0.010 |
Fle | -0.010 |
Bees | -0.010 |
Cro | -0.009 |
Token | no |
Token ID | 645 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
pron | +0.110 |
lifetime | +0.103 |
THE | +0.090 |
+. | +0.088 |
possession | +0.087 |
Neg logit contributions | |
means | -0.088 |
Bird | -0.087 |
Fle | -0.085 |
Cro | -0.082 |
Bee | -0.076 |
Token | because |
Token ID | 780 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
pron | +0.144 |
lifetime | +0.126 |
THE | +0.113 |
+. | +0.112 |
ouse | +0.109 |
Neg logit contributions | |
means | -0.107 |
Bird | -0.102 |
Fle | -0.100 |
Cro | -0.094 |
calls | -0.092 |
Token | he |
Token ID | 339 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
pron | +0.140 |
lifetime | +0.124 |
+. | +0.111 |
THE | +0.109 |
ouse | +0.109 |
Neg logit contributions | |
means | -0.112 |
Bird | -0.108 |
Fle | -0.104 |
Cro | -0.099 |
calls | -0.095 |
Token | knew |
Token ID | 2993 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
pron | +0.044 |
lifetime | +0.037 |
+. | +0.034 |
ouse | +0.034 |
"! | +0.032 |
Neg logit contributions | |
Bird | -0.036 |
means | -0.035 |
Fle | -0.034 |
Bees | -0.033 |
Bee | -0.032 |
Token | his |
Token ID | 465 |
Feature activation | +4.39e-01 |
Pos logit contributions | |
pron | +0.035 |
lifetime | +0.031 |
ouse | +0.027 |
+. | +0.027 |
THE | +0.027 |
Neg logit contributions | |
means | -0.027 |
Bird | -0.025 |
Fle | -0.024 |
Cro | -0.023 |
Bunny | -0.022 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
pron | +0.024 |
lifetime | +0.022 |
THE | +0.020 |
"! | +0.019 |
+. | +0.019 |
Neg logit contributions | |
means | -0.022 |
Fle | -0.020 |
Bird | -0.020 |
Cro | -0.019 |
calls | -0.019 |
Token | excited |
Token ID | 6568 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
means | +0.010 |
Bird | +0.010 |
Fle | +0.010 |
Cro | +0.009 |
calls | +0.009 |
Neg logit contributions | |
pron | -0.011 |
lifetime | -0.010 |
THE | -0.009 |
+. | -0.009 |
"! | -0.008 |
Token | ! |
Token ID | 0 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
means | +0.032 |
Bird | +0.030 |
Fle | +0.028 |
calls | +0.027 |
Cro | +0.026 |
Neg logit contributions | |
pron | -0.048 |
lifetime | -0.042 |
THE | -0.039 |
ouse | -0.038 |
+. | -0.038 |
Token | He |
Token ID | 679 |
Feature activation | +5.91e-02 |
Pos logit contributions | |
pron | +0.039 |
lifetime | +0.035 |
+. | +0.032 |
THE | +0.032 |
ouse | +0.031 |
Neg logit contributions | |
means | -0.016 |
Bird | -0.016 |
Fle | -0.015 |
Cro | -0.014 |
Bees | -0.013 |
Token | painted |
Token ID | 13055 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
pron | +0.004 |
lifetime | +0.004 |
THE | +0.003 |
+. | +0.003 |
possession | +0.003 |
Neg logit contributions | |
means | -0.002 |
Bird | -0.002 |
Fle | -0.002 |
calls | -0.002 |
Cro | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
pron | +0.049 |
lifetime | +0.046 |
+. | +0.042 |
ouse | +0.042 |
arest | +0.040 |
Neg logit contributions | |
means | -0.024 |
Bird | -0.023 |
Fle | -0.021 |
Bee | -0.019 |
Cro | -0.019 |
Token | hay |
Token ID | 27678 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
pron | +0.035 |
lifetime | +0.031 |
THE | +0.029 |
+. | +0.029 |
"! | +0.029 |
Neg logit contributions | |
Bird | -0.028 |
means | -0.028 |
Fle | -0.026 |
calls | -0.025 |
Cro | -0.025 |
Token | all |
Token ID | 477 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
pron | +0.135 |
lifetime | +0.120 |
+. | +0.111 |
THE | +0.108 |
ouse | +0.106 |
Neg logit contributions | |
means | -0.092 |
Bird | -0.090 |
Fle | -0.084 |
Cro | -0.079 |
Bee | -0.078 |
Token | different |
Token ID | 1180 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
pron | +0.030 |
lifetime | +0.028 |
ouse | +0.026 |
+. | +0.025 |
arest | +0.024 |
Neg logit contributions | |
means | -0.015 |
Bird | -0.012 |
Fle | -0.011 |
meant | -0.011 |
Cro | -0.010 |
Token | colors |
Token ID | 7577 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
means | +0.020 |
Bird | +0.019 |
Fle | +0.018 |
Cro | +0.017 |
calls | +0.017 |
Neg logit contributions | |
pron | -0.023 |
lifetime | -0.020 |
+. | -0.018 |
THE | -0.018 |
ouse | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
pron | +0.012 |
lifetime | +0.011 |
+. | +0.010 |
THE | +0.009 |
ouse | +0.009 |
Neg logit contributions | |
means | -0.006 |
Bird | -0.005 |
Fle | -0.005 |
Cro | -0.005 |
meant | -0.004 |
Token | His |
Token ID | 2399 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
means | +0.006 |
Bird | +0.006 |
Fle | +0.006 |
Cro | +0.006 |
Bees | +0.005 |
Neg logit contributions | |
pron | -0.014 |
lifetime | -0.012 |
+. | -0.012 |
THE | -0.011 |
ouse | -0.011 |
Token | Dave |
Token ID | 27984 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
pron | +0.007 |
lifetime | +0.006 |
possession | +0.006 |
brand | +0.006 |
ouse | +0.005 |
Neg logit contributions | |
means | -0.006 |
Bird | -0.006 |
Fle | -0.006 |
Bees | -0.006 |
Cro | -0.005 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
pron | +0.033 |
lifetime | +0.030 |
+. | +0.027 |
THE | +0.027 |
ouse | +0.027 |
Neg logit contributions | |
means | -0.019 |
Bird | -0.019 |
Fle | -0.018 |
Cro | -0.016 |
Bees | -0.016 |
Token | at |
Token ID | 379 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
pron | +0.018 |
lifetime | +0.016 |
THE | +0.014 |
"! | +0.014 |
+. | +0.014 |
Neg logit contributions | |
means | -0.008 |
Fle | -0.008 |
Bird | -0.008 |
calls | -0.007 |
asks | -0.007 |
Token | Ms |
Token ID | 6997 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
pron | +0.083 |
lifetime | +0.072 |
+. | +0.067 |
THE | +0.066 |
possession | +0.066 |
Neg logit contributions | |
means | -0.053 |
Bird | -0.052 |
Fle | -0.049 |
Bees | -0.047 |
Cro | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
pron | +0.040 |
lifetime | +0.034 |
"! | +0.031 |
+. | +0.031 |
THE | +0.031 |
Neg logit contributions | |
means | -0.044 |
Bird | -0.042 |
Fle | -0.040 |
Bees | -0.040 |
Cro | -0.039 |
Token | Sarah |
Token ID | 10490 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
pron | +0.078 |
lifetime | +0.068 |
+. | +0.063 |
THE | +0.062 |
"! | +0.061 |
Neg logit contributions | |
means | -0.049 |
Bird | -0.047 |
Fle | -0.045 |
Cro | -0.042 |
Bees | -0.042 |
Token | with |
Token ID | 351 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
pron | +0.145 |
lifetime | +0.128 |
+. | +0.118 |
THE | +0.117 |
"! | +0.114 |
Neg logit contributions | |
means | -0.089 |
Bird | -0.087 |
Fle | -0.081 |
Cro | -0.076 |
calls | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
pron | +0.017 |
lifetime | +0.014 |
+. | +0.013 |
brand | +0.013 |
THE | +0.013 |
Neg logit contributions | |
means | -0.014 |
Bird | -0.014 |
Fle | -0.013 |
Bees | -0.013 |
Cro | -0.013 |
Token | smile |
Token ID | 8212 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
THE | +0.047 |
pron | +0.047 |
lifetime | +0.045 |
"! | +0.042 |
possession | +0.042 |
Neg logit contributions | |
means | -0.030 |
Fle | -0.029 |
Bird | -0.028 |
calls | -0.027 |
acts | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
pron | +0.080 |
lifetime | +0.072 |
THE | +0.065 |
+. | +0.065 |
"! | +0.063 |
Neg logit contributions | |
means | -0.054 |
Bird | -0.051 |
Fle | -0.048 |
calls | -0.045 |
Cro | -0.045 |
Token | said |
Token ID | 531 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
pron | +0.016 |
lifetime | +0.014 |
+. | +0.013 |
brand | +0.013 |
THE | +0.013 |
Neg logit contributions | |
means | -0.007 |
Bird | -0.007 |
Fle | -0.007 |
Bees | -0.006 |
Cro | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
pron | +0.029 |
lifetime | +0.026 |
+. | +0.025 |
THE | +0.025 |
"! | +0.024 |
Neg logit contributions | |
means | -0.011 |
Bird | -0.011 |
Fle | -0.010 |
Cro | -0.009 |
acts | -0.009 |
Token | want |
Token ID | 765 |
Feature activation | +7.66e-01 |
Pos logit contributions | |
means | +0.011 |
Bird | +0.011 |
Fle | +0.010 |
Cro | +0.010 |
Bees | +0.010 |
Neg logit contributions | |
pron | -0.018 |
lifetime | -0.016 |
+. | -0.014 |
THE | -0.014 |
"! | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
pron | +0.033 |
lifetime | +0.026 |
+. | +0.023 |
brand | +0.023 |
possession | +0.022 |
Neg logit contributions | |
means | -0.046 |
Bird | -0.045 |
Fle | -0.044 |
Bees | -0.043 |
Cro | -0.042 |
Token | help |
Token ID | 1037 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
means | +0.004 |
Bird | +0.004 |
Fle | +0.004 |
Bees | +0.004 |
Cro | +0.004 |
Neg logit contributions | |
pron | -0.007 |
lifetime | -0.006 |
+. | -0.005 |
THE | -0.005 |
"! | -0.005 |
Token | Mom |
Token ID | 11254 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Bird | +0.074 |
means | +0.073 |
Bees | +0.071 |
Fle | +0.069 |
Cro | +0.068 |
Neg logit contributions | |
pron | -0.071 |
lifetime | -0.051 |
ouse | -0.049 |
+. | -0.049 |
passport | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +6.64e-02 |
Pos logit contributions | |
Bird | +0.018 |
Fle | +0.017 |
means | +0.017 |
Cro | +0.017 |
Bees | +0.016 |
Neg logit contributions | |
pron | -0.017 |
lifetime | -0.013 |
ouse | -0.013 |
+. | -0.012 |
brand | -0.012 |
Token | They |
Token ID | 1119 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
pron | +0.004 |
lifetime | +0.004 |
+. | +0.004 |
THE | +0.004 |
"! | +0.004 |
Neg logit contributions | |
Bird | -0.002 |
means | -0.002 |
Fle | -0.002 |
Cro | -0.002 |
acts | -0.002 |
Token | want |
Token ID | 765 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
means | +0.014 |
Bird | +0.014 |
Fle | +0.013 |
Cro | +0.012 |
Bees | +0.012 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.019 |
+. | -0.018 |
THE | -0.018 |
"! | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
pron | +0.027 |
lifetime | +0.021 |
+. | +0.019 |
brand | +0.019 |
possession | +0.018 |
Neg logit contributions | |
means | -0.039 |
Bird | -0.038 |
Fle | -0.037 |
Bees | -0.036 |
Cro | -0.036 |
Token | help |
Token ID | 1037 |
Feature activation | -1.50e+00 |
Pos logit contributions | |
means | +0.010 |
Bird | +0.010 |
Fle | +0.009 |
Bees | +0.009 |
Cro | +0.009 |
Neg logit contributions | |
pron | -0.013 |
lifetime | -0.011 |
+. | -0.011 |
"! | -0.010 |
THE | -0.010 |
Token | Grand |
Token ID | 5675 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
means | +0.078 |
Bird | +0.078 |
Bees | +0.076 |
Fle | +0.075 |
Cro | +0.073 |
Neg logit contributions | |
pron | -0.075 |
+. | -0.050 |
ouse | -0.050 |
!". | -0.049 |
"! | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
pron | +0.047 |
lifetime | +0.045 |
+. | +0.041 |
possession | +0.041 |
THE | +0.041 |
Neg logit contributions | |
means | -0.025 |
Bird | -0.024 |
Fle | -0.021 |
calls | -0.021 |
Bee | -0.020 |
Token | have |
Token ID | 423 |
Feature activation | +4.93e-02 |
Pos logit contributions | |
means | +0.014 |
Bird | +0.014 |
Fle | +0.013 |
calls | +0.012 |
Cro | +0.012 |
Neg logit contributions | |
pron | -0.021 |
lifetime | -0.019 |
+. | -0.017 |
THE | -0.017 |
"! | -0.016 |
Token | sweet |
Token ID | 6029 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
pron | +0.004 |
ouse | +0.003 |
lifetime | +0.003 |
belt | +0.003 |
arest | +0.003 |
Neg logit contributions | |
Bird | -0.002 |
means | -0.001 |
Bunny | -0.001 |
Bee | -0.001 |
Tweet | -0.001 |
Token | dreams |
Token ID | 10625 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
means | +0.032 |
Bird | +0.031 |
Fle | +0.030 |
Cro | +0.028 |
Bees | +0.028 |
Neg logit contributions | |
pron | -0.037 |
lifetime | -0.032 |
+. | -0.029 |
THE | -0.028 |
"! | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
Bird | +0.011 |
means | +0.011 |
from | +0.009 |
calls | +0.009 |
Bunny | +0.009 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.021 |
possession | -0.020 |
+. | -0.019 |
joy | -0.019 |
Token | I |
Token ID | 314 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
means | +0.013 |
Bird | +0.012 |
Fle | +0.011 |
Cro | +0.011 |
calls | +0.010 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.020 |
THE | -0.019 |
"! | -0.018 |
+. | -0.018 |
Token | have |
Token ID | 423 |
Feature activation | +9.72e-03 |
Pos logit contributions | |
pron | +0.073 |
lifetime | +0.064 |
+. | +0.058 |
possession | +0.057 |
THE | +0.057 |
Neg logit contributions | |
means | -0.057 |
Bird | -0.055 |
Fle | -0.052 |
calls | -0.049 |
Cro | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
pron | +0.001 |
lifetime | +0.001 |
ouse | +0.001 |
+. | +0.001 |
oor | +0.001 |
Neg logit contributions | |
Bird | -0.000 |
means | -0.000 |
Bunny | -0.000 |
Bee | -0.000 |
Fle | -0.000 |
Token | go |
Token ID | 467 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
means | +0.024 |
Bird | +0.024 |
Fle | +0.022 |
Cro | +0.021 |
calls | +0.020 |
Neg logit contributions | |
pron | -0.037 |
lifetime | -0.033 |
+. | -0.030 |
THE | -0.030 |
ouse | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -4.38e-03 |
Pos logit contributions | |
Bird | +0.051 |
calls | +0.048 |
means | +0.048 |
Fle | +0.047 |
Bunny | +0.046 |
Neg logit contributions | |
pron | -0.074 |
lifetime | -0.064 |
+. | -0.059 |
possession | -0.057 |
arest | -0.056 |
Token | visit |
Token ID | 3187 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
means | +0.000 |
Bird | +0.000 |
Fle | +0.000 |
Cro | +0.000 |
Bees | +0.000 |
Neg logit contributions | |
pron | -0.000 |
lifetime | -0.000 |
+. | -0.000 |
THE | -0.000 |
ouse | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
pron | +0.056 |
lifetime | +0.049 |
+. | +0.045 |
THE | +0.045 |
"! | +0.044 |
Neg logit contributions | |
means | -0.036 |
Bird | -0.035 |
Fle | -0.033 |
Cro | -0.031 |
Bees | -0.031 |
Token | " |
Token ID | 366 |
Feature activation | +8.00e-02 |
Pos logit contributions | |
pron | +0.039 |
lifetime | +0.034 |
+. | +0.031 |
THE | +0.031 |
ouse | +0.030 |
Neg logit contributions | |
means | -0.036 |
Bird | -0.035 |
Fle | -0.034 |
Cro | -0.032 |
Bees | -0.031 |
Token | Yes |
Token ID | 5297 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
pron | +0.005 |
lifetime | +0.004 |
+. | +0.004 |
THE | +0.003 |
ouse | +0.003 |
Neg logit contributions | |
means | -0.004 |
Bird | -0.004 |
Fle | -0.004 |
Cro | -0.003 |
Bees | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
pron | +0.021 |
lifetime | +0.019 |
ouse | +0.017 |
THE | +0.017 |
+. | +0.017 |
Neg logit contributions | |
Bird | -0.006 |
means | -0.005 |
Fle | -0.005 |
Bee | -0.005 |
Bunny | -0.005 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
means | +0.026 |
Bird | +0.026 |
Fle | +0.023 |
Bunny | +0.023 |
Tweet | +0.022 |
Neg logit contributions | |
pron | -0.050 |
lifetime | -0.049 |
+. | -0.043 |
ouse | -0.043 |
THE | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +6.46e-03 |
Pos logit contributions | |
means | +0.026 |
Bird | +0.026 |
Fle | +0.023 |
calls | +0.022 |
Bunny | +0.022 |
Neg logit contributions | |
pron | -0.034 |
lifetime | -0.030 |
THE | -0.027 |
arest | -0.026 |
+. | -0.026 |
Token | Dolphins |
Token ID | 21668 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
pron | +0.000 |
lifetime | +0.000 |
"! | +0.000 |
THE | +0.000 |
!". | +0.000 |
Neg logit contributions | |
means | -0.000 |
calls | -0.000 |
acts | -0.000 |
Fle | -0.000 |
Bird | -0.000 |
Token | are |
Token ID | 389 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
pron | +0.035 |
lifetime | +0.031 |
+. | +0.028 |
THE | +0.028 |
ouse | +0.028 |
Neg logit contributions | |
means | -0.018 |
Bird | -0.018 |
Fle | -0.016 |
calls | -0.015 |
Cro | -0.015 |
Token | very |
Token ID | 845 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
means | +0.014 |
Bird | +0.014 |
Fle | +0.013 |
Bees | +0.013 |
Cro | +0.013 |
Neg logit contributions | |
pron | -0.014 |
lifetime | -0.013 |
THE | -0.011 |
+. | -0.011 |
"! | -0.011 |
Token | smart |
Token ID | 4451 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
pron | +0.035 |
lifetime | +0.031 |
+. | +0.026 |
ouse | +0.025 |
THE | +0.025 |
Neg logit contributions | |
means | -0.048 |
Bird | -0.046 |
Fle | -0.044 |
Bees | -0.043 |
Cro | -0.042 |
Token | and |
Token ID | 290 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
means | +0.003 |
Bird | +0.003 |
Fle | +0.003 |
calls | +0.003 |
Bee | +0.002 |
Neg logit contributions | |
pron | -0.005 |
lifetime | -0.004 |
+. | -0.004 |
THE | -0.004 |
ouse | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
means | +0.048 |
Bird | +0.048 |
Fle | +0.045 |
Cro | +0.042 |
calls | +0.042 |
Neg logit contributions | |
pron | -0.064 |
lifetime | -0.057 |
+. | -0.051 |
THE | -0.051 |
"! | -0.049 |
Token | He |
Token ID | 679 |
Feature activation | +6.73e-02 |
Pos logit contributions | |
pron | +0.026 |
lifetime | +0.023 |
"! | +0.022 |
+. | +0.022 |
THE | +0.022 |
Neg logit contributions | |
means | -0.014 |
Bird | -0.013 |
Fle | -0.012 |
acts | -0.011 |
calls | -0.011 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
pron | +0.004 |
lifetime | +0.004 |
+. | +0.004 |
"! | +0.003 |
THE | +0.003 |
Neg logit contributions | |
Bird | -0.002 |
means | -0.002 |
Fle | -0.002 |
Cro | -0.002 |
Bees | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
pron | +0.011 |
+. | +0.009 |
lifetime | +0.009 |
possession | +0.009 |
brand | +0.009 |
Neg logit contributions | |
means | -0.009 |
Bird | -0.008 |
Bees | -0.008 |
Fle | -0.008 |
calls | -0.007 |
Token | with |
Token ID | 351 |
Feature activation | -7.90e-01 |
Pos logit contributions | |
means | +0.031 |
Bird | +0.030 |
Fle | +0.029 |
Bees | +0.028 |
Cro | +0.027 |
Neg logit contributions | |
pron | -0.045 |
lifetime | -0.039 |
THE | -0.036 |
+. | -0.036 |
pad | -0.035 |
Token | his |
Token ID | 465 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
means | +0.035 |
Bird | +0.035 |
Fle | +0.033 |
Cro | +0.031 |
calls | +0.031 |
Neg logit contributions | |
pron | -0.048 |
lifetime | -0.042 |
+. | -0.038 |
THE | -0.038 |
ouse | -0.037 |
Token | claws |
Token ID | 28421 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
pron | +0.012 |
lifetime | +0.011 |
THE | +0.010 |
+. | +0.010 |
"! | +0.010 |
Neg logit contributions | |
Bird | -0.010 |
means | -0.010 |
Fle | -0.009 |
Cro | -0.009 |
calls | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +4.14e-02 |
Pos logit contributions | |
pron | +0.112 |
lifetime | +0.102 |
THE | +0.093 |
+. | +0.093 |
ileen | +0.090 |
Neg logit contributions | |
means | -0.045 |
Bird | -0.044 |
Fle | -0.039 |
calls | -0.038 |
Cro | -0.034 |
Token | teeth |
Token ID | 9941 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
pron | +0.002 |
lifetime | +0.002 |
+. | +0.002 |
brand | +0.002 |
ouse | +0.002 |
Neg logit contributions | |
means | -0.002 |
Bird | -0.002 |
Fle | -0.002 |
Bees | -0.002 |
Cro | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
pron | +0.059 |
lifetime | +0.052 |
+. | +0.047 |
THE | +0.047 |
ouse | +0.045 |
Neg logit contributions | |
means | -0.044 |
Bird | -0.043 |
Fle | -0.040 |
Cro | -0.038 |
calls | -0.038 |
Token | ripped |
Token ID | 19551 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
pron | +0.002 |
lifetime | +0.002 |
+. | +0.002 |
brand | +0.002 |
ouse | +0.002 |
Neg logit contributions | |
means | -0.002 |
Bird | -0.002 |
Fle | -0.001 |
Bees | -0.001 |
Cro | -0.001 |
Token | time |
Token ID | 640 |
Feature activation | -7.03e-01 |
Pos logit contributions | |
Bird | +0.035 |
means | +0.034 |
Fle | +0.033 |
Bee | +0.031 |
Cro | +0.030 |
Neg logit contributions | |
pron | -0.041 |
lifetime | -0.038 |
THE | -0.033 |
+. | -0.033 |
ouse | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -9.85e-01 |
Pos logit contributions | |
means | +0.031 |
Bird | +0.030 |
Fle | +0.028 |
Bees | +0.027 |
calls | +0.027 |
Neg logit contributions | |
pron | -0.042 |
lifetime | -0.037 |
THE | -0.034 |
+. | -0.034 |
"! | -0.033 |
Token | there |
Token ID | 612 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
means | +0.050 |
Bird | +0.050 |
Fle | +0.048 |
Cro | +0.045 |
Bees | +0.044 |
Neg logit contributions | |
pron | -0.053 |
lifetime | -0.046 |
+. | -0.041 |
THE | -0.040 |
"! | -0.039 |
Token | lived |
Token ID | 5615 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
Bird | +0.022 |
means | +0.022 |
Fle | +0.021 |
Bees | +0.020 |
calls | +0.020 |
Neg logit contributions | |
pron | -0.039 |
lifetime | -0.034 |
THE | -0.033 |
+. | -0.032 |
"! | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
pron | +0.006 |
lifetime | +0.005 |
THE | +0.005 |
+. | +0.005 |
"! | +0.004 |
Neg logit contributions | |
means | -0.004 |
Bird | -0.004 |
Fle | -0.004 |
calls | -0.004 |
Bees | -0.004 |
Token | mighty |
Token ID | 18680 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
means | +0.002 |
Bird | +0.002 |
Fle | +0.002 |
calls | +0.002 |
Cro | +0.002 |
Neg logit contributions | |
pron | -0.003 |
lifetime | -0.002 |
+. | -0.002 |
THE | -0.002 |
ouse | -0.002 |
Token | mole |
Token ID | 9411 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
means | +0.011 |
Bird | +0.011 |
Fle | +0.010 |
Cro | +0.009 |
Bees | +0.009 |
Neg logit contributions | |
pron | -0.017 |
lifetime | -0.015 |
+. | -0.014 |
THE | -0.013 |
ouse | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -2.22e-01 |
Pos logit contributions | |
Bird | +0.020 |
means | +0.020 |
Fle | +0.018 |
Cro | +0.017 |
Bees | +0.017 |
Neg logit contributions | |
pron | -0.047 |
lifetime | -0.043 |
+. | -0.039 |
THE | -0.039 |
brand | -0.039 |
Token | He |
Token ID | 679 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
means | +0.010 |
calls | +0.009 |
Bird | +0.009 |
Fle | +0.008 |
acts | +0.008 |
Neg logit contributions | |
pron | -0.012 |
lifetime | -0.010 |
"! | -0.010 |
possession | -0.010 |
!". | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -8.57e-01 |
Pos logit contributions | |
means | +0.021 |
Bird | +0.021 |
Fle | +0.020 |
Bees | +0.019 |
Cro | +0.019 |
Neg logit contributions | |
pron | -0.023 |
lifetime | -0.020 |
THE | -0.018 |
+. | -0.018 |
ouse | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
means | +0.063 |
acts | +0.060 |
Bees | +0.054 |
unn | +0.053 |
Ask | +0.053 |
Neg logit contributions | |
pron | -0.024 |
brand | -0.018 |
satisfied | -0.018 |
whole | -0.016 |
mine | -0.016 |
Token | Later |
Token ID | 11450 |
Feature activation | +8.84e-02 |
Pos logit contributions | |
means | +0.004 |
Bird | +0.004 |
Fle | +0.003 |
Cro | +0.003 |
Bee | +0.003 |
Neg logit contributions | |
pron | -0.007 |
lifetime | -0.007 |
+. | -0.006 |
THE | -0.006 |
"! | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -4.59e-01 |
Pos logit contributions | |
pron | +0.005 |
lifetime | +0.004 |
+. | +0.004 |
THE | +0.004 |
"! | +0.004 |
Neg logit contributions | |
means | -0.005 |
Bird | -0.004 |
Fle | -0.004 |
Cro | -0.004 |
Bees | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
means | +0.016 |
Bird | +0.016 |
Fle | +0.015 |
Bee | +0.013 |
Cro | +0.013 |
Neg logit contributions | |
pron | -0.031 |
lifetime | -0.030 |
"! | -0.026 |
ouse | -0.026 |
+. | -0.026 |
Token | saw |
Token ID | 2497 |
Feature activation | +4.50e-01 |
Pos logit contributions | |
pron | +0.018 |
lifetime | +0.015 |
THE | +0.013 |
+. | +0.013 |
ouse | +0.013 |
Neg logit contributions | |
means | -0.020 |
Bird | -0.020 |
Fle | -0.019 |
Cro | -0.018 |
Bees | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +8.30e-01 |
Pos logit contributions | |
pron | +0.027 |
lifetime | +0.024 |
+. | +0.022 |
THE | +0.022 |
brand | +0.021 |
Neg logit contributions | |
means | -0.020 |
Bird | -0.019 |
Fle | -0.018 |
Cro | -0.017 |
Bees | -0.017 |
Token | butterfly |
Token ID | 35113 |
Feature activation | -7.11e-01 |
Pos logit contributions | |
pron | +0.049 |
lifetime | +0.044 |
THE | +0.042 |
"! | +0.041 |
possession | +0.040 |
Neg logit contributions | |
Bird | -0.036 |
means | -0.034 |
Fle | -0.033 |
Cro | -0.031 |
Bee | -0.030 |
Token | flying |
Token ID | 7348 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
means | +0.033 |
Bird | +0.033 |
Fle | +0.031 |
Cro | +0.030 |
Bees | +0.029 |
Neg logit contributions | |
pron | -0.041 |
lifetime | -0.036 |
THE | -0.032 |
+. | -0.032 |
"! | -0.031 |
Token | around |
Token ID | 1088 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
means | +0.026 |
Bird | +0.025 |
Fle | +0.024 |
Cro | +0.023 |
Bees | +0.022 |
Neg logit contributions | |
pron | -0.030 |
lifetime | -0.026 |
+. | -0.024 |
THE | -0.024 |
"! | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
pron | +0.094 |
lifetime | +0.083 |
+. | +0.076 |
THE | +0.075 |
ouse | +0.075 |
Neg logit contributions | |
means | -0.057 |
Bird | -0.056 |
Fle | -0.053 |
Cro | -0.049 |
Bee | -0.048 |
Token | gate |
Token ID | 8946 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
pron | +0.027 |
lifetime | +0.023 |
ouse | +0.022 |
inations | +0.021 |
arest | +0.021 |
Neg logit contributions | |
Bird | -0.016 |
means | -0.016 |
Bees | -0.015 |
calls | -0.014 |
Fle | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -3.96e-01 |
Pos logit contributions | |
pron | +0.083 |
lifetime | +0.073 |
+. | +0.068 |
ouse | +0.066 |
THE | +0.065 |
Neg logit contributions | |
means | -0.048 |
Bird | -0.047 |
Fle | -0.043 |
calls | -0.042 |
Cro | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | +3.49e-02 |
Pos logit contributions | |
pron | +0.046 |
lifetime | +0.040 |
THE | +0.037 |
+. | +0.036 |
ouse | +0.036 |
Neg logit contributions | |
means | -0.036 |
Bird | -0.036 |
Fle | -0.035 |
Cro | -0.033 |
Bees | -0.031 |
Token | said |
Token ID | 531 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
pron | +0.002 |
lifetime | +0.002 |
+. | +0.002 |
THE | +0.002 |
ouse | +0.002 |
Neg logit contributions | |
means | -0.001 |
Bird | -0.001 |
Fle | -0.001 |
Cro | -0.001 |
Bees | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
pron | +0.057 |
lifetime | +0.050 |
+. | +0.046 |
THE | +0.045 |
"! | +0.044 |
Neg logit contributions | |
means | -0.039 |
Bird | -0.038 |
Fle | -0.036 |
calls | -0.034 |
Cro | -0.034 |
Token | " |
Token ID | 366 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
pron | +0.025 |
lifetime | +0.022 |
+. | +0.020 |
THE | +0.020 |
ouse | +0.019 |
Neg logit contributions | |
means | -0.022 |
Bird | -0.022 |
Fle | -0.021 |
Cro | -0.020 |
Bee | -0.019 |
Token | Why |
Token ID | 5195 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
pron | +0.001 |
lifetime | +0.001 |
THE | +0.001 |
+. | +0.001 |
"! | +0.001 |
Neg logit contributions | |
means | -0.001 |
Bird | -0.001 |
Fle | -0.001 |
calls | -0.001 |
Cro | -0.001 |
Token | do |
Token ID | 466 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
means | +0.025 |
Bird | +0.024 |
Fle | +0.022 |
Cro | +0.020 |
calls | +0.020 |
Neg logit contributions | |
pron | -0.047 |
lifetime | -0.043 |
THE | -0.039 |
+. | -0.039 |
brand | -0.038 |
Token | you |
Token ID | 345 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
means | +0.074 |
Bird | +0.072 |
Fle | +0.069 |
calls | +0.067 |
Cro | +0.067 |
Neg logit contributions | |
pron | -0.071 |
lifetime | -0.060 |
+. | -0.055 |
"! | -0.053 |
THE | -0.053 |
Token | look |
Token ID | 804 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
pron | +0.014 |
lifetime | +0.012 |
+. | +0.011 |
THE | +0.011 |
"! | +0.011 |
Neg logit contributions | |
means | -0.009 |
Bird | -0.009 |
Fle | -0.008 |
Cro | -0.008 |
Bees | -0.008 |
Token | so |
Token ID | 523 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
means | +0.059 |
Fle | +0.057 |
Bird | +0.057 |
from | +0.053 |
calls | +0.052 |
Neg logit contributions | |
pron | -0.124 |
lifetime | -0.119 |
THE | -0.104 |
arest | -0.103 |
ouse | -0.103 |
Token | sad |
Token ID | 6507 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
means | +0.053 |
Bird | +0.052 |
Fle | +0.050 |
Bees | +0.046 |
Cro | +0.046 |
Neg logit contributions | |
pron | -0.089 |
lifetime | -0.079 |
THE | -0.071 |
+. | -0.071 |
"! | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
means | +0.099 |
Bird | +0.098 |
Fle | +0.094 |
Cro | +0.089 |
Bees | +0.088 |
Neg logit contributions | |
pron | -0.103 |
lifetime | -0.089 |
+. | -0.079 |
THE | -0.078 |
"! | -0.077 |
Token | They |
Token ID | 2990 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Bird | +0.002 |
means | +0.001 |
Fle | +0.001 |
Bees | +0.001 |
Bee | +0.001 |
Neg logit contributions | |
pron | -0.002 |
lifetime | -0.002 |
possession | -0.002 |
brand | -0.002 |
ouse | -0.002 |
Token | hugged |
Token ID | 41130 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
pron | +0.021 |
lifetime | +0.018 |
+. | +0.017 |
possession | +0.017 |
brand | +0.017 |
Neg logit contributions | |
Bird | -0.012 |
means | -0.012 |
Fle | -0.011 |
calls | -0.011 |
Cro | -0.011 |
Token | each |
Token ID | 1123 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
pron | +0.014 |
lifetime | +0.012 |
THE | +0.011 |
+. | +0.011 |
possession | +0.011 |
Neg logit contributions | |
means | -0.012 |
Bird | -0.011 |
Fle | -0.011 |
Bees | -0.010 |
Cro | -0.010 |
Token | other |
Token ID | 584 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
means | +0.004 |
Bird | +0.004 |
Fle | +0.004 |
calls | +0.003 |
Bee | +0.003 |
Neg logit contributions | |
pron | -0.007 |
lifetime | -0.007 |
ouse | -0.006 |
brand | -0.006 |
+. | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -5.18e-01 |
Pos logit contributions | |
Bird | +0.027 |
means | +0.027 |
Fle | +0.025 |
Bee | +0.023 |
calls | +0.023 |
Neg logit contributions | |
pron | -0.051 |
lifetime | -0.045 |
+. | -0.042 |
arest | -0.040 |
brand | -0.039 |
Token | They |
Token ID | 1119 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
means | +0.011 |
Bird | +0.011 |
Fle | +0.009 |
Cro | +0.008 |
Bees | +0.008 |
Neg logit contributions | |
pron | -0.041 |
lifetime | -0.038 |
THE | -0.036 |
+. | -0.036 |
"! | -0.035 |
Token | went |
Token ID | 1816 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Bird | +0.022 |
means | +0.022 |
Fle | +0.020 |
Cro | +0.019 |
calls | +0.019 |
Neg logit contributions | |
pron | -0.039 |
lifetime | -0.034 |
+. | -0.031 |
THE | -0.031 |
"! | -0.030 |
Token | back |
Token ID | 736 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
Bird | +0.061 |
means | +0.059 |
Fle | +0.059 |
calls | +0.057 |
Cro | +0.055 |
Neg logit contributions | |
pron | -0.058 |
lifetime | -0.048 |
+. | -0.042 |
"! | -0.041 |
ouse | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
means | +0.041 |
Bird | +0.040 |
Fle | +0.039 |
Bees | +0.037 |
Cro | +0.037 |
Neg logit contributions | |
pron | -0.032 |
lifetime | -0.027 |
+. | -0.024 |
THE | -0.024 |
possession | -0.023 |
Token | the |
Token ID | 262 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
means | +0.009 |
Bird | +0.009 |
Fle | +0.009 |
Cro | +0.008 |
Bees | +0.008 |
Neg logit contributions | |
pron | -0.016 |
lifetime | -0.014 |
+. | -0.013 |
THE | -0.013 |
"! | -0.013 |
Token | hose |
Token ID | 31489 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
Bird | +0.005 |
means | +0.005 |
Fle | +0.005 |
calls | +0.004 |
Bees | +0.004 |
Neg logit contributions | |
pron | -0.007 |
lifetime | -0.006 |
"! | -0.006 |
ouse | -0.006 |
+. | -0.006 |
Token | needed |
Token ID | 2622 |
Feature activation | +9.97e-02 |
Pos logit contributions | |
pron | +0.038 |
lifetime | +0.033 |
THE | +0.030 |
+. | +0.030 |
ouse | +0.029 |
Neg logit contributions | |
means | -0.024 |
Bird | -0.024 |
Fle | -0.022 |
Cro | -0.021 |
calls | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +3.58e-01 |
Pos logit contributions | |
pron | +0.006 |
lifetime | +0.005 |
+. | +0.004 |
ouse | +0.004 |
THE | +0.004 |
Neg logit contributions | |
means | -0.005 |
Bird | -0.005 |
Fle | -0.005 |
Cro | -0.004 |
calls | -0.004 |
Token | watch |
Token ID | 2342 |
Feature activation | +4.73e-01 |
Pos logit contributions | |
pron | +0.022 |
lifetime | +0.020 |
+. | +0.018 |
THE | +0.018 |
"! | +0.018 |
Neg logit contributions | |
means | -0.015 |
Bird | -0.014 |
Fle | -0.014 |
Bees | -0.013 |
Cro | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
pron | +0.028 |
lifetime | +0.025 |
+. | +0.022 |
THE | +0.022 |
"! | +0.022 |
Neg logit contributions | |
means | -0.021 |
Bird | -0.021 |
Fle | -0.020 |
Cro | -0.018 |
Bees | -0.018 |
Token | figure |
Token ID | 3785 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
means | +0.006 |
Bird | +0.006 |
Fle | +0.006 |
Bees | +0.005 |
Cro | +0.005 |
Neg logit contributions | |
pron | -0.007 |
lifetime | -0.007 |
+. | -0.006 |
THE | -0.006 |
possession | -0.006 |
Token | from |
Token ID | 422 |
Feature activation | -6.91e-01 |
Pos logit contributions | |
means | +0.020 |
Bird | +0.019 |
calls | +0.017 |
Fle | +0.017 |
Bee | +0.016 |
Neg logit contributions | |
pron | -0.032 |
lifetime | -0.027 |
+. | -0.025 |
THE | -0.025 |
ouse | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
means | +0.030 |
Bird | +0.029 |
Fle | +0.028 |
Cro | +0.026 |
calls | +0.026 |
Neg logit contributions | |
pron | -0.043 |
lifetime | -0.038 |
+. | -0.034 |
THE | -0.034 |
ouse | -0.034 |
Token | hide |
Token ID | 7808 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
pron | +0.034 |
lifetime | +0.029 |
ouse | +0.027 |
THE | +0.027 |
"! | +0.027 |
Neg logit contributions | |
Bird | -0.023 |
means | -0.023 |
Fle | -0.022 |
Cro | -0.021 |
calls | -0.021 |
Token | out |
Token ID | 448 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
means | +0.012 |
Bird | +0.011 |
Fle | +0.010 |
Bee | +0.010 |
calls | +0.010 |
Neg logit contributions | |
pron | -0.019 |
lifetime | -0.016 |
+. | -0.015 |
ouse | -0.015 |
THE | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -6.14e-02 |
Pos logit contributions | |
pron | +0.092 |
lifetime | +0.077 |
+. | +0.074 |
ouse | +0.073 |
THE | +0.070 |
Neg logit contributions | |
means | -0.059 |
Bird | -0.058 |
calls | -0.053 |
Fle | -0.052 |
Bee | -0.051 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
means | +0.002 |
Bird | +0.002 |
Fle | +0.002 |
Cro | +0.002 |
Bees | +0.002 |
Neg logit contributions | |
pron | -0.004 |
lifetime | -0.004 |
+. | -0.003 |
THE | -0.003 |
ouse | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
means | +0.006 |
Bird | +0.005 |
Fle | +0.005 |
from | +0.005 |
calls | +0.005 |
Neg logit contributions | |
pron | -0.011 |
lifetime | -0.010 |
ouse | -0.009 |
arest | -0.009 |
THE | -0.009 |
Token | couldn |
Token ID | 3521 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
means | +0.016 |
Bird | +0.014 |
Fle | +0.013 |
calls | +0.012 |
Bee | +0.012 |
Neg logit contributions | |
pron | -0.033 |
lifetime | -0.030 |
THE | -0.027 |
+. | -0.027 |
arest | -0.027 |
Token | 't |
Token ID | 470 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
pron | +0.046 |
THE | +0.038 |
"! | +0.038 |
lifetime | +0.037 |
+. | +0.037 |
Neg logit contributions | |
Bird | -0.042 |
means | -0.041 |
Fle | -0.039 |
acts | -0.039 |
calls | -0.039 |
Token | wait |
Token ID | 4043 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
pron | +0.009 |
lifetime | +0.008 |
+. | +0.007 |
THE | +0.007 |
ouse | +0.007 |
Neg logit contributions | |
Bird | -0.008 |
means | -0.007 |
Fle | -0.007 |
Cro | -0.007 |
calls | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
pron | +0.048 |
lifetime | +0.048 |
icycle | +0.046 |
belt | +0.046 |
ouse | +0.046 |
Neg logit contributions | |
means | -0.010 |
from | -0.009 |
calls | -0.009 |
O | -0.008 |
They | -0.008 |
Token | show |
Token ID | 905 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
means | +0.037 |
Bird | +0.036 |
Fle | +0.034 |
Cro | +0.032 |
Bees | +0.032 |
Neg logit contributions | |
pron | -0.048 |
lifetime | -0.041 |
+. | -0.038 |
THE | -0.037 |
"! | -0.036 |
Token | her |
Token ID | 607 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
means | +0.071 |
Bird | +0.069 |
Fle | +0.065 |
calls | +0.062 |
Bee | +0.059 |
Neg logit contributions | |
pron | -0.112 |
lifetime | -0.102 |
ouse | -0.089 |
THE | -0.088 |
pad | -0.087 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
pron | +0.034 |
lifetime | +0.031 |
THE | +0.028 |
pad | +0.028 |
arest | +0.028 |
Neg logit contributions | |
means | -0.020 |
Bird | -0.019 |
Fle | -0.017 |
Bee | -0.017 |
Bunny | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
means | +0.012 |
Bird | +0.011 |
Fle | +0.010 |
Bunny | +0.010 |
calls | +0.010 |
Neg logit contributions | |
pron | -0.023 |
lifetime | -0.022 |
arest | -0.020 |
+. | -0.019 |
ouse | -0.019 |
Token | |
Token ID | 220 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
pron | +0.003 |
lifetime | +0.003 |
+. | +0.002 |
THE | +0.002 |
arest | +0.002 |
Neg logit contributions | |
means | -0.001 |
Bird | -0.001 |
Fle | -0.001 |
Bees | -0.001 |
calls | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
pron | +0.055 |
lifetime | +0.049 |
+. | +0.045 |
THE | +0.044 |
"! | +0.043 |
Neg logit contributions | |
means | -0.032 |
Bird | -0.031 |
Fle | -0.029 |
Cro | -0.027 |
Bees | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
means | +0.016 |
Bird | +0.016 |
Fle | +0.015 |
Cro | +0.013 |
calls | +0.013 |
Neg logit contributions | |
pron | -0.035 |
lifetime | -0.031 |
+. | -0.029 |
THE | -0.028 |
ouse | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
pron | +0.009 |
lifetime | +0.008 |
possession | +0.008 |
ouse | +0.008 |
pad | +0.007 |
Neg logit contributions | |
means | -0.003 |
Bird | -0.003 |
Fle | -0.002 |
Bee | -0.002 |
calls | -0.002 |
Token | They |
Token ID | 2990 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
pron | +0.008 |
possession | +0.007 |
ouse | +0.007 |
lifetime | +0.006 |
urger | +0.006 |
Neg logit contributions | |
means | -0.006 |
Bird | -0.006 |
Be | -0.005 |
Bee | -0.005 |
Ch | -0.005 |
Token | had |
Token ID | 550 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
pron | +0.019 |
lifetime | +0.017 |
+. | +0.016 |
"! | +0.015 |
possession | +0.015 |
Neg logit contributions | |
means | -0.012 |
Bird | -0.012 |
Fle | -0.011 |
Cro | -0.010 |
calls | -0.010 |
Token | lots |
Token ID | 6041 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
pron | +0.088 |
ouse | +0.079 |
lifetime | +0.075 |
arest | +0.074 |
possession | +0.072 |
Neg logit contributions | |
means | -0.038 |
Bird | -0.037 |
Fle | -0.033 |
Cro | -0.032 |
calls | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | -3.12e+00 |
Pos logit contributions | |
pron | +0.112 |
lifetime | +0.100 |
+. | +0.092 |
THE | +0.092 |
ouse | +0.091 |
Neg logit contributions | |
means | -0.053 |
Bird | -0.051 |
Fle | -0.048 |
calls | -0.044 |
Cro | -0.044 |
Token | fun |
Token ID | 1257 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
means | +0.167 |
Bird | +0.161 |
Fle | +0.157 |
calls | +0.154 |
acts | +0.143 |
Neg logit contributions | |
pron | -0.167 |
lifetime | -0.140 |
ouse | -0.132 |
THE | -0.131 |
"! | -0.128 |
Token | playing |
Token ID | 2712 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
means | +0.001 |
Bird | +0.001 |
Fle | +0.001 |
calls | +0.001 |
acts | +0.001 |
Neg logit contributions | |
pron | -0.002 |
lifetime | -0.001 |
ouse | -0.001 |
THE | -0.001 |
+. | -0.001 |
Token | together |
Token ID | 1978 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
pron | +0.003 |
lifetime | +0.002 |
+. | +0.002 |
THE | +0.002 |
ouse | +0.002 |
Neg logit contributions | |
means | -0.002 |
Bird | -0.002 |
Fle | -0.002 |
Bee | -0.002 |
Cro | -0.002 |
Token | until |
Token ID | 1566 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
means | +0.028 |
Bird | +0.025 |
Fle | +0.024 |
calls | +0.021 |
Bee | +0.021 |
Neg logit contributions | |
pron | -0.061 |
lifetime | -0.054 |
ouse | -0.051 |
+. | -0.051 |
arest | -0.049 |
Token | Paul |
Token ID | 3362 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
pron | +0.027 |
ouse | +0.024 |
lifetime | +0.023 |
pad | +0.023 |
+. | +0.021 |
Neg logit contributions | |
means | -0.014 |
Bird | -0.014 |
Fle | -0.013 |
Cro | -0.012 |
Bee | -0.012 |
Token | finger |
Token ID | 7660 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
lifetime | +0.004 |
pron | +0.004 |
THE | +0.004 |
"! | +0.004 |
+. | +0.004 |
Neg logit contributions | |
means | -0.004 |
Bird | -0.004 |
Fle | -0.004 |
calls | -0.004 |
Cro | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
pron | +0.018 |
lifetime | +0.016 |
+. | +0.015 |
THE | +0.015 |
"! | +0.014 |
Neg logit contributions | |
means | -0.012 |
Bird | -0.011 |
Fle | -0.011 |
Cro | -0.010 |
calls | -0.010 |
Token | puts |
Token ID | 7584 |
Feature activation | -7.41e-01 |
Pos logit contributions | |
Bird | +0.012 |
Fle | +0.011 |
means | +0.011 |
Cro | +0.011 |
Bees | +0.010 |
Neg logit contributions | |
pron | -0.017 |
+. | -0.013 |
brand | -0.013 |
lifetime | -0.013 |
helmet | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
means | +0.033 |
Bird | +0.033 |
Fle | +0.031 |
Cro | +0.029 |
calls | +0.029 |
Neg logit contributions | |
pron | -0.044 |
lifetime | -0.040 |
+. | -0.036 |
THE | -0.035 |
ouse | -0.035 |
Token | band |
Token ID | 4097 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Bird | +0.009 |
means | +0.008 |
Fle | +0.008 |
Bee | +0.008 |
calls | +0.008 |
Neg logit contributions | |
lifetime | -0.015 |
THE | -0.014 |
"! | -0.014 |
oor | -0.014 |
pron | -0.013 |
Token | - |
Token ID | 12 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
means | +0.097 |
Bird | +0.096 |
Fle | +0.090 |
calls | +0.085 |
Cro | +0.084 |
Neg logit contributions | |
pron | -0.104 |
lifetime | -0.095 |
+. | -0.082 |
THE | -0.081 |
"! | -0.079 |
Token | aid |
Token ID | 1698 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
means | +0.169 |
Bird | +0.166 |
Fle | +0.159 |
Cro | +0.151 |
calls | +0.149 |
Neg logit contributions | |
pron | -0.173 |
lifetime | -0.149 |
+. | -0.133 |
THE | -0.131 |
ouse | -0.128 |
Token | on |
Token ID | 319 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
means | +0.019 |
Bird | +0.019 |
Fle | +0.018 |
Cro | +0.017 |
calls | +0.017 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.019 |
+. | -0.017 |
THE | -0.017 |
"! | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
pron | +0.040 |
lifetime | +0.037 |
+. | +0.033 |
ouse | +0.032 |
THE | +0.032 |
Neg logit contributions | |
means | -0.027 |
Bird | -0.027 |
Fle | -0.026 |
Cro | -0.024 |
Bee | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
means | +0.025 |
Bird | +0.024 |
Fle | +0.023 |
calls | +0.021 |
Cro | +0.021 |
Neg logit contributions | |
pron | -0.032 |
lifetime | -0.029 |
+. | -0.026 |
THE | -0.025 |
"! | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
means | +0.004 |
Bird | +0.004 |
Fle | +0.003 |
Cro | +0.003 |
Bees | +0.003 |
Neg logit contributions | |
pron | -0.010 |
lifetime | -0.009 |
+. | -0.009 |
THE | -0.009 |
"! | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
pron | +0.003 |
lifetime | +0.002 |
+. | +0.002 |
THE | +0.002 |
ouse | +0.002 |
Neg logit contributions | |
means | -0.002 |
Bird | -0.002 |
Fle | -0.002 |
Cro | -0.002 |
Bees | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
Bird | +0.001 |
means | +0.001 |
Fle | +0.001 |
Bees | +0.001 |
Cro | +0.001 |
Neg logit contributions | |
pron | -0.002 |
lifetime | -0.002 |
brand | -0.001 |
possession | -0.001 |
+. | -0.001 |
Token | moral |
Token ID | 6573 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
means | +0.014 |
Bird | +0.014 |
Fle | +0.013 |
Cro | +0.012 |
calls | +0.012 |
Neg logit contributions | |
pron | -0.022 |
lifetime | -0.019 |
+. | -0.017 |
THE | -0.017 |
"! | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
Bird | +0.082 |
Bee | +0.077 |
means | +0.077 |
Fle | +0.077 |
Cro | +0.074 |
Neg logit contributions | |
pron | -0.083 |
lifetime | -0.075 |
THE | -0.073 |
possession | -0.069 |
+. | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
means | +0.149 |
Bird | +0.144 |
Fle | +0.144 |
Bees | +0.137 |
calls | +0.136 |
Neg logit contributions | |
pron | -0.181 |
THE | -0.152 |
lifetime | -0.148 |
+. | -0.141 |
possession | -0.138 |
Token | story |
Token ID | 1621 |
Feature activation | -3.16e+00 |
Pos logit contributions | |
means | +0.080 |
Bird | +0.074 |
Fle | +0.073 |
Bees | +0.069 |
Cro | +0.069 |
Neg logit contributions | |
pron | -0.062 |
lifetime | -0.052 |
THE | -0.045 |
+. | -0.044 |
reminder | -0.041 |
Token | is |
Token ID | 318 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
Bird | +0.106 |
means | +0.103 |
Fle | +0.098 |
Cro | +0.091 |
Bees | +0.089 |
Neg logit contributions | |
pron | -0.221 |
lifetime | -0.198 |
THE | -0.185 |
+. | -0.184 |
"! | -0.181 |
Token | that |
Token ID | 326 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
means | +0.151 |
Bird | +0.144 |
Fle | +0.144 |
acts | +0.136 |
calls | +0.134 |
Neg logit contributions | |
pron | -0.101 |
lifetime | -0.089 |
THE | -0.086 |
+. | -0.080 |
"! | -0.078 |
Token | sometimes |
Token ID | 3360 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
means | +0.057 |
Bird | +0.057 |
Fle | +0.056 |
Cro | +0.053 |
calls | +0.053 |
Neg logit contributions | |
pron | -0.052 |
lifetime | -0.046 |
THE | -0.042 |
+. | -0.039 |
possession | -0.039 |
Token | we |
Token ID | 356 |
Feature activation | +4.91e-01 |
Pos logit contributions | |
Bird | +0.073 |
Fle | +0.071 |
Cro | +0.070 |
means | +0.070 |
Bee | +0.068 |
Neg logit contributions | |
pron | -0.060 |
lifetime | -0.054 |
+. | -0.048 |
THE | -0.047 |
"! | -0.046 |
Token | need |
Token ID | 761 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
pron | +0.028 |
lifetime | +0.025 |
THE | +0.024 |
+. | +0.023 |
ouse | +0.023 |
Neg logit contributions | |
Bird | -0.021 |
Fle | -0.020 |
means | -0.020 |
Cro | -0.019 |
Bee | -0.019 |
Token | new |
Token ID | 649 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
means | +0.046 |
Bird | +0.042 |
Fle | +0.041 |
calls | +0.039 |
Cro | +0.038 |
Neg logit contributions | |
pron | -0.050 |
lifetime | -0.043 |
THE | -0.037 |
ouse | -0.037 |
pad | -0.037 |
Token | ! |
Token ID | 0 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
means | +0.104 |
Bird | +0.077 |
from | +0.076 |
meant | +0.074 |
Fle | +0.072 |
Neg logit contributions | |
pron | -0.218 |
lifetime | -0.185 |
aults | -0.173 |
arest | -0.172 |
inations | -0.164 |
Token | She |
Token ID | 1375 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
pron | +0.002 |
lifetime | +0.002 |
THE | +0.002 |
"! | +0.002 |
+. | +0.002 |
Neg logit contributions | |
means | -0.001 |
Bird | -0.001 |
Fle | -0.001 |
calls | -0.001 |
Bee | -0.001 |
Token | thought |
Token ID | 1807 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
pron | +0.007 |
lifetime | +0.006 |
+. | +0.005 |
THE | +0.005 |
possession | +0.005 |
Neg logit contributions | |
means | -0.005 |
Bird | -0.005 |
Fle | -0.004 |
Cro | -0.004 |
calls | -0.004 |
Token | av |
Token ID | 1196 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
pron | +0.008 |
lifetime | +0.007 |
+. | +0.006 |
THE | +0.006 |
ouse | +0.006 |
Neg logit contributions | |
means | -0.007 |
Bird | -0.007 |
Fle | -0.007 |
Cro | -0.006 |
calls | -0.006 |
Token | oc |
Token ID | 420 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
Bird | +0.188 |
means | +0.186 |
Fle | +0.179 |
calls | +0.172 |
Cro | +0.172 |
Neg logit contributions | |
pron | -0.216 |
lifetime | -0.190 |
THE | -0.169 |
+. | -0.168 |
"! | -0.166 |
Token | ados |
Token ID | 22484 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
means | +0.198 |
Bird | +0.194 |
calls | +0.191 |
Fle | +0.191 |
Bees | +0.189 |
Neg logit contributions | |
pron | -0.130 |
lifetime | -0.109 |
possession | -0.103 |
"! | -0.102 |
+. | -0.096 |
Token | were |
Token ID | 547 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
means | +0.017 |
Bird | +0.017 |
Fle | +0.016 |
Cro | +0.014 |
calls | +0.014 |
Neg logit contributions | |
pron | -0.031 |
lifetime | -0.028 |
+. | -0.025 |
THE | -0.025 |
"! | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
means | +0.015 |
Bird | +0.015 |
Fle | +0.014 |
Cro | +0.013 |
Bunny | +0.013 |
Neg logit contributions | |
pron | -0.017 |
lifetime | -0.015 |
ouse | -0.013 |
+. | -0.013 |
"! | -0.013 |
Token | most |
Token ID | 749 |
Feature activation | +6.29e-02 |
Pos logit contributions | |
means | +0.003 |
Bird | +0.003 |
Fle | +0.003 |
Cro | +0.002 |
calls | +0.002 |
Neg logit contributions | |
pron | -0.004 |
lifetime | -0.003 |
ouse | -0.003 |
+. | -0.003 |
THE | -0.003 |
Token | interesting |
Token ID | 3499 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
pron | +0.003 |
lifetime | +0.003 |
ouse | +0.002 |
THE | +0.002 |
"! | +0.002 |
Neg logit contributions | |
means | -0.003 |
Bird | -0.003 |
Fle | -0.003 |
meant | -0.003 |
Bees | -0.003 |
Token | him |
Token ID | 683 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
means | +0.109 |
Bird | +0.102 |
Fle | +0.101 |
Cro | +0.094 |
Bees | +0.093 |
Neg logit contributions | |
pron | -0.162 |
lifetime | -0.142 |
THE | -0.130 |
+. | -0.128 |
"! | -0.127 |
Token | ! |
Token ID | 0 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Bird | +0.067 |
means | +0.066 |
Fle | +0.060 |
Bee | +0.057 |
Bunny | +0.057 |
Neg logit contributions | |
pron | -0.107 |
lifetime | -0.092 |
+. | -0.087 |
ouse | -0.082 |
THE | -0.082 |
Token | He |
Token ID | 679 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
pron | +0.030 |
lifetime | +0.027 |
"! | +0.026 |
+. | +0.025 |
pad | +0.025 |
Neg logit contributions | |
means | -0.012 |
Bird | -0.011 |
Fle | -0.010 |
calls | -0.009 |
Cro | -0.009 |
Token | ate |
Token ID | 15063 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
means | +0.020 |
Bird | +0.020 |
Fle | +0.019 |
Cro | +0.018 |
Bees | +0.018 |
Neg logit contributions | |
pron | -0.026 |
lifetime | -0.023 |
+. | -0.020 |
THE | -0.020 |
"! | -0.020 |
Token | all |
Token ID | 477 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
pron | +0.034 |
lifetime | +0.028 |
THE | +0.026 |
+. | +0.025 |
brand | +0.025 |
Neg logit contributions | |
means | -0.031 |
Bird | -0.029 |
Fle | -0.028 |
Bees | -0.027 |
calls | -0.027 |
Token | of |
Token ID | 286 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
means | +0.019 |
Bird | +0.019 |
Fle | +0.018 |
Cro | +0.017 |
calls | +0.016 |
Neg logit contributions | |
pron | -0.030 |
lifetime | -0.026 |
THE | -0.024 |
+. | -0.024 |
"! | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
means | +0.180 |
Fle | +0.162 |
Bird | +0.159 |
calls | +0.157 |
Bees | +0.157 |
Neg logit contributions | |
pron | -0.182 |
lifetime | -0.146 |
THE | -0.137 |
possession | -0.134 |
+. | -0.133 |
Token | food |
Token ID | 2057 |
Feature activation | -7.46e-01 |
Pos logit contributions | |
means | +0.066 |
Bird | +0.064 |
Fle | +0.062 |
Cro | +0.059 |
Bees | +0.058 |
Neg logit contributions | |
pron | -0.070 |
lifetime | -0.061 |
THE | -0.054 |
+. | -0.053 |
"! | -0.052 |
Token | she |
Token ID | 673 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
means | +0.030 |
Bird | +0.030 |
Fle | +0.028 |
Cro | +0.026 |
Bees | +0.026 |
Neg logit contributions | |
pron | -0.048 |
lifetime | -0.042 |
+. | -0.039 |
THE | -0.038 |
"! | -0.037 |
Token | brought |
Token ID | 3181 |
Feature activation | -9.45e-01 |
Pos logit contributions | |
means | +0.006 |
Bird | +0.006 |
Fle | +0.006 |
Cro | +0.006 |
Bees | +0.005 |
Neg logit contributions | |
pron | -0.006 |
lifetime | -0.005 |
+. | -0.005 |
THE | -0.005 |
ouse | -0.005 |
Token | him |
Token ID | 683 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
Bird | +0.039 |
means | +0.038 |
Fle | +0.035 |
Bee | +0.033 |
Bunny | +0.033 |
Neg logit contributions | |
pron | -0.062 |
lifetime | -0.054 |
+. | -0.051 |
THE | -0.049 |
ouse | -0.048 |