Token | said |
Token ID | 531 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
asis | +0.055 |
rig | +0.050 |
place | +0.049 |
row | +0.044 |
eh | +0.042 |
Neg logit contributions | |
ked | -0.059 |
joy | -0.053 |
Ow | -0.052 |
anish | -0.052 |
superstar | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
asis | +0.063 |
place | +0.060 |
old | +0.059 |
row | +0.057 |
rig | +0.057 |
Neg logit contributions | |
ked | -0.103 |
arre | -0.102 |
Ow | -0.100 |
adoes | -0.099 |
anish | -0.099 |
Token | " |
Token ID | 366 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
asis | +0.062 |
rig | +0.062 |
called | +0.059 |
place | +0.057 |
isin | +0.056 |
Neg logit contributions | |
anish | -0.053 |
ked | -0.052 |
tant | -0.052 |
Ow | -0.052 |
anymore | -0.052 |
Token | That |
Token ID | 2504 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
ked | +0.015 |
anish | +0.015 |
Ow | +0.014 |
joy | +0.014 |
anymore | +0.013 |
Neg logit contributions | |
asis | -0.032 |
rig | -0.030 |
place | -0.030 |
row | -0.028 |
eh | -0.028 |
Token | is |
Token ID | 318 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
asis | +0.048 |
rig | +0.048 |
place | +0.046 |
eh | +0.044 |
rim | +0.043 |
Neg logit contributions | |
Ow | -0.027 |
ked | -0.026 |
anish | -0.026 |
anymore | -0.024 |
joy | -0.023 |
Token | called |
Token ID | 1444 |
Feature activation | +7.53e+00 |
Pos logit contributions | |
asis | +0.151 |
rig | +0.145 |
old | +0.141 |
place | +0.139 |
rim | +0.137 |
Neg logit contributions | |
Ow | -0.036 |
anymore | -0.033 |
ked | -0.029 |
adoes | -0.029 |
anish | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
asis | +0.404 |
rig | +0.387 |
place | +0.375 |
row | +0.344 |
old | +0.344 |
Neg logit contributions | |
ked | -0.254 |
Ow | -0.247 |
anish | -0.244 |
anymore | -0.228 |
joy | -0.228 |
Token | stand |
Token ID | 1302 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
rig | +0.090 |
asis | +0.086 |
old | +0.085 |
row | +0.083 |
place | +0.082 |
Neg logit contributions | |
Ow | -0.076 |
joy | -0.075 |
anish | -0.073 |
superstar | -0.073 |
ked | -0.072 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
rig | +0.139 |
asis | +0.137 |
place | +0.132 |
isin | +0.122 |
old | +0.121 |
Neg logit contributions | |
anymore | -0.095 |
ked | -0.095 |
anish | -0.090 |
joy | -0.083 |
adoes | -0.082 |
Token | We |
Token ID | 775 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
asis | +0.086 |
rig | +0.082 |
place | +0.081 |
eh | +0.077 |
row | +0.076 |
Neg logit contributions | |
ked | -0.035 |
anish | -0.033 |
Ow | -0.033 |
joy | -0.030 |
anymore | -0.030 |
Token | need |
Token ID | 761 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
asis | +0.003 |
rig | +0.003 |
place | +0.003 |
row | +0.003 |
eh | +0.003 |
Neg logit contributions | |
ked | -0.002 |
anish | -0.002 |
Ow | -0.002 |
joy | -0.002 |
anymore | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
asis | +0.050 |
rig | +0.049 |
place | +0.047 |
row | +0.043 |
old | +0.043 |
Neg logit contributions | |
ked | -0.042 |
anish | -0.039 |
Ow | -0.038 |
joy | -0.038 |
anymore | -0.038 |
Token | " |
Token ID | 1 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
asis | +0.049 |
rig | +0.047 |
place | +0.046 |
row | +0.041 |
old | +0.041 |
Neg logit contributions | |
ked | -0.053 |
anish | -0.049 |
Ow | -0.049 |
anymore | -0.049 |
joy | -0.049 |
Token | Those |
Token ID | 9627 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
rig | +0.011 |
place | +0.011 |
asis | +0.011 |
isin | +0.010 |
eh | +0.010 |
Neg logit contributions | |
anymore | -0.007 |
ked | -0.007 |
Ow | -0.006 |
adoes | -0.006 |
joy | -0.006 |
Token | cars |
Token ID | 5006 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
asis | +0.135 |
place | +0.134 |
rig | +0.128 |
old | +0.120 |
row | +0.118 |
Neg logit contributions | |
ked | -0.073 |
anish | -0.070 |
joy | -0.069 |
Ow | -0.066 |
anymore | -0.062 |
Token | are |
Token ID | 389 |
Feature activation | +9.29e-01 |
Pos logit contributions | |
asis | +0.128 |
rig | +0.127 |
place | +0.121 |
eh | +0.117 |
row | +0.115 |
Neg logit contributions | |
ked | -0.040 |
anish | -0.037 |
anymore | -0.036 |
Ow | -0.034 |
joy | -0.030 |
Token | called |
Token ID | 1444 |
Feature activation | +7.46e+00 |
Pos logit contributions | |
asis | +0.046 |
rig | +0.043 |
place | +0.041 |
old | +0.039 |
eh | +0.039 |
Neg logit contributions | |
ked | -0.035 |
anymore | -0.034 |
Ow | -0.032 |
adoes | -0.031 |
anish | -0.031 |
Token | traffic |
Token ID | 4979 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
asis | +0.371 |
rig | +0.353 |
place | +0.343 |
row | +0.316 |
eh | +0.314 |
Neg logit contributions | |
ked | -0.280 |
anish | -0.266 |
Ow | -0.260 |
anymore | -0.255 |
joy | -0.254 |
Token | ," |
Token ID | 553 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
asis | +0.217 |
rig | +0.207 |
place | +0.197 |
eh | +0.188 |
row | +0.184 |
Neg logit contributions | |
ked | -0.174 |
anymore | -0.170 |
anish | -0.166 |
Ow | -0.159 |
adoes | -0.156 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ked | +0.008 |
anish | +0.008 |
Ow | +0.007 |
joy | +0.007 |
anymore | +0.007 |
Neg logit contributions | |
asis | -0.007 |
rig | -0.007 |
place | -0.006 |
old | -0.006 |
row | -0.006 |
Token | my |
Token ID | 1820 |
Feature activation | -5.07e-02 |
Pos logit contributions | |
asis | +0.077 |
place | +0.073 |
rig | +0.070 |
ands | +0.063 |
fire | +0.063 |
Neg logit contributions | |
ked | -0.046 |
anish | -0.041 |
anymore | -0.039 |
joy | -0.038 |
Ow | -0.038 |
Token | said |
Token ID | 531 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
ked | +0.002 |
anish | +0.002 |
joy | +0.002 |
anymore | +0.002 |
again | +0.002 |
Neg logit contributions | |
asis | -0.003 |
place | -0.002 |
rig | -0.002 |
ands | -0.002 |
eh | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.12e-03 |
Pos logit contributions | |
ked | +0.011 |
anish | +0.010 |
Ow | +0.010 |
joy | +0.010 |
anymore | +0.010 |
Neg logit contributions | |
asis | -0.016 |
rig | -0.016 |
place | -0.015 |
row | -0.014 |
eh | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
asis | +0.000 |
place | +0.000 |
rig | +0.000 |
row | +0.000 |
stump | +0.000 |
Neg logit contributions | |
Ow | -0.000 |
anish | -0.000 |
ked | -0.000 |
joy | -0.000 |
Look | -0.000 |
Token | " |
Token ID | 1 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
asis | +0.013 |
rig | +0.012 |
place | +0.012 |
row | +0.011 |
stump | +0.011 |
Neg logit contributions | |
anish | -0.010 |
ked | -0.010 |
Ow | -0.010 |
arre | -0.009 |
joy | -0.009 |
Token | That |
Token ID | 2504 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
ked | +0.010 |
anish | +0.010 |
anymore | +0.009 |
Ow | +0.009 |
joy | +0.009 |
Neg logit contributions | |
asis | -0.016 |
rig | -0.016 |
place | -0.015 |
row | -0.014 |
eh | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
asis | +0.034 |
rig | +0.033 |
place | +0.032 |
eh | +0.029 |
old | +0.029 |
Neg logit contributions | |
ked | -0.019 |
anish | -0.019 |
Ow | -0.019 |
anymore | -0.017 |
adoes | -0.017 |
Token | called |
Token ID | 1444 |
Feature activation | +7.19e+00 |
Pos logit contributions | |
asis | +0.106 |
rig | +0.099 |
place | +0.096 |
old | +0.095 |
row | +0.094 |
Neg logit contributions | |
Ow | -0.042 |
anymore | -0.042 |
ked | -0.039 |
anish | -0.039 |
adoes | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
asis | +0.368 |
rig | +0.345 |
place | +0.338 |
row | +0.308 |
eh | +0.306 |
Neg logit contributions | |
ked | -0.264 |
Ow | -0.255 |
anish | -0.254 |
anymore | -0.242 |
joy | -0.237 |
Token | cell |
Token ID | 2685 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
rig | +0.073 |
asis | +0.072 |
place | +0.067 |
old | +0.066 |
aling | +0.063 |
Neg logit contributions | |
anish | -0.069 |
Ow | -0.069 |
ked | -0.068 |
superstar | -0.067 |
joy | -0.066 |
Token | ," |
Token ID | 553 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
asis | +0.091 |
rig | +0.090 |
place | +0.086 |
eh | +0.077 |
old | +0.077 |
Neg logit contributions | |
ked | -0.080 |
anish | -0.076 |
anymore | -0.074 |
Ow | -0.073 |
joy | -0.071 |
Token | his |
Token ID | 465 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ked | +0.037 |
anish | +0.035 |
Ow | +0.035 |
joy | +0.034 |
anymore | +0.033 |
Neg logit contributions | |
asis | -0.043 |
rig | -0.041 |
place | -0.039 |
row | -0.035 |
eh | -0.035 |
Token | mum |
Token ID | 25682 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
joy | +0.049 |
ked | +0.047 |
Ow | +0.046 |
eyes | +0.046 |
anish | +0.045 |
Neg logit contributions | |
asis | -0.067 |
rig | -0.062 |
place | -0.062 |
aling | -0.059 |
isin | -0.057 |
Token | said |
Token ID | 531 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
asis | +0.009 |
rig | +0.009 |
place | +0.008 |
row | +0.008 |
eh | +0.007 |
Neg logit contributions | |
ked | -0.009 |
anish | -0.008 |
Ow | -0.008 |
joy | -0.008 |
anymore | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +5.80e-01 |
Pos logit contributions | |
asis | +0.047 |
rig | +0.045 |
place | +0.044 |
row | +0.042 |
old | +0.041 |
Neg logit contributions | |
ked | -0.045 |
Ow | -0.044 |
anish | -0.044 |
joy | -0.042 |
adoes | -0.042 |
Token | " |
Token ID | 366 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
asis | +0.037 |
rig | +0.035 |
place | +0.035 |
row | +0.032 |
eh | +0.032 |
Neg logit contributions | |
ked | -0.014 |
anish | -0.013 |
joy | -0.013 |
Ow | -0.013 |
anymore | -0.012 |
Token | It |
Token ID | 1026 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
ked | +0.036 |
anish | +0.034 |
Ow | +0.033 |
joy | +0.032 |
anymore | +0.031 |
Neg logit contributions | |
asis | -0.071 |
rig | -0.068 |
place | -0.067 |
row | -0.062 |
eh | -0.062 |
Token | is |
Token ID | 318 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
asis | +0.089 |
rig | +0.086 |
place | +0.084 |
eh | +0.078 |
row | +0.077 |
Neg logit contributions | |
ked | -0.049 |
anish | -0.049 |
Ow | -0.048 |
anymore | -0.045 |
adoes | -0.044 |
Token | called |
Token ID | 1444 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
asis | +0.088 |
rig | +0.084 |
place | +0.081 |
old | +0.079 |
row | +0.077 |
Neg logit contributions | |
Ow | -0.043 |
anymore | -0.042 |
anish | -0.041 |
ked | -0.040 |
joy | -0.039 |
Token | jelly |
Token ID | 27644 |
Feature activation | +3.08e+00 |
Pos logit contributions | |
asis | +0.366 |
rig | +0.348 |
place | +0.337 |
row | +0.309 |
old | +0.308 |
Neg logit contributions | |
ked | -0.260 |
anish | -0.251 |
Ow | -0.250 |
anymore | -0.235 |
joy | -0.234 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
rig | +0.144 |
asis | +0.139 |
place | +0.134 |
old | +0.133 |
aling | +0.124 |
Neg logit contributions | |
anymore | -0.113 |
ked | -0.113 |
anish | -0.113 |
Ow | -0.106 |
guys | -0.100 |
Token | Would |
Token ID | 10928 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
asis | +0.086 |
rig | +0.081 |
place | +0.081 |
eh | +0.077 |
row | +0.075 |
Neg logit contributions | |
ked | -0.035 |
Ow | -0.034 |
anish | -0.034 |
anymore | -0.030 |
joy | -0.030 |
Token | you |
Token ID | 345 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
anish | +0.008 |
anymore | +0.008 |
Ow | +0.008 |
ked | +0.007 |
joy | +0.007 |
Neg logit contributions | |
asis | -0.009 |
rig | -0.009 |
row | -0.008 |
place | -0.008 |
eh | -0.007 |
Token | like |
Token ID | 588 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
asis | +0.105 |
rig | +0.099 |
place | +0.093 |
rim | +0.090 |
eh | +0.089 |
Neg logit contributions | |
ked | -0.049 |
anymore | -0.048 |
Ow | -0.046 |
anish | -0.046 |
joy | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
asis | +0.008 |
place | +0.008 |
rig | +0.007 |
row | +0.007 |
eh | +0.007 |
Neg logit contributions | |
Ow | -0.004 |
anish | -0.004 |
ked | -0.004 |
joy | -0.004 |
arre | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
asis | +0.018 |
rig | +0.017 |
place | +0.017 |
row | +0.015 |
stump | +0.015 |
Neg logit contributions | |
anish | -0.011 |
Ow | -0.010 |
arre | -0.010 |
ked | -0.010 |
joy | -0.009 |
Token | That |
Token ID | 2504 |
Feature activation | +5.65e-01 |
Pos logit contributions | |
ked | +0.006 |
anish | +0.006 |
Ow | +0.006 |
joy | +0.006 |
anymore | +0.006 |
Neg logit contributions | |
asis | -0.010 |
rig | -0.010 |
place | -0.010 |
row | -0.009 |
eh | -0.009 |
Token | pepper |
Token ID | 13385 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
asis | +0.026 |
rig | +0.025 |
place | +0.024 |
row | +0.022 |
eh | +0.022 |
Neg logit contributions | |
ked | -0.023 |
anish | -0.022 |
Ow | -0.022 |
joy | -0.022 |
anymore | -0.021 |
Token | is |
Token ID | 318 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
rig | +0.072 |
asis | +0.071 |
place | +0.067 |
old | +0.064 |
aling | +0.063 |
Neg logit contributions | |
anish | -0.044 |
anymore | -0.041 |
ked | -0.040 |
Ow | -0.040 |
adoes | -0.038 |
Token | called |
Token ID | 1444 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
asis | +0.082 |
rig | +0.075 |
place | +0.072 |
old | +0.072 |
row | +0.068 |
Neg logit contributions | |
anymore | -0.050 |
Ow | -0.048 |
ked | -0.048 |
anish | -0.047 |
adoes | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
asis | +0.339 |
rig | +0.319 |
place | +0.306 |
old | +0.283 |
eh | +0.280 |
Neg logit contributions | |
ked | -0.289 |
Ow | -0.287 |
anish | -0.278 |
anymore | -0.267 |
joy | -0.254 |
Token | jumping |
Token ID | 14284 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
asis | +0.063 |
rig | +0.061 |
place | +0.058 |
old | +0.054 |
row | +0.054 |
Neg logit contributions | |
anish | -0.071 |
ked | -0.070 |
Ow | -0.070 |
joy | -0.068 |
anymore | -0.068 |
Token | pepper |
Token ID | 13385 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
asis | +0.032 |
rig | +0.031 |
place | +0.030 |
old | +0.027 |
row | +0.027 |
Neg logit contributions | |
ked | -0.031 |
anish | -0.030 |
Ow | -0.029 |
anymore | -0.029 |
joy | -0.029 |
Token | ," |
Token ID | 553 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
ked | +0.005 |
anish | +0.005 |
anymore | +0.005 |
Ow | +0.005 |
adoes | +0.004 |
Neg logit contributions | |
rig | -0.006 |
asis | -0.006 |
place | -0.006 |
old | -0.006 |
isin | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
ked | +0.035 |
anish | +0.034 |
Ow | +0.034 |
joy | +0.033 |
anymore | +0.033 |
Neg logit contributions | |
asis | -0.035 |
rig | -0.033 |
place | -0.032 |
row | -0.029 |
eh | -0.029 |
Token | said |
Token ID | 531 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
ked | +0.016 |
anish | +0.015 |
anymore | +0.014 |
joy | +0.014 |
Ow | +0.014 |
Neg logit contributions | |
asis | -0.015 |
rig | -0.014 |
place | -0.014 |
eh | -0.012 |
row | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
asis | +0.073 |
place | +0.072 |
rig | +0.069 |
old | +0.067 |
isin | +0.066 |
Neg logit contributions | |
Ow | -0.089 |
ked | -0.089 |
anish | -0.087 |
adoes | -0.083 |
joy | -0.083 |
Token | " |
Token ID | 366 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
rig | +0.050 |
asis | +0.050 |
place | +0.047 |
called | +0.045 |
old | +0.045 |
Neg logit contributions | |
ked | -0.035 |
anish | -0.034 |
Ow | -0.033 |
anymore | -0.031 |
joy | -0.031 |
Token | These |
Token ID | 4711 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
ked | +0.045 |
anymore | +0.043 |
anish | +0.041 |
adoes | +0.041 |
joy | +0.041 |
Neg logit contributions | |
rig | -0.053 |
asis | -0.052 |
place | -0.051 |
isin | -0.046 |
old | -0.046 |
Token | are |
Token ID | 389 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
place | +0.035 |
asis | +0.035 |
rig | +0.034 |
old | +0.031 |
isin | +0.031 |
Neg logit contributions | |
ked | -0.027 |
joy | -0.025 |
Ow | -0.025 |
anish | -0.024 |
anymore | -0.023 |
Token | called |
Token ID | 1444 |
Feature activation | +7.10e+00 |
Pos logit contributions | |
asis | +0.019 |
rig | +0.018 |
place | +0.017 |
row | +0.016 |
eh | +0.016 |
Neg logit contributions | |
ked | -0.013 |
anish | -0.012 |
anymore | -0.012 |
Ow | -0.012 |
joy | -0.012 |
Token | notes |
Token ID | 4710 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
asis | +0.337 |
rig | +0.331 |
place | +0.323 |
row | +0.293 |
old | +0.291 |
Neg logit contributions | |
ked | -0.269 |
anish | -0.259 |
Ow | -0.253 |
joy | -0.252 |
anymore | -0.245 |
Token | , |
Token ID | 11 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
asis | +0.078 |
rig | +0.075 |
place | +0.073 |
row | +0.067 |
old | +0.066 |
Neg logit contributions | |
ked | -0.061 |
anish | -0.059 |
Ow | -0.057 |
joy | -0.057 |
anymore | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
rig | +0.028 |
asis | +0.027 |
place | +0.027 |
isin | +0.024 |
old | +0.024 |
Neg logit contributions | |
ked | -0.028 |
anish | -0.026 |
joy | -0.026 |
Ow | -0.026 |
anymore | -0.024 |
Token | they |
Token ID | 484 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
asis | +0.001 |
rig | +0.001 |
place | +0.001 |
old | +0.001 |
row | +0.001 |
Neg logit contributions | |
ked | -0.001 |
anish | -0.001 |
Ow | -0.001 |
joy | -0.001 |
anymore | -0.001 |
Token | are |
Token ID | 389 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
ked | +0.035 |
anish | +0.033 |
Ow | +0.032 |
joy | +0.032 |
anymore | +0.031 |
Neg logit contributions | |
asis | -0.062 |
rig | -0.059 |
place | -0.058 |
row | -0.054 |
eh | -0.053 |
Token | said |
Token ID | 531 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
asis | +0.037 |
rig | +0.035 |
place | +0.034 |
row | +0.030 |
eh | +0.030 |
Neg logit contributions | |
ked | -0.045 |
anish | -0.042 |
joy | -0.041 |
Ow | -0.041 |
anymore | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +9.44e-01 |
Pos logit contributions | |
asis | +0.049 |
place | +0.047 |
old | +0.046 |
rig | +0.045 |
row | +0.045 |
Neg logit contributions | |
Ow | -0.069 |
ked | -0.068 |
anish | -0.066 |
arre | -0.065 |
joy | -0.064 |
Token | " |
Token ID | 366 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
asis | +0.052 |
rig | +0.051 |
place | +0.049 |
row | +0.046 |
eh | +0.046 |
Neg logit contributions | |
ked | -0.028 |
anish | -0.027 |
Ow | -0.026 |
anymore | -0.026 |
joy | -0.025 |
Token | This |
Token ID | 1212 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
ked | +0.037 |
anish | +0.036 |
joy | +0.035 |
Ow | +0.034 |
superstar | +0.032 |
Neg logit contributions | |
asis | -0.059 |
rig | -0.055 |
place | -0.053 |
row | -0.050 |
eh | -0.050 |
Token | is |
Token ID | 318 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
asis | +0.087 |
rig | +0.086 |
place | +0.082 |
eh | +0.078 |
row | +0.077 |
Neg logit contributions | |
anish | -0.039 |
Ow | -0.036 |
ked | -0.036 |
anymore | -0.035 |
joy | -0.034 |
Token | called |
Token ID | 1444 |
Feature activation | +7.06e+00 |
Pos logit contributions | |
asis | +0.091 |
rig | +0.081 |
place | +0.079 |
rim | +0.079 |
row | +0.078 |
Neg logit contributions | |
anymore | -0.032 |
Ow | -0.031 |
anish | -0.030 |
ked | -0.030 |
joy | -0.029 |
Token | striking |
Token ID | 8871 |
Feature activation | +7.24e-01 |
Pos logit contributions | |
asis | +0.359 |
rig | +0.335 |
place | +0.326 |
eh | +0.300 |
row | +0.299 |
Neg logit contributions | |
ked | -0.262 |
anish | -0.254 |
Ow | -0.250 |
anymore | -0.237 |
joy | -0.236 |
Token | . |
Token ID | 13 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
asis | +0.035 |
rig | +0.032 |
place | +0.031 |
row | +0.029 |
eh | +0.029 |
Neg logit contributions | |
ked | -0.028 |
anish | -0.028 |
Ow | -0.027 |
anymore | -0.027 |
joy | -0.026 |
Token | Watch |
Token ID | 6305 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
asis | +0.078 |
rig | +0.073 |
place | +0.073 |
eh | +0.068 |
row | +0.067 |
Neg logit contributions | |
ked | -0.043 |
anish | -0.042 |
Ow | -0.041 |
joy | -0.039 |
anymore | -0.038 |
Token | what |
Token ID | 644 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
asis | +0.015 |
rig | +0.014 |
place | +0.013 |
eh | +0.012 |
row | +0.012 |
Neg logit contributions | |
ked | -0.015 |
anish | -0.015 |
Ow | -0.015 |
anymore | -0.015 |
adoes | -0.014 |
Token | I |
Token ID | 314 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
ked | +0.065 |
anish | +0.061 |
joy | +0.060 |
Ow | +0.060 |
anymore | +0.058 |
Neg logit contributions | |
asis | -0.067 |
rig | -0.064 |
place | -0.064 |
old | -0.057 |
row | -0.057 |
Token | says |
Token ID | 1139 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
asis | +0.065 |
rig | +0.063 |
place | +0.059 |
old | +0.053 |
row | +0.053 |
Neg logit contributions | |
ked | -0.084 |
anish | -0.081 |
Ow | -0.079 |
joy | -0.079 |
anymore | -0.077 |
Token | , |
Token ID | 11 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
asis | +0.046 |
place | +0.045 |
ion | +0.044 |
called | +0.042 |
old | +0.041 |
Neg logit contributions | |
tant | -0.109 |
ked | -0.107 |
Ow | -0.107 |
ifying | -0.107 |
arre | -0.106 |
Token | " |
Token ID | 366 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
asis | +0.022 |
called | +0.021 |
rig | +0.020 |
eh | +0.020 |
isin | +0.019 |
Neg logit contributions | |
tant | -0.021 |
anish | -0.021 |
Ow | -0.021 |
anymore | -0.021 |
ked | -0.020 |
Token | They |
Token ID | 2990 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
ked | +0.038 |
anish | +0.037 |
Ow | +0.037 |
joy | +0.034 |
anymore | +0.033 |
Neg logit contributions | |
asis | -0.065 |
rig | -0.062 |
place | -0.060 |
row | -0.058 |
old | -0.056 |
Token | are |
Token ID | 389 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
asis | +0.122 |
rig | +0.121 |
place | +0.114 |
eh | +0.110 |
row | +0.108 |
Neg logit contributions | |
ked | -0.055 |
anish | -0.053 |
anymore | -0.052 |
Ow | -0.051 |
joy | -0.045 |
Token | called |
Token ID | 1444 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
asis | +0.015 |
rig | +0.014 |
place | +0.013 |
row | +0.013 |
old | +0.013 |
Neg logit contributions | |
anymore | -0.009 |
ked | -0.009 |
Ow | -0.008 |
joy | -0.008 |
adoes | -0.008 |
Token | seasons |
Token ID | 7028 |
Feature activation | +5.71e+00 |
Pos logit contributions | |
asis | +0.336 |
rig | +0.321 |
place | +0.311 |
row | +0.286 |
eh | +0.283 |
Neg logit contributions | |
ked | -0.275 |
anish | -0.264 |
Ow | -0.259 |
joy | -0.252 |
anymore | -0.252 |
Token | . |
Token ID | 13 |
Feature activation | +8.11e-01 |
Pos logit contributions | |
asis | +0.323 |
rig | +0.311 |
place | +0.304 |
eh | +0.294 |
old | +0.290 |
Neg logit contributions | |
anymore | -0.166 |
ked | -0.161 |
anish | -0.153 |
Ow | -0.145 |
adoes | -0.141 |
Token | And |
Token ID | 843 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
asis | +0.052 |
rig | +0.050 |
place | +0.049 |
eh | +0.047 |
row | +0.047 |
Neg logit contributions | |
Ow | -0.018 |
ked | -0.018 |
anish | -0.017 |
anymore | -0.016 |
joy | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
ked | +0.002 |
anymore | +0.002 |
Ow | +0.002 |
anish | +0.002 |
adoes | +0.002 |
Neg logit contributions | |
asis | -0.003 |
rig | -0.003 |
eh | -0.003 |
place | -0.003 |
old | -0.003 |
Token | happen |
Token ID | 1645 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ked | +0.013 |
anymore | +0.013 |
anish | +0.012 |
Ow | +0.012 |
arre | +0.011 |
Neg logit contributions | |
rig | -0.035 |
asis | -0.034 |
eh | -0.032 |
place | -0.032 |
row | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +9.33e-01 |
Pos logit contributions | |
asis | +0.062 |
place | +0.058 |
rig | +0.057 |
row | +0.055 |
old | +0.054 |
Neg logit contributions | |
ked | -0.071 |
Ow | -0.071 |
arre | -0.069 |
anish | -0.068 |
tant | -0.068 |
Token | " |
Token ID | 366 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
asis | +0.052 |
rig | +0.051 |
place | +0.048 |
row | +0.046 |
eh | +0.045 |
Neg logit contributions | |
ked | -0.027 |
anish | -0.027 |
Ow | -0.026 |
anymore | -0.026 |
joy | -0.025 |
Token | This |
Token ID | 1212 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
ked | +0.030 |
anish | +0.028 |
Ow | +0.027 |
joy | +0.026 |
anymore | +0.024 |
Neg logit contributions | |
asis | -0.062 |
rig | -0.060 |
place | -0.059 |
row | -0.055 |
eh | -0.055 |
Token | lake |
Token ID | 13546 |
Feature activation | +3.96e+00 |
Pos logit contributions | |
rig | +0.084 |
asis | +0.083 |
place | +0.080 |
old | +0.077 |
eh | +0.076 |
Neg logit contributions | |
anish | -0.047 |
ked | -0.046 |
Ow | -0.046 |
anymore | -0.045 |
joy | -0.043 |
Token | is |
Token ID | 318 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
rig | +0.239 |
asis | +0.238 |
eh | +0.230 |
place | +0.228 |
old | +0.221 |
Neg logit contributions | |
ked | -0.086 |
anymore | -0.086 |
anish | -0.085 |
Ow | -0.076 |
adoes | -0.074 |
Token | called |
Token ID | 1444 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
asis | +0.090 |
rig | +0.086 |
old | +0.084 |
place | +0.082 |
isin | +0.079 |
Neg logit contributions | |
anymore | -0.049 |
ked | -0.045 |
Ow | -0.045 |
joy | -0.043 |
ifying | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
asis | +0.372 |
rig | +0.354 |
place | +0.341 |
eh | +0.325 |
old | +0.323 |
Neg logit contributions | |
ked | -0.246 |
Ow | -0.235 |
anish | -0.228 |
anymore | -0.219 |
joy | -0.215 |
Token | Bright |
Token ID | 17558 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
asis | +0.153 |
rig | +0.148 |
place | +0.141 |
row | +0.129 |
old | +0.129 |
Neg logit contributions | |
ked | -0.159 |
anish | -0.153 |
Ow | -0.151 |
joy | -0.148 |
anymore | -0.148 |
Token | Blue |
Token ID | 4518 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
asis | +0.147 |
rig | +0.143 |
place | +0.138 |
eh | +0.131 |
old | +0.129 |
Neg logit contributions | |
ked | -0.121 |
anymore | -0.114 |
anish | -0.114 |
Ow | -0.114 |
joy | -0.108 |
Token | Eye |
Token ID | 14144 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
ked | +0.016 |
anish | +0.016 |
Ow | +0.015 |
joy | +0.015 |
anymore | +0.015 |
Neg logit contributions | |
asis | -0.021 |
rig | -0.021 |
place | -0.020 |
row | -0.018 |
eh | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
asis | +0.145 |
rig | +0.141 |
place | +0.135 |
eh | +0.128 |
isin | +0.128 |
Neg logit contributions | |
ked | -0.094 |
anymore | -0.093 |
anish | -0.089 |
Ow | -0.084 |
joy | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | +9.62e-01 |
Pos logit contributions | |
ked | +0.020 |
Ow | +0.019 |
anish | +0.019 |
anymore | +0.018 |
joy | +0.018 |
Neg logit contributions | |
asis | -0.030 |
rig | -0.028 |
place | -0.028 |
row | -0.026 |
eh | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
asis | +0.046 |
rig | +0.044 |
place | +0.043 |
row | +0.039 |
eh | +0.038 |
Neg logit contributions | |
ked | -0.037 |
anish | -0.037 |
Ow | -0.036 |
joy | -0.035 |
anymore | -0.034 |
Token | " |
Token ID | 1 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
asis | +0.048 |
rig | +0.045 |
place | +0.044 |
row | +0.040 |
eh | +0.039 |
Neg logit contributions | |
ked | -0.047 |
anish | -0.046 |
Ow | -0.045 |
joy | -0.044 |
anymore | -0.043 |
Token | That |
Token ID | 2504 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
asis | +0.017 |
rig | +0.017 |
place | +0.016 |
row | +0.015 |
eh | +0.015 |
Neg logit contributions | |
ked | -0.010 |
anish | -0.009 |
Ow | -0.009 |
joy | -0.009 |
anymore | -0.009 |
Token | 's |
Token ID | 338 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
asis | +0.055 |
rig | +0.053 |
place | +0.052 |
row | +0.048 |
eh | +0.047 |
Neg logit contributions | |
ked | -0.037 |
anish | -0.035 |
Ow | -0.034 |
joy | -0.034 |
anymore | -0.033 |
Token | called |
Token ID | 1444 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
asis | +0.119 |
rig | +0.111 |
place | +0.110 |
old | +0.107 |
row | +0.105 |
Neg logit contributions | |
Ow | -0.047 |
anymore | -0.044 |
anish | -0.043 |
ked | -0.043 |
adoes | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +4.30e+00 |
Pos logit contributions | |
asis | +0.335 |
rig | +0.329 |
place | +0.319 |
row | +0.294 |
eh | +0.288 |
Neg logit contributions | |
ked | -0.266 |
anish | -0.253 |
joy | -0.249 |
Ow | -0.243 |
anymore | -0.241 |
Token | clouds |
Token ID | 15114 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
asis | +0.205 |
rig | +0.197 |
place | +0.189 |
old | +0.175 |
row | +0.173 |
Neg logit contributions | |
ked | -0.169 |
anish | -0.165 |
Ow | -0.161 |
joy | -0.157 |
anymore | -0.157 |
Token | , |
Token ID | 11 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
asis | +0.201 |
rig | +0.195 |
place | +0.187 |
eh | +0.174 |
row | +0.169 |
Neg logit contributions | |
ked | -0.169 |
anymore | -0.163 |
anish | -0.161 |
Ow | -0.156 |
adoes | -0.148 |
Token | John |
Token ID | 1757 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
asis | +0.053 |
rig | +0.051 |
place | +0.050 |
old | +0.045 |
isin | +0.045 |
Neg logit contributions | |
ked | -0.040 |
anish | -0.038 |
joy | -0.037 |
Ow | -0.035 |
anymore | -0.035 |
Token | ," |
Token ID | 553 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
asis | +0.001 |
rig | +0.001 |
place | +0.001 |
eh | +0.001 |
isin | +0.001 |
Neg logit contributions | |
ked | -0.001 |
anymore | -0.001 |
Ow | -0.001 |
anish | -0.001 |
joy | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ked | +0.007 |
anish | +0.006 |
joy | +0.006 |
arre | +0.006 |
anymore | +0.006 |
Neg logit contributions | |
asis | -0.008 |
place | -0.007 |
rig | -0.007 |
row | -0.007 |
aster | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
ked | +0.031 |
anymore | +0.030 |
anish | +0.027 |
Ow | +0.026 |
again | +0.026 |
Neg logit contributions | |
asis | -0.059 |
rig | -0.057 |
place | -0.055 |
rim | -0.052 |
old | -0.052 |
Token | " |
Token ID | 366 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
ked | +0.005 |
Ow | +0.004 |
anish | +0.004 |
anymore | +0.004 |
joy | +0.004 |
Neg logit contributions | |
asis | -0.011 |
rig | -0.010 |
place | -0.010 |
row | -0.010 |
isin | -0.009 |
Token | This |
Token ID | 1212 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
ked | +0.088 |
anymore | +0.082 |
anish | +0.081 |
joy | +0.080 |
Ow | +0.079 |
Neg logit contributions | |
asis | -0.118 |
rig | -0.112 |
place | -0.112 |
eh | -0.104 |
row | -0.101 |
Token | is |
Token ID | 318 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
asis | +0.051 |
place | +0.046 |
rig | +0.046 |
eh | +0.043 |
row | +0.042 |
Neg logit contributions | |
ked | -0.044 |
joy | -0.038 |
anish | -0.038 |
Ow | -0.036 |
anymore | -0.036 |
Token | called |
Token ID | 1444 |
Feature activation | +7.01e+00 |
Pos logit contributions | |
asis | +0.065 |
rig | +0.061 |
old | +0.059 |
place | +0.059 |
row | +0.057 |
Neg logit contributions | |
Ow | -0.032 |
anymore | -0.031 |
anish | -0.028 |
ked | -0.028 |
adoes | -0.026 |
Token | flour |
Token ID | 10601 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
asis | +0.372 |
rig | +0.354 |
place | +0.345 |
old | +0.317 |
row | +0.316 |
Neg logit contributions | |
ked | -0.242 |
anish | -0.232 |
Ow | -0.231 |
anymore | -0.218 |
joy | -0.216 |
Token | ," |
Token ID | 553 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
rig | +0.208 |
asis | +0.207 |
place | +0.199 |
old | +0.185 |
eh | +0.183 |
Neg logit contributions | |
ked | -0.139 |
anymore | -0.135 |
anish | -0.133 |
Ow | -0.132 |
adoes | -0.120 |
Token | she |
Token ID | 673 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
asis | +0.008 |
rig | +0.008 |
place | +0.008 |
row | +0.007 |
aling | +0.007 |
Neg logit contributions | |
ked | -0.005 |
Ow | -0.005 |
anish | -0.005 |
adoes | -0.005 |
Wow | -0.005 |
Token | told |
Token ID | 1297 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
asis | +0.040 |
place | +0.037 |
rig | +0.035 |
row | +0.031 |
rim | +0.030 |
Neg logit contributions | |
ked | -0.034 |
Ow | -0.031 |
anish | -0.031 |
superstar | -0.029 |
arre | -0.028 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
asis | +0.019 |
rig | +0.018 |
place | +0.018 |
row | +0.017 |
eh | +0.017 |
Neg logit contributions | |
ked | -0.010 |
anish | -0.010 |
joy | -0.009 |
Ow | -0.009 |
anymore | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
asis | +0.102 |
rig | +0.100 |
place | +0.097 |
eh | +0.089 |
row | +0.087 |
Neg logit contributions | |
ked | -0.062 |
anish | -0.058 |
anymore | -0.057 |
Ow | -0.057 |
joy | -0.056 |
Token | this |
Token ID | 428 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
asis | +0.031 |
rig | +0.029 |
place | +0.029 |
row | +0.026 |
old | +0.025 |
Neg logit contributions | |
ked | -0.030 |
anish | -0.029 |
Ow | -0.028 |
joy | -0.028 |
anymore | -0.028 |
Token | little |
Token ID | 1310 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
asis | +0.033 |
rig | +0.032 |
place | +0.031 |
old | +0.028 |
row | +0.028 |
Neg logit contributions | |
ked | -0.022 |
anish | -0.022 |
Ow | -0.022 |
joy | -0.021 |
anymore | -0.021 |
Token | thing |
Token ID | 1517 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
asis | +0.051 |
rig | +0.049 |
place | +0.047 |
row | +0.042 |
eh | +0.042 |
Neg logit contributions | |
ked | -0.051 |
anish | -0.049 |
Ow | -0.048 |
joy | -0.047 |
anymore | -0.047 |
Token | is |
Token ID | 318 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
ked | +0.041 |
anish | +0.039 |
Ow | +0.038 |
anymore | +0.037 |
joy | +0.036 |
Neg logit contributions | |
asis | -0.077 |
rig | -0.074 |
place | -0.072 |
row | -0.067 |
eh | -0.067 |
Token | called |
Token ID | 1444 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
asis | +0.070 |
rig | +0.067 |
place | +0.064 |
old | +0.062 |
isin | +0.061 |
Neg logit contributions | |
anymore | -0.032 |
ked | -0.031 |
Ow | -0.031 |
anish | -0.030 |
adoes | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
asis | +0.369 |
rig | +0.351 |
place | +0.340 |
old | +0.314 |
row | +0.312 |
Neg logit contributions | |
ked | -0.242 |
anish | -0.233 |
Ow | -0.232 |
anymore | -0.220 |
joy | -0.217 |
Token | mole |
Token ID | 9411 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
asis | +0.062 |
rig | +0.060 |
place | +0.058 |
row | +0.052 |
old | +0.052 |
Neg logit contributions | |
ked | -0.067 |
anish | -0.066 |
Ow | -0.065 |
joy | -0.064 |
anymore | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +9.96e-01 |
Pos logit contributions | |
asis | +0.055 |
rig | +0.054 |
place | +0.052 |
isin | +0.047 |
old | +0.047 |
Neg logit contributions | |
ked | -0.043 |
anymore | -0.041 |
anish | -0.040 |
Ow | -0.040 |
joy | -0.038 |
Token | He |
Token ID | 679 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
asis | +0.065 |
rig | +0.062 |
place | +0.061 |
eh | +0.058 |
row | +0.057 |
Neg logit contributions | |
ked | -0.023 |
Ow | -0.022 |
anish | -0.022 |
joy | -0.019 |
anymore | -0.019 |
Token | is |
Token ID | 318 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
asis | +0.048 |
rig | +0.047 |
place | +0.045 |
eh | +0.042 |
row | +0.042 |
Neg logit contributions | |
ked | -0.026 |
Ow | -0.024 |
anish | -0.023 |
anymore | -0.022 |
joy | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
ked | +0.028 |
anish | +0.027 |
Ow | +0.026 |
joy | +0.026 |
anymore | +0.025 |
Neg logit contributions | |
asis | -0.036 |
rig | -0.035 |
place | -0.033 |
row | -0.031 |
old | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
asis | +0.017 |
rig | +0.016 |
place | +0.016 |
row | +0.015 |
eh | +0.014 |
Neg logit contributions | |
Ow | -0.009 |
anish | -0.008 |
ked | -0.008 |
joy | -0.008 |
anymore | -0.008 |
Token | " |
Token ID | 1 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
asis | +0.020 |
rig | +0.019 |
place | +0.019 |
row | +0.017 |
isin | +0.016 |
Neg logit contributions | |
anish | -0.014 |
ked | -0.013 |
Ow | -0.012 |
joy | -0.012 |
Look | -0.012 |
Token | It |
Token ID | 1026 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ked | +0.005 |
joy | +0.004 |
anish | +0.004 |
anymore | +0.004 |
Ow | +0.004 |
Neg logit contributions | |
asis | -0.007 |
rig | -0.007 |
place | -0.007 |
row | -0.006 |
eh | -0.006 |
Token | is |
Token ID | 318 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
asis | +0.067 |
rig | +0.065 |
place | +0.063 |
row | +0.058 |
eh | +0.057 |
Neg logit contributions | |
ked | -0.049 |
anish | -0.047 |
joy | -0.046 |
Ow | -0.046 |
anymore | -0.044 |
Token | called |
Token ID | 1444 |
Feature activation | +6.98e+00 |
Pos logit contributions | |
asis | +0.074 |
rig | +0.071 |
place | +0.069 |
old | +0.064 |
row | +0.064 |
Neg logit contributions | |
ked | -0.047 |
anish | -0.046 |
Ow | -0.046 |
anymore | -0.045 |
joy | -0.044 |
Token | chalk |
Token ID | 30860 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
asis | +0.359 |
rig | +0.345 |
place | +0.336 |
row | +0.309 |
eh | +0.306 |
Neg logit contributions | |
ked | -0.249 |
anish | -0.238 |
Ow | -0.232 |
joy | -0.227 |
anymore | -0.225 |
Token | ," |
Token ID | 553 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
asis | +0.119 |
rig | +0.113 |
place | +0.110 |
row | +0.100 |
eh | +0.099 |
Neg logit contributions | |
ked | -0.115 |
anish | -0.110 |
Ow | -0.108 |
joy | -0.107 |
anymore | -0.105 |
Token | said |
Token ID | 531 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
ked | +0.033 |
anish | +0.031 |
Ow | +0.031 |
anymore | +0.030 |
joy | +0.030 |
Neg logit contributions | |
asis | -0.040 |
rig | -0.039 |
place | -0.038 |
old | -0.035 |
eh | -0.035 |
Token | Dad |
Token ID | 17415 |
Feature activation | +4.92e-01 |
Pos logit contributions | |
asis | +0.038 |
rig | +0.037 |
place | +0.036 |
old | +0.035 |
called | +0.035 |
Neg logit contributions | |
anish | -0.034 |
ked | -0.033 |
Ow | -0.033 |
arre | -0.032 |
ifying | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
asis | +0.028 |
place | +0.026 |
rig | +0.026 |
eh | +0.024 |
ands | +0.023 |
Neg logit contributions | |
ked | -0.018 |
anymore | -0.016 |
joy | -0.015 |
again | -0.014 |
anish | -0.014 |
Token | € |
Token ID | 26391 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
erry | +0.071 |
rig | +0.070 |
place | +0.069 |
asis | +0.068 |
row | +0.067 |
Neg logit contributions | |
ked | -0.056 |
joy | -0.053 |
anish | -0.051 |
ved | -0.048 |
anymore | -0.048 |
Token | � |
Token ID | 129 |
Feature activation | +2.53e-01 |
Pos logit contributions | |
asis | +0.074 |
rig | +0.070 |
place | +0.068 |
row | +0.062 |
eh | +0.062 |
Neg logit contributions | |
ked | -0.059 |
anish | -0.057 |
Ow | -0.056 |
anymore | -0.054 |
joy | -0.054 |
Token | � |
Token ID | 241 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
place | +0.012 |
asis | +0.012 |
row | +0.011 |
erry | +0.011 |
atmeal | +0.011 |
Neg logit contributions | |
ked | -0.010 |
anymore | -0.008 |
Ow | -0.008 |
joy | -0.008 |
adoes | -0.008 |
Token | I |
Token ID | 40 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
asis | +0.144 |
rig | +0.140 |
place | +0.135 |
old | +0.124 |
eh | +0.122 |
Neg logit contributions | |
ked | -0.111 |
anish | -0.106 |
anymore | -0.101 |
Ow | -0.101 |
joy | -0.098 |
Token | am |
Token ID | 716 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
asis | +0.080 |
place | +0.075 |
rig | +0.075 |
row | +0.070 |
isin | +0.069 |
Neg logit contributions | |
ked | -0.056 |
Ow | -0.054 |
anish | -0.053 |
joy | -0.050 |
anymore | -0.050 |
Token | called |
Token ID | 1444 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
asis | +0.119 |
rig | +0.113 |
place | +0.113 |
row | +0.106 |
isin | +0.098 |
Neg logit contributions | |
ked | -0.055 |
joy | -0.054 |
anymore | -0.052 |
Ow | -0.052 |
anish | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
asis | +0.353 |
rig | +0.336 |
place | +0.326 |
row | +0.300 |
eh | +0.299 |
Neg logit contributions | |
ked | -0.257 |
anish | -0.246 |
Ow | -0.246 |
joy | -0.238 |
anymore | -0.236 |
Token | squirrel |
Token ID | 33039 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
asis | +0.089 |
rig | +0.087 |
place | +0.083 |
row | +0.079 |
old | +0.078 |
Neg logit contributions | |
ked | -0.062 |
anish | -0.060 |
Ow | -0.060 |
joy | -0.059 |
anymore | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
asis | +0.018 |
rig | +0.018 |
place | +0.017 |
isin | +0.016 |
row | +0.015 |
Neg logit contributions | |
ked | -0.014 |
anymore | -0.013 |
anish | -0.013 |
Ow | -0.012 |
joy | -0.012 |
Token | I |
Token ID | 314 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
asis | +0.027 |
rig | +0.025 |
place | +0.025 |
row | +0.023 |
eh | +0.023 |
Neg logit contributions | |
ked | -0.017 |
Ow | -0.016 |
anish | -0.016 |
joy | -0.015 |
anymore | -0.015 |
Token | have |
Token ID | 423 |
Feature activation | +9.80e-02 |
Pos logit contributions | |
ked | +0.005 |
anish | +0.005 |
Ow | +0.005 |
anymore | +0.004 |
joy | +0.004 |
Neg logit contributions | |
asis | -0.006 |
rig | -0.006 |
place | -0.005 |
row | -0.005 |
eh | -0.005 |
Token | replied |
Token ID | 8712 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
ked | +0.078 |
anish | +0.074 |
Ow | +0.073 |
joy | +0.072 |
anymore | +0.072 |
Neg logit contributions | |
asis | -0.070 |
rig | -0.067 |
place | -0.065 |
row | -0.058 |
eh | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
asis | +0.026 |
rig | +0.025 |
place | +0.025 |
row | +0.023 |
old | +0.023 |
Neg logit contributions | |
Ow | -0.030 |
ked | -0.029 |
anish | -0.029 |
joy | -0.028 |
adoes | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
asis | +0.062 |
rig | +0.060 |
place | +0.057 |
eh | +0.055 |
called | +0.055 |
Neg logit contributions | |
anish | -0.040 |
ked | -0.039 |
Ow | -0.038 |
anymore | -0.037 |
tant | -0.036 |
Token | That |
Token ID | 2504 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
ked | +0.030 |
anish | +0.029 |
joy | +0.028 |
Ow | +0.028 |
anymore | +0.028 |
Neg logit contributions | |
asis | -0.047 |
rig | -0.046 |
place | -0.045 |
row | -0.041 |
eh | -0.041 |
Token | 's |
Token ID | 338 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
asis | +0.031 |
place | +0.027 |
rig | +0.027 |
eh | +0.025 |
old | +0.025 |
Neg logit contributions | |
ked | -0.034 |
joy | -0.031 |
anish | -0.031 |
anymore | -0.029 |
Ow | -0.029 |
Token | called |
Token ID | 1444 |
Feature activation | +6.96e+00 |
Pos logit contributions | |
asis | +0.110 |
rig | +0.105 |
place | +0.103 |
row | +0.098 |
old | +0.097 |
Neg logit contributions | |
Ow | -0.048 |
ked | -0.046 |
anymore | -0.044 |
anish | -0.043 |
adoes | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
asis | +0.343 |
rig | +0.329 |
place | +0.320 |
row | +0.293 |
eh | +0.290 |
Neg logit contributions | |
ked | -0.263 |
anish | -0.251 |
Ow | -0.246 |
joy | -0.241 |
anymore | -0.239 |
Token | mustache |
Token ID | 49303 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
asis | +0.096 |
rig | +0.090 |
place | +0.088 |
eh | +0.081 |
row | +0.079 |
Neg logit contributions | |
ked | -0.080 |
anish | -0.075 |
Ow | -0.073 |
anymore | -0.072 |
joy | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
ked | +0.050 |
anish | +0.048 |
anymore | +0.047 |
Ow | +0.046 |
joy | +0.044 |
Neg logit contributions | |
asis | -0.061 |
rig | -0.061 |
place | -0.058 |
eh | -0.053 |
row | -0.052 |
Token | There |
Token ID | 1318 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
asis | +0.073 |
rig | +0.070 |
place | +0.069 |
eh | +0.064 |
row | +0.064 |
Neg logit contributions | |
ked | -0.029 |
anish | -0.027 |
Ow | -0.027 |
joy | -0.025 |
anymore | -0.024 |
Token | are |
Token ID | 389 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
asis | +0.062 |
rig | +0.061 |
place | +0.058 |
eh | +0.055 |
row | +0.054 |
Neg logit contributions | |
ked | -0.031 |
anish | -0.030 |
Ow | -0.029 |
anymore | -0.029 |
adoes | -0.027 |
Token | bowl |
Token ID | 9396 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
joy | +0.093 |
anish | +0.091 |
ked | +0.089 |
anymore | +0.088 |
tant | +0.088 |
Neg logit contributions | |
rig | -0.108 |
asis | -0.108 |
place | -0.099 |
old | -0.096 |
row | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
ked | +0.033 |
anymore | +0.030 |
anish | +0.030 |
joy | +0.029 |
Ow | +0.027 |
Neg logit contributions | |
asis | -0.070 |
rig | -0.070 |
place | -0.067 |
isin | -0.063 |
old | -0.061 |
Token | " |
Token ID | 366 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
ked | +0.003 |
Ow | +0.003 |
anish | +0.003 |
joy | +0.003 |
anymore | +0.003 |
Neg logit contributions | |
asis | -0.006 |
place | -0.006 |
rig | -0.006 |
row | -0.005 |
rim | -0.005 |
Token | This |
Token ID | 1212 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
ked | +0.096 |
anish | +0.091 |
Ow | +0.089 |
anymore | +0.089 |
joy | +0.088 |
Neg logit contributions | |
asis | -0.114 |
rig | -0.109 |
place | -0.107 |
eh | -0.097 |
row | -0.097 |
Token | is |
Token ID | 318 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
asis | +0.045 |
rig | +0.044 |
place | +0.042 |
row | +0.039 |
old | +0.038 |
Neg logit contributions | |
ked | -0.034 |
anish | -0.033 |
Ow | -0.032 |
joy | -0.031 |
anymore | -0.031 |
Token | called |
Token ID | 1444 |
Feature activation | +6.94e+00 |
Pos logit contributions | |
asis | +0.063 |
old | +0.058 |
rig | +0.057 |
place | +0.056 |
row | +0.054 |
Neg logit contributions | |
anymore | -0.028 |
Ow | -0.027 |
anish | -0.025 |
ked | -0.024 |
no | -0.023 |
Token | caul |
Token ID | 46087 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
asis | +0.342 |
rig | +0.328 |
place | +0.319 |
row | +0.292 |
eh | +0.289 |
Neg logit contributions | |
ked | -0.262 |
anish | -0.251 |
Ow | -0.245 |
joy | -0.240 |
anymore | -0.238 |
Token | iflower |
Token ID | 42642 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
rig | +0.043 |
asis | +0.038 |
old | +0.036 |
place | +0.036 |
roads | +0.031 |
Neg logit contributions | |
anish | -0.076 |
Ow | -0.072 |
ked | -0.072 |
anymore | -0.070 |
rots | -0.069 |
Token | soup |
Token ID | 17141 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
rig | +0.156 |
asis | +0.151 |
place | +0.143 |
isin | +0.136 |
aling | +0.135 |
Neg logit contributions | |
anymore | -0.100 |
anish | -0.100 |
ked | -0.096 |
Ow | -0.094 |
again | -0.086 |
Token | ," |
Token ID | 553 |
Feature activation | +5.18e-02 |
Pos logit contributions | |
rig | +0.073 |
asis | +0.072 |
place | +0.069 |
old | +0.066 |
aling | +0.065 |
Neg logit contributions | |
anymore | -0.051 |
ked | -0.049 |
anish | -0.049 |
Ow | -0.047 |
adoes | -0.043 |
Token | said |
Token ID | 531 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
asis | +0.003 |
rig | +0.003 |
place | +0.003 |
row | +0.002 |
rim | +0.002 |
Neg logit contributions | |
ked | -0.002 |
Ow | -0.002 |
anish | -0.002 |
anymore | -0.002 |
joy | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
asis | +0.034 |
rig | +0.033 |
place | +0.033 |
row | +0.030 |
old | +0.030 |
Neg logit contributions | |
ked | -0.030 |
Ow | -0.029 |
anish | -0.028 |
joy | -0.028 |
anymore | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
asis | +0.010 |
rig | +0.010 |
place | +0.010 |
old | +0.009 |
eh | +0.009 |
Neg logit contributions | |
ked | -0.009 |
anish | -0.008 |
Ow | -0.008 |
anymore | -0.008 |
joy | -0.008 |
Token | The |
Token ID | 464 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
ked | +0.076 |
anymore | +0.072 |
Ow | +0.069 |
anish | +0.069 |
joy | +0.067 |
Neg logit contributions | |
asis | -0.101 |
rig | -0.099 |
place | -0.098 |
eh | -0.091 |
old | -0.090 |
Token | game |
Token ID | 983 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
asis | +0.068 |
place | +0.066 |
rig | +0.066 |
isin | +0.057 |
eh | +0.057 |
Neg logit contributions | |
ked | -0.072 |
Ow | -0.066 |
joy | -0.063 |
anish | -0.062 |
anymore | -0.061 |
Token | is |
Token ID | 318 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
ked | +0.012 |
anish | +0.011 |
Ow | +0.011 |
joy | +0.011 |
anymore | +0.011 |
Neg logit contributions | |
asis | -0.020 |
rig | -0.019 |
place | -0.019 |
row | -0.017 |
eh | -0.017 |
Token | called |
Token ID | 1444 |
Feature activation | +6.93e+00 |
Pos logit contributions | |
asis | +0.060 |
rig | +0.056 |
place | +0.055 |
row | +0.051 |
old | +0.050 |
Neg logit contributions | |
ked | -0.044 |
anymore | -0.043 |
anish | -0.042 |
Ow | -0.041 |
joy | -0.041 |
Token | Match |
Token ID | 13225 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
rig | +0.317 |
asis | +0.309 |
place | +0.305 |
row | +0.273 |
old | +0.268 |
Neg logit contributions | |
ked | -0.270 |
joy | -0.259 |
anish | -0.255 |
Ow | -0.251 |
anymore | -0.243 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
asis | +0.094 |
rig | +0.092 |
place | +0.089 |
row | +0.082 |
old | +0.082 |
Neg logit contributions | |
ked | -0.094 |
Ow | -0.091 |
anish | -0.090 |
joy | -0.087 |
anymore | -0.085 |
Token | Everyone |
Token ID | 11075 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
asis | +0.052 |
rig | +0.050 |
place | +0.048 |
old | +0.044 |
row | +0.044 |
Neg logit contributions | |
ked | -0.049 |
anish | -0.047 |
Ow | -0.046 |
joy | -0.046 |
anymore | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
asis | +0.000 |
rig | +0.000 |
place | +0.000 |
old | +0.000 |
row | +0.000 |
Neg logit contributions | |
ked | -0.000 |
Ow | -0.000 |
anish | -0.000 |
joy | -0.000 |
anymore | -0.000 |
Token | quiet |
Token ID | 5897 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
asis | +0.016 |
rig | +0.015 |
place | +0.015 |
old | +0.013 |
eh | +0.013 |
Neg logit contributions | |
ked | -0.016 |
anish | -0.016 |
Ow | -0.016 |
joy | -0.015 |
anymore | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
asis | +0.035 |
rig | +0.034 |
place | +0.033 |
old | +0.031 |
eh | +0.030 |
Neg logit contributions | |
anymore | -0.022 |
ked | -0.021 |
anish | -0.020 |
Ow | -0.019 |
joy | -0.019 |
Token | Annie |
Token ID | 25860 |
Feature activation | +7.18e-02 |
Pos logit contributions | |
asis | +0.021 |
rig | +0.020 |
place | +0.019 |
row | +0.018 |
eh | +0.017 |
Neg logit contributions | |
ked | -0.017 |
anish | -0.016 |
Ow | -0.016 |
joy | -0.015 |
anymore | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
asis | +0.003 |
rig | +0.003 |
place | +0.003 |
row | +0.002 |
eh | +0.002 |
Neg logit contributions | |
ked | -0.003 |
anish | -0.003 |
Ow | -0.003 |
joy | -0.003 |
anymore | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
place | +0.080 |
asis | +0.079 |
called | +0.075 |
old | +0.074 |
isin | +0.074 |
Neg logit contributions | |
Ow | -0.101 |
arre | -0.098 |
ked | -0.098 |
anish | -0.097 |
adoes | -0.096 |
Token | was |
Token ID | 373 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
asis | +0.114 |
rig | +0.111 |
place | +0.108 |
row | +0.100 |
eh | +0.097 |
Neg logit contributions | |
ked | -0.080 |
anish | -0.077 |
joy | -0.076 |
Ow | -0.076 |
anymore | -0.072 |
Token | called |
Token ID | 1444 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
asis | +0.108 |
rig | +0.104 |
place | +0.101 |
row | +0.093 |
old | +0.092 |
Neg logit contributions | |
ked | -0.062 |
anish | -0.058 |
Ow | -0.058 |
anymore | -0.058 |
joy | -0.057 |
Token | � |
Token ID | 6184 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
asis | +0.316 |
rig | +0.315 |
place | +0.304 |
row | +0.280 |
eh | +0.280 |
Neg logit contributions | |
ked | -0.262 |
anish | -0.256 |
joy | -0.243 |
Ow | -0.240 |
anymore | -0.237 |
Token | � |
Token ID | 95 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
asis | +0.076 |
row | +0.072 |
rig | +0.069 |
eh | +0.068 |
b | +0.068 |
Neg logit contributions | |
ked | -0.063 |
superstar | -0.063 |
anymore | -0.063 |
anish | -0.062 |
joy | -0.061 |
Token | € |
Token ID | 26391 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
asis | +0.084 |
place | +0.078 |
row | +0.077 |
erry | +0.077 |
rig | +0.074 |
Neg logit contributions | |
anish | -0.068 |
superstar | -0.064 |
anymore | -0.063 |
ked | -0.062 |
joy | -0.061 |
Token | ˜ |
Token ID | 41185 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
asis | +0.075 |
rig | +0.069 |
place | +0.065 |
old | +0.061 |
eh | +0.061 |
Neg logit contributions | |
ked | -0.064 |
tant | -0.059 |
anish | -0.059 |
Ow | -0.058 |
anymore | -0.054 |
Token | Pretty |
Token ID | 35700 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
asis | +0.023 |
rig | +0.022 |
place | +0.021 |
row | +0.020 |
old | +0.019 |
Neg logit contributions | |
ked | -0.023 |
anish | -0.022 |
Ow | -0.022 |
joy | -0.021 |
anymore | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
asis | +0.028 |
rig | +0.027 |
place | +0.026 |
eh | +0.025 |
isin | +0.024 |
Neg logit contributions | |
ked | -0.017 |
anymore | -0.017 |
anish | -0.017 |
Ow | -0.016 |
joy | -0.016 |
Token | She |
Token ID | 1375 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
asis | +0.022 |
rig | +0.021 |
place | +0.021 |
row | +0.019 |
eh | +0.019 |
Neg logit contributions | |
ked | -0.015 |
anish | -0.015 |
Ow | -0.014 |
joy | -0.014 |
anymore | -0.014 |
Token | said |
Token ID | 531 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
asis | +0.073 |
rig | +0.067 |
place | +0.066 |
row | +0.058 |
isin | +0.057 |
Neg logit contributions | |
ked | -0.070 |
anish | -0.065 |
Ow | -0.064 |
joy | -0.063 |
anymore | -0.060 |
Token | it |
Token ID | 340 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
old | +0.061 |
place | +0.060 |
asis | +0.060 |
called | +0.058 |
isin | +0.055 |
Neg logit contributions | |
anish | -0.087 |
Ow | -0.087 |
arre | -0.087 |
ked | -0.086 |
ifying | -0.084 |
Token | was |
Token ID | 373 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
asis | +0.105 |
rig | +0.102 |
place | +0.100 |
row | +0.092 |
old | +0.090 |
Neg logit contributions | |
ked | -0.077 |
anish | -0.074 |
joy | -0.074 |
Ow | -0.072 |
anymore | -0.070 |
Token | called |
Token ID | 1444 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
asis | +0.114 |
rig | +0.108 |
place | +0.105 |
old | +0.099 |
row | +0.098 |
Neg logit contributions | |
ked | -0.049 |
Ow | -0.046 |
anymore | -0.046 |
joy | -0.044 |
anish | -0.044 |
Token | dust |
Token ID | 8977 |
Feature activation | +4.18e+00 |
Pos logit contributions | |
asis | +0.361 |
rig | +0.348 |
place | +0.339 |
row | +0.312 |
eh | +0.309 |
Neg logit contributions | |
ked | -0.240 |
anish | -0.229 |
Ow | -0.223 |
joy | -0.219 |
anymore | -0.217 |
Token | . |
Token ID | 13 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
asis | +0.190 |
rig | +0.181 |
place | +0.177 |
row | +0.166 |
eh | +0.158 |
Neg logit contributions | |
ked | -0.169 |
anish | -0.165 |
Ow | -0.162 |
joy | -0.162 |
anymore | -0.154 |
Token | He |
Token ID | 679 |
Feature activation | +5.56e-01 |
Pos logit contributions | |
rig | +0.031 |
asis | +0.031 |
place | +0.030 |
old | +0.029 |
aster | +0.028 |
Neg logit contributions | |
ked | -0.026 |
anish | -0.025 |
prope | -0.023 |
superstar | -0.023 |
anymore | -0.023 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
asis | +0.025 |
rig | +0.024 |
place | +0.023 |
row | +0.021 |
eh | +0.020 |
Neg logit contributions | |
ked | -0.024 |
anish | -0.022 |
Ow | -0.022 |
joy | -0.021 |
anymore | -0.021 |
Token | her |
Token ID | 607 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
asis | +0.164 |
rig | +0.157 |
place | +0.154 |
row | +0.141 |
eh | +0.140 |
Neg logit contributions | |
ked | -0.113 |
anish | -0.108 |
Ow | -0.105 |
joy | -0.103 |
anymore | -0.102 |
Token | , |
Token ID | 11 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
asis | +0.137 |
rig | +0.132 |
place | +0.129 |
row | +0.119 |
eh | +0.118 |
Neg logit contributions | |
ked | -0.086 |
anish | -0.080 |
Ow | -0.078 |
joy | -0.078 |
anymore | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
asis | +0.030 |
rig | +0.029 |
place | +0.029 |
eh | +0.027 |
old | +0.027 |
Neg logit contributions | |
anish | -0.023 |
ked | -0.023 |
Ow | -0.021 |
tant | -0.021 |
anymore | -0.021 |
Token | other |
Token ID | 584 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
asis | +0.069 |
rig | +0.066 |
place | +0.064 |
eh | +0.057 |
old | +0.056 |
Neg logit contributions | |
ked | -0.073 |
anish | -0.070 |
Ow | -0.067 |
anymore | -0.067 |
adoes | -0.065 |
Token | child |
Token ID | 1200 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
asis | +0.049 |
place | +0.048 |
rig | +0.048 |
old | +0.044 |
row | +0.042 |
Neg logit contributions | |
ked | -0.038 |
anish | -0.036 |
Ow | -0.035 |
prope | -0.033 |
adoes | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | +9.12e-01 |
Pos logit contributions | |
asis | +0.060 |
rig | +0.058 |
place | +0.056 |
row | +0.052 |
eh | +0.051 |
Neg logit contributions | |
ked | -0.038 |
anymore | -0.036 |
anish | -0.036 |
joy | -0.035 |
Ow | -0.034 |
Token | called |
Token ID | 1444 |
Feature activation | +6.81e+00 |
Pos logit contributions | |
asis | +0.044 |
rig | +0.042 |
place | +0.041 |
row | +0.037 |
eh | +0.037 |
Neg logit contributions | |
ked | -0.036 |
anish | -0.034 |
Ow | -0.033 |
joy | -0.033 |
anymore | -0.033 |
Token | Bob |
Token ID | 5811 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
asis | +0.365 |
rig | +0.352 |
place | +0.343 |
row | +0.317 |
eh | +0.314 |
Neg logit contributions | |
ked | -0.227 |
anish | -0.216 |
Ow | -0.210 |
joy | -0.205 |
anymore | -0.203 |
Token | . |
Token ID | 13 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
asis | +0.121 |
rig | +0.116 |
place | +0.112 |
row | +0.102 |
eh | +0.101 |
Neg logit contributions | |
ked | -0.120 |
anish | -0.117 |
Ow | -0.114 |
joy | -0.111 |
anymore | -0.110 |
Token | |
Token ID | 220 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
asis | +0.024 |
rig | +0.024 |
place | +0.022 |
old | +0.021 |
eh | +0.021 |
Neg logit contributions | |
ked | -0.019 |
anish | -0.019 |
Ow | -0.017 |
joy | -0.017 |
anymore | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
ked | +0.035 |
anish | +0.033 |
Ow | +0.032 |
joy | +0.032 |
anymore | +0.031 |
Neg logit contributions | |
asis | -0.045 |
rig | -0.043 |
place | -0.042 |
row | -0.038 |
eh | -0.038 |
Token | Amy |
Token ID | 40797 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
asis | +0.030 |
rig | +0.029 |
place | +0.028 |
old | +0.026 |
row | +0.026 |
Neg logit contributions | |
ked | -0.026 |
anish | -0.024 |
Ow | -0.024 |
joy | -0.023 |
anymore | -0.023 |
Token | flew |
Token ID | 13112 |
Feature activation | -9.68e-01 |
Pos logit contributions | |
ked | +0.023 |
anish | +0.022 |
Ow | +0.021 |
joy | +0.021 |
anymore | +0.021 |
Neg logit contributions | |
asis | -0.029 |
rig | -0.028 |
place | -0.027 |
row | -0.025 |
eh | -0.025 |
Token | away |
Token ID | 1497 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
anish | +0.040 |
Ow | +0.038 |
ked | +0.038 |
arre | +0.035 |
adoes | +0.035 |
Neg logit contributions | |
asis | -0.043 |
rig | -0.042 |
place | -0.040 |
row | -0.040 |
eh | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ked | +0.084 |
anish | +0.080 |
Ow | +0.078 |
joy | +0.076 |
anymore | +0.075 |
Neg logit contributions | |
asis | -0.115 |
rig | -0.111 |
place | -0.108 |
row | -0.099 |
eh | -0.098 |
Token | singing |
Token ID | 13777 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
ked | +0.045 |
anish | +0.044 |
Ow | +0.044 |
anymore | +0.041 |
joy | +0.040 |
Neg logit contributions | |
asis | -0.043 |
rig | -0.041 |
place | -0.039 |
eh | -0.035 |
old | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
Ow | +0.073 |
ked | +0.069 |
anish | +0.067 |
arre | +0.066 |
tant | +0.065 |
Neg logit contributions | |
asis | -0.064 |
rig | -0.061 |
place | -0.061 |
called | -0.058 |
row | -0.058 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -7.09e+00 |
Pos logit contributions | |
ked | +0.098 |
anish | +0.094 |
Ow | +0.092 |
joy | +0.090 |
anymore | +0.089 |
Neg logit contributions | |
asis | -0.105 |
rig | -0.101 |
place | -0.097 |
row | -0.088 |
eh | -0.087 |
Token | to |
Token ID | 284 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
anish | +0.254 |
ked | +0.249 |
Ow | +0.248 |
joy | +0.225 |
tant | +0.225 |
Neg logit contributions | |
asis | -0.358 |
rig | -0.343 |
place | -0.332 |
row | -0.313 |
eh | -0.301 |
Token | me |
Token ID | 502 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
ked | +0.064 |
anish | +0.062 |
Ow | +0.060 |
joy | +0.059 |
anymore | +0.058 |
Neg logit contributions | |
asis | -0.076 |
rig | -0.072 |
place | -0.070 |
row | -0.064 |
eh | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
asis | +0.011 |
place | +0.010 |
rig | +0.010 |
eh | +0.009 |
isin | +0.009 |
Neg logit contributions | |
anymore | -0.009 |
ked | -0.009 |
joy | -0.008 |
anish | -0.008 |
Ow | -0.008 |
Token | I |
Token ID | 314 |
Feature activation | -9.37e-01 |
Pos logit contributions | |
ked | +0.019 |
Ow | +0.019 |
anish | +0.019 |
joy | +0.019 |
anymore | +0.017 |
Neg logit contributions | |
asis | -0.034 |
place | -0.032 |
rig | -0.032 |
row | -0.030 |
eh | -0.029 |
Token | waved |
Token ID | 26834 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
ked | +0.034 |
anish | +0.032 |
Ow | +0.032 |
joy | +0.031 |
anymore | +0.031 |
Neg logit contributions | |
asis | -0.047 |
rig | -0.045 |
place | -0.044 |
row | -0.041 |
eh | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
ked | +0.102 |
anish | +0.098 |
Ow | +0.097 |
joy | +0.094 |
anymore | +0.090 |
Neg logit contributions | |
asis | -0.113 |
rig | -0.108 |
place | -0.105 |
row | -0.097 |
eh | -0.095 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ked | +0.036 |
anish | +0.034 |
arre | +0.031 |
adoes | +0.030 |
prope | +0.030 |
Neg logit contributions | |
rig | -0.034 |
asis | -0.034 |
place | -0.032 |
old | -0.031 |
aster | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ked | +0.039 |
anish | +0.036 |
Ow | +0.036 |
joy | +0.035 |
anymore | +0.035 |
Neg logit contributions | |
asis | -0.087 |
rig | -0.084 |
place | -0.083 |
row | -0.077 |
eh | -0.076 |
Token | Anna |
Token ID | 11735 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ked | +0.035 |
anish | +0.033 |
Ow | +0.032 |
joy | +0.032 |
anymore | +0.031 |
Neg logit contributions | |
asis | -0.067 |
rig | -0.065 |
place | -0.063 |
row | -0.059 |
old | -0.059 |
Token | wave |
Token ID | 6769 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
ked | +0.049 |
anish | +0.047 |
Ow | +0.045 |
joy | +0.045 |
anymore | +0.044 |
Neg logit contributions | |
asis | -0.073 |
rig | -0.070 |
place | -0.068 |
row | -0.063 |
old | -0.062 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
anish | +0.064 |
Ow | +0.062 |
arre | +0.059 |
adoes | +0.057 |
ifying | +0.056 |
Neg logit contributions | |
old | -0.063 |
rig | -0.061 |
place | -0.061 |
called | -0.059 |
asis | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
anish | +0.328 |
Ow | +0.318 |
ked | +0.312 |
arre | +0.303 |
joy | +0.301 |
Neg logit contributions | |
asis | -0.267 |
rig | -0.260 |
place | -0.250 |
row | -0.233 |
old | -0.220 |
Token | They |
Token ID | 1119 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
anish | +0.021 |
ked | +0.021 |
tant | +0.019 |
arre | +0.018 |
joy | +0.018 |
Neg logit contributions | |
rig | -0.030 |
asis | -0.030 |
place | -0.028 |
old | -0.027 |
called | -0.026 |
Token | go |
Token ID | 467 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
asis | +0.008 |
rig | +0.007 |
place | +0.007 |
row | +0.007 |
eh | +0.007 |
Neg logit contributions | |
ked | -0.006 |
Ow | -0.005 |
anymore | -0.005 |
anish | -0.005 |
joy | -0.005 |
Token | back |
Token ID | 736 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
asis | +0.022 |
rig | +0.022 |
place | +0.021 |
eh | +0.019 |
row | +0.019 |
Neg logit contributions | |
ked | -0.012 |
anish | -0.011 |
anymore | -0.011 |
joy | -0.011 |
Ow | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
ked | +0.048 |
anish | +0.045 |
Ow | +0.043 |
joy | +0.043 |
anymore | +0.042 |
Neg logit contributions | |
asis | -0.094 |
rig | -0.091 |
place | -0.089 |
row | -0.082 |
eh | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
anish | +0.166 |
Ow | +0.163 |
ked | +0.157 |
arre | +0.157 |
joy | +0.153 |
Neg logit contributions | |
asis | -0.095 |
rig | -0.090 |
place | -0.085 |
called | -0.080 |
fire | -0.079 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
ked | +0.024 |
anish | +0.023 |
joy | +0.021 |
adoes | +0.021 |
tant | +0.021 |
Neg logit contributions | |
rig | -0.025 |
asis | -0.024 |
place | -0.024 |
old | -0.022 |
called | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
ked | +0.007 |
anish | +0.007 |
Ow | +0.007 |
joy | +0.007 |
anymore | +0.007 |
Neg logit contributions | |
asis | -0.011 |
rig | -0.011 |
place | -0.010 |
old | -0.009 |
row | -0.009 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
anish | +0.025 |
ked | +0.024 |
Ow | +0.022 |
joy | +0.022 |
anymore | +0.022 |
Neg logit contributions | |
asis | -0.038 |
rig | -0.036 |
place | -0.036 |
aster | -0.033 |
old | -0.033 |
Token | wave |
Token ID | 6769 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
anish | +0.071 |
joy | +0.070 |
ked | +0.070 |
Ow | +0.068 |
adoes | +0.067 |
Neg logit contributions | |
asis | -0.086 |
rig | -0.083 |
place | -0.081 |
old | -0.071 |
row | -0.070 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.90e+00 |
Pos logit contributions | |
anish | +0.069 |
arre | +0.064 |
Ow | +0.062 |
ifying | +0.061 |
adoes | +0.059 |
Neg logit contributions | |
old | -0.048 |
called | -0.044 |
old | -0.043 |
rig | -0.043 |
aling | -0.042 |
Token | to |
Token ID | 284 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
anish | +0.236 |
Ow | +0.225 |
ked | +0.225 |
joy | +0.214 |
anymore | +0.206 |
Neg logit contributions | |
asis | -0.356 |
rig | -0.348 |
place | -0.335 |
row | -0.319 |
old | -0.307 |
Token | the |
Token ID | 262 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
anish | +0.072 |
ked | +0.071 |
arre | +0.066 |
Ow | +0.064 |
joy | +0.064 |
Neg logit contributions | |
asis | -0.061 |
place | -0.056 |
rig | -0.055 |
aster | -0.053 |
old | -0.051 |
Token | bird |
Token ID | 6512 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ked | +0.019 |
ifying | +0.017 |
anish | +0.017 |
ved | +0.017 |
arre | +0.016 |
Neg logit contributions | |
asis | -0.017 |
place | -0.014 |
old | -0.013 |
igator | -0.013 |
stump | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
ked | +0.083 |
anymore | +0.076 |
anish | +0.076 |
Ow | +0.074 |
joy | +0.072 |
Neg logit contributions | |
asis | -0.158 |
rig | -0.153 |
place | -0.150 |
row | -0.138 |
eh | -0.137 |
Token | They |
Token ID | 1119 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
anish | +0.023 |
ked | +0.023 |
tant | +0.021 |
anymore | +0.021 |
joy | +0.021 |
Neg logit contributions | |
rig | -0.038 |
asis | -0.037 |
place | -0.036 |
old | -0.034 |
called | -0.033 |
Token | sm |
Token ID | 895 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
asis | +0.009 |
rig | +0.009 |
place | +0.009 |
row | +0.008 |
isin | +0.008 |
Neg logit contributions | |
ked | -0.007 |
Ow | -0.006 |
anish | -0.006 |
joy | -0.006 |
tant | -0.006 |
Token | elly |
Token ID | 6148 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
anymore | +0.019 |
anish | +0.019 |
joy | +0.019 |
ked | +0.018 |
Ow | +0.018 |
Neg logit contributions | |
asis | -0.032 |
rig | -0.030 |
place | -0.028 |
isin | -0.027 |
eh | -0.027 |
Token | flower |
Token ID | 15061 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
asis | +0.045 |
rig | +0.043 |
place | +0.041 |
row | +0.038 |
old | +0.037 |
Neg logit contributions | |
ked | -0.039 |
anish | -0.038 |
Ow | -0.037 |
joy | -0.037 |
anymore | -0.037 |
Token | as |
Token ID | 355 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
asis | +0.016 |
rig | +0.015 |
place | +0.014 |
old | +0.013 |
isin | +0.013 |
Neg logit contributions | |
ked | -0.012 |
anish | -0.012 |
anymore | -0.012 |
Ow | -0.011 |
joy | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
asis | +0.031 |
rig | +0.030 |
place | +0.029 |
eh | +0.027 |
row | +0.027 |
Neg logit contributions | |
ked | -0.020 |
anish | -0.020 |
Ow | -0.019 |
joy | -0.018 |
anymore | -0.018 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
ked | +0.079 |
anish | +0.076 |
joy | +0.075 |
Ow | +0.074 |
anymore | +0.073 |
Neg logit contributions | |
asis | -0.091 |
rig | -0.086 |
place | -0.083 |
row | -0.077 |
eh | -0.076 |
Token | gift |
Token ID | 6979 |
Feature activation | -3.48e+00 |
Pos logit contributions | |
ked | +0.298 |
anish | +0.294 |
Ow | +0.287 |
joy | +0.278 |
anymore | +0.273 |
Neg logit contributions | |
asis | -0.292 |
rig | -0.277 |
place | -0.269 |
row | -0.245 |
eh | -0.239 |
Token | . |
Token ID | 13 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
ked | +0.145 |
anish | +0.138 |
anymore | +0.134 |
Ow | +0.134 |
joy | +0.133 |
Neg logit contributions | |
asis | -0.160 |
rig | -0.153 |
place | -0.148 |
eh | -0.134 |
row | -0.133 |
Token | Sam |
Token ID | 3409 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
ked | +0.017 |
anish | +0.016 |
Ow | +0.016 |
joy | +0.016 |
anymore | +0.016 |
Neg logit contributions | |
asis | -0.028 |
place | -0.026 |
rig | -0.026 |
row | -0.024 |
eh | -0.024 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ked | +0.013 |
anish | +0.012 |
joy | +0.012 |
Ow | +0.012 |
anymore | +0.012 |
Neg logit contributions | |
asis | -0.020 |
rig | -0.020 |
place | -0.019 |
row | -0.018 |
eh | -0.017 |
Token | him |
Token ID | 683 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
ked | +0.051 |
anish | +0.049 |
Ow | +0.048 |
joy | +0.047 |
anymore | +0.046 |
Neg logit contributions | |
asis | -0.063 |
rig | -0.060 |
place | -0.059 |
row | -0.053 |
old | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
ked | +0.028 |
anish | +0.026 |
Ow | +0.025 |
joy | +0.025 |
anymore | +0.025 |
Neg logit contributions | |
asis | -0.054 |
rig | -0.053 |
place | -0.051 |
row | -0.048 |
eh | -0.047 |
Token | Anna |
Token ID | 11735 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
ked | +0.029 |
anish | +0.028 |
joy | +0.026 |
arre | +0.026 |
Ow | +0.025 |
Neg logit contributions | |
asis | -0.037 |
rig | -0.035 |
place | -0.035 |
aster | -0.033 |
old | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
ked | +0.017 |
anymore | +0.015 |
anish | +0.015 |
joy | +0.015 |
Ow | +0.015 |
Neg logit contributions | |
asis | -0.040 |
rig | -0.039 |
place | -0.039 |
eh | -0.035 |
row | -0.035 |
Token | He |
Token ID | 679 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
ked | +0.017 |
anish | +0.016 |
Ow | +0.015 |
joy | +0.015 |
anymore | +0.015 |
Neg logit contributions | |
asis | -0.024 |
rig | -0.024 |
place | -0.023 |
row | -0.021 |
eh | -0.021 |
Token | waves |
Token ID | 9813 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
ked | +0.026 |
anish | +0.025 |
Ow | +0.024 |
joy | +0.024 |
anymore | +0.023 |
Neg logit contributions | |
asis | -0.028 |
rig | -0.026 |
place | -0.026 |
row | -0.023 |
eh | -0.023 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.74e+00 |
Pos logit contributions | |
asis | +0.020 |
old | +0.020 |
rig | +0.020 |
place | +0.019 |
row | +0.019 |
Neg logit contributions | |
anish | -0.021 |
arre | -0.021 |
Ow | -0.021 |
adoes | -0.020 |
joy | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
ked | +0.216 |
anish | +0.215 |
Ow | +0.208 |
joy | +0.199 |
anymore | +0.195 |
Neg logit contributions | |
asis | -0.364 |
rig | -0.351 |
place | -0.341 |
row | -0.322 |
eh | -0.315 |
Token | walks |
Token ID | 11114 |
Feature activation | -8.56e-01 |
Pos logit contributions | |
ked | +0.020 |
anish | +0.019 |
Ow | +0.019 |
joy | +0.019 |
anymore | +0.019 |
Neg logit contributions | |
asis | -0.020 |
rig | -0.019 |
place | -0.018 |
row | -0.016 |
eh | -0.016 |
Token | away |
Token ID | 1497 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
anish | +0.036 |
Ow | +0.036 |
arre | +0.034 |
ked | +0.034 |
adoes | +0.032 |
Neg logit contributions | |
asis | -0.037 |
place | -0.035 |
rig | -0.033 |
old | -0.033 |
row | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
ked | +0.117 |
anish | +0.113 |
Ow | +0.111 |
joy | +0.109 |
anymore | +0.107 |
Neg logit contributions | |
asis | -0.124 |
rig | -0.119 |
place | -0.115 |
row | -0.105 |
eh | -0.103 |
Token |
|
Token ID | 198 |
Feature activation | -7.33e-02 |
Pos logit contributions | |
ked | +0.015 |
anish | +0.014 |
Ow | +0.013 |
anymore | +0.013 |
joy | +0.013 |
Neg logit contributions | |
asis | -0.020 |
rig | -0.020 |
place | -0.019 |
old | -0.018 |
eh | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
ked | +0.011 |
anish | +0.011 |
Ow | +0.010 |
joy | +0.010 |
anymore | +0.010 |
Neg logit contributions | |
asis | -0.012 |
rig | -0.011 |
place | -0.011 |
row | -0.010 |
old | -0.010 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
ked | +0.020 |
anish | +0.020 |
Ow | +0.019 |
joy | +0.018 |
anymore | +0.018 |
Neg logit contributions | |
asis | -0.025 |
rig | -0.024 |
place | -0.023 |
old | -0.021 |
eh | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -7.50e-01 |
Pos logit contributions | |
ked | +0.006 |
anish | +0.005 |
Ow | +0.005 |
joy | +0.005 |
anymore | +0.005 |
Neg logit contributions | |
asis | -0.012 |
rig | -0.012 |
place | -0.012 |
row | -0.011 |
eh | -0.011 |
Token | Mia |
Token ID | 32189 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ked | +0.034 |
anish | +0.033 |
Ow | +0.032 |
joy | +0.032 |
anymore | +0.031 |
Neg logit contributions | |
asis | -0.032 |
rig | -0.030 |
place | -0.030 |
row | -0.026 |
eh | -0.026 |
Token | wave |
Token ID | 6769 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
asis | +0.056 |
rig | +0.053 |
place | +0.052 |
row | +0.048 |
old | +0.048 |
Neg logit contributions | |
ked | -0.034 |
anish | -0.033 |
Ow | -0.032 |
joy | -0.032 |
anymore | -0.031 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.74e+00 |
Pos logit contributions | |
anish | +0.062 |
Ow | +0.059 |
arre | +0.058 |
ifying | +0.055 |
adoes | +0.054 |
Neg logit contributions | |
old | -0.047 |
called | -0.045 |
rig | -0.044 |
place | -0.044 |
asis | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
anish | +0.294 |
Ow | +0.285 |
ked | +0.285 |
joy | +0.272 |
arre | +0.266 |
Neg logit contributions | |
asis | -0.286 |
rig | -0.276 |
place | -0.266 |
row | -0.248 |
old | -0.236 |
Token | They |
Token ID | 1119 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
ked | +0.018 |
anish | +0.018 |
anymore | +0.016 |
joy | +0.016 |
tant | +0.016 |
Neg logit contributions | |
asis | -0.031 |
rig | -0.031 |
place | -0.030 |
old | -0.028 |
called | -0.027 |
Token | are |
Token ID | 389 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
asis | +0.015 |
rig | +0.014 |
place | +0.014 |
row | +0.013 |
eh | +0.013 |
Neg logit contributions | |
ked | -0.010 |
Ow | -0.009 |
anymore | -0.009 |
anish | -0.009 |
joy | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
anish | +0.068 |
ked | +0.066 |
Ow | +0.065 |
joy | +0.062 |
tant | +0.061 |
Neg logit contributions | |
asis | -0.048 |
rig | -0.044 |
place | -0.043 |
eh | -0.040 |
called | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
ked | +0.025 |
anish | +0.025 |
Ow | +0.024 |
tant | +0.024 |
arre | +0.023 |
Neg logit contributions | |
asis | -0.019 |
place | -0.018 |
rig | -0.017 |
old | -0.016 |
called | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
anish | +0.065 |
ked | +0.063 |
Ow | +0.062 |
joy | +0.059 |
anymore | +0.057 |
Neg logit contributions | |
asis | -0.119 |
rig | -0.114 |
place | -0.114 |
row | -0.107 |
eh | -0.105 |
Token | the |
Token ID | 262 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
anish | +0.001 |
ked | +0.001 |
arre | +0.001 |
Ow | +0.001 |
adoes | +0.001 |
Neg logit contributions | |
asis | -0.001 |
place | -0.001 |
rig | -0.001 |
aster | -0.001 |
called | -0.001 |
Token | car |
Token ID | 1097 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
ked | +0.017 |
anish | +0.016 |
Ow | +0.016 |
joy | +0.015 |
anymore | +0.015 |
Neg logit contributions | |
asis | -0.022 |
rig | -0.021 |
place | -0.021 |
row | -0.019 |
eh | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
ked | +0.039 |
anymore | +0.036 |
anish | +0.035 |
joy | +0.032 |
Ow | +0.030 |
Neg logit contributions | |
asis | -0.095 |
rig | -0.092 |
place | -0.089 |
isin | -0.086 |
rim | -0.085 |
Token | waves |
Token ID | 9813 |
Feature activation | +4.58e-01 |
Pos logit contributions | |
ked | +0.050 |
anish | +0.050 |
Ow | +0.048 |
joy | +0.047 |
anymore | +0.047 |
Neg logit contributions | |
asis | -0.052 |
rig | -0.049 |
place | -0.047 |
eh | -0.043 |
row | -0.043 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.69e+00 |
Pos logit contributions | |
asis | +0.018 |
rig | +0.017 |
place | +0.017 |
row | +0.017 |
old | +0.017 |
Neg logit contributions | |
anish | -0.020 |
Ow | -0.019 |
arre | -0.019 |
adoes | -0.018 |
joy | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
anish | +0.302 |
ked | +0.299 |
Ow | +0.293 |
joy | +0.283 |
arre | +0.276 |
Neg logit contributions | |
asis | -0.275 |
rig | -0.261 |
place | -0.253 |
row | -0.233 |
eh | -0.224 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ked | +0.024 |
anish | +0.023 |
Ow | +0.022 |
joy | +0.022 |
anymore | +0.022 |
Neg logit contributions | |
asis | -0.029 |
rig | -0.028 |
place | -0.027 |
old | -0.024 |
eh | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
ked | +0.039 |
anish | +0.037 |
Ow | +0.036 |
joy | +0.035 |
anymore | +0.035 |
Neg logit contributions | |
asis | -0.070 |
rig | -0.068 |
place | -0.066 |
row | -0.061 |
old | -0.061 |
Token | Mia |
Token ID | 32189 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
ked | +0.033 |
anish | +0.032 |
Ow | +0.031 |
joy | +0.031 |
anymore | +0.030 |
Neg logit contributions | |
asis | -0.040 |
rig | -0.038 |
place | -0.037 |
row | -0.034 |
eh | -0.033 |
Token | wave |
Token ID | 6769 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
asis | +0.041 |
rig | +0.038 |
place | +0.037 |
row | +0.034 |
old | +0.034 |
Neg logit contributions | |
ked | -0.038 |
anish | -0.038 |
Ow | -0.036 |
joy | -0.036 |
anymore | -0.035 |
Token | away |
Token ID | 1497 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
rig | +0.029 |
asis | +0.029 |
place | +0.028 |
row | +0.026 |
fire | +0.026 |
Neg logit contributions | |
Ow | -0.029 |
anish | -0.029 |
ked | -0.027 |
adoes | -0.026 |
prope | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -9.69e-01 |
Pos logit contributions | |
anish | +0.081 |
ked | +0.081 |
Ow | +0.080 |
joy | +0.074 |
adoes | +0.073 |
Neg logit contributions | |
asis | -0.081 |
rig | -0.078 |
place | -0.075 |
row | -0.068 |
eh | -0.067 |
Token | waving |
Token ID | 25849 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
anish | +0.046 |
ked | +0.045 |
Ow | +0.045 |
adoes | +0.040 |
tant | +0.039 |
Neg logit contributions | |
asis | -0.038 |
rig | -0.036 |
called | -0.033 |
place | -0.033 |
secure | -0.032 |
Token | its |
Token ID | 663 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
arre | +0.045 |
anish | +0.044 |
Ow | +0.044 |
yles | +0.038 |
fault | +0.038 |
Neg logit contributions | |
called | -0.037 |
old | -0.036 |
asis | -0.034 |
row | -0.034 |
place | -0.033 |
Token | tail |
Token ID | 7894 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
ked | +0.059 |
anish | +0.058 |
joy | +0.056 |
Ow | +0.056 |
anymore | +0.056 |
Neg logit contributions | |
asis | -0.055 |
place | -0.052 |
rig | -0.052 |
row | -0.048 |
b | -0.045 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
Ow | +0.035 |
anish | +0.035 |
ked | +0.032 |
joy | +0.031 |
tant | +0.030 |
Neg logit contributions | |
asis | -0.041 |
rig | -0.039 |
place | -0.038 |
row | -0.037 |
eh | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
anish | +0.293 |
Ow | +0.285 |
ked | +0.273 |
arre | +0.264 |
Mine | +0.261 |
Neg logit contributions | |
asis | -0.279 |
rig | -0.269 |
place | -0.257 |
row | -0.250 |
fire | -0.236 |
Token | |
Token ID | 220 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ked | +0.022 |
anish | +0.021 |
Ow | +0.020 |
joy | +0.020 |
anymore | +0.020 |
Neg logit contributions | |
asis | -0.028 |
rig | -0.027 |
place | -0.026 |
row | -0.024 |
old | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
ked | +0.069 |
anish | +0.066 |
Ow | +0.066 |
joy | +0.063 |
anymore | +0.063 |
Neg logit contributions | |
asis | -0.106 |
rig | -0.100 |
place | -0.100 |
row | -0.091 |
eh | -0.090 |
Token |
|
Token ID | 198 |
Feature activation | +6.20e-02 |
Pos logit contributions | |
ked | +0.007 |
Ow | +0.007 |
anish | +0.007 |
joy | +0.007 |
anymore | +0.006 |
Neg logit contributions | |
asis | -0.013 |
place | -0.012 |
rig | -0.012 |
row | -0.011 |
eh | -0.011 |
Token | L |
Token ID | 43 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
asis | +0.003 |
rig | +0.003 |
place | +0.003 |
row | +0.003 |
eh | +0.002 |
Neg logit contributions | |
ked | -0.002 |
anish | -0.002 |
Ow | -0.002 |
joy | -0.002 |
anymore | -0.002 |
Token | L |
Token ID | 43 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
asis | +0.010 |
rig | +0.010 |
place | +0.009 |
row | +0.009 |
at | +0.009 |
Neg logit contributions | |
anish | -0.006 |
ked | -0.005 |
joy | -0.005 |
Ow | -0.005 |
Wow | -0.005 |
Token | ily |
Token ID | 813 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
ked | +0.018 |
anish | +0.017 |
Ow | +0.017 |
joy | +0.017 |
anymore | +0.017 |
Neg logit contributions | |
asis | -0.013 |
rig | -0.012 |
place | -0.012 |
row | -0.010 |
eh | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
asis | +0.076 |
rig | +0.074 |
place | +0.071 |
old | +0.067 |
row | +0.066 |
Neg logit contributions | |
ked | -0.045 |
anish | -0.043 |
Ow | -0.042 |
anymore | -0.041 |
joy | -0.040 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
ked | +0.021 |
anish | +0.021 |
Ow | +0.019 |
joy | +0.019 |
anymore | +0.019 |
Neg logit contributions | |
asis | -0.036 |
rig | -0.034 |
place | -0.034 |
old | -0.031 |
eh | -0.031 |
Token | wave |
Token ID | 6769 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
ked | +0.055 |
anish | +0.054 |
Ow | +0.053 |
joy | +0.052 |
anymore | +0.051 |
Neg logit contributions | |
asis | -0.061 |
rig | -0.059 |
place | -0.058 |
old | -0.052 |
row | -0.051 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.67e+00 |
Pos logit contributions | |
Ow | +0.044 |
anish | +0.044 |
ifying | +0.039 |
arre | +0.039 |
adoes | +0.039 |
Neg logit contributions | |
old | -0.045 |
rig | -0.043 |
called | -0.041 |
place | -0.041 |
row | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -6.25e-01 |
Pos logit contributions | |
anish | +0.267 |
Ow | +0.260 |
ked | +0.248 |
joy | +0.239 |
superstar | +0.236 |
Neg logit contributions | |
asis | -0.303 |
rig | -0.301 |
place | -0.289 |
row | -0.274 |
fire | -0.261 |
Token | They |
Token ID | 1119 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
anish | +0.020 |
ked | +0.020 |
tant | +0.018 |
Ow | +0.018 |
anymore | +0.018 |
Neg logit contributions | |
rig | -0.033 |
asis | -0.031 |
place | -0.030 |
old | -0.029 |
called | -0.029 |
Token | learn |
Token ID | 2193 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
asis | +0.008 |
rig | +0.007 |
place | +0.007 |
row | +0.007 |
eh | +0.007 |
Neg logit contributions | |
ked | -0.007 |
anish | -0.006 |
Ow | -0.006 |
anymore | -0.006 |
joy | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
rig | +0.010 |
asis | +0.010 |
place | +0.010 |
old | +0.010 |
row | +0.009 |
Neg logit contributions | |
ked | -0.007 |
anish | -0.006 |
Ow | -0.006 |
joy | -0.006 |
anymore | -0.006 |
Token | lesson |
Token ID | 11483 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
ked | +0.031 |
anish | +0.030 |
Ow | +0.029 |
joy | +0.029 |
anymore | +0.028 |
Neg logit contributions | |
asis | -0.034 |
rig | -0.033 |
place | -0.032 |
row | -0.029 |
old | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -4.03e-01 |
Pos logit contributions | |
anish | +0.161 |
Ow | +0.161 |
ked | +0.158 |
arre | +0.156 |
Mine | +0.150 |
Neg logit contributions | |
asis | -0.077 |
rig | -0.075 |
place | -0.070 |
fire | -0.066 |
called | -0.064 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ked | +0.017 |
anish | +0.016 |
anymore | +0.015 |
joy | +0.015 |
adoes | +0.015 |
Neg logit contributions | |
asis | -0.018 |
rig | -0.017 |
place | -0.016 |
old | -0.015 |
isin | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
asis | +0.062 |
rig | +0.061 |
place | +0.057 |
old | +0.054 |
row | +0.052 |
Neg logit contributions | |
ked | -0.041 |
anish | -0.040 |
Ow | -0.039 |
joy | -0.038 |
anymore | -0.037 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ked | +0.014 |
anish | +0.014 |
Ow | +0.013 |
joy | +0.013 |
anymore | +0.012 |
Neg logit contributions | |
asis | -0.033 |
rig | -0.032 |
place | -0.031 |
old | -0.029 |
eh | -0.029 |
Token | wave |
Token ID | 6769 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
anish | +0.077 |
joy | +0.075 |
ked | +0.074 |
Ow | +0.073 |
adoes | +0.072 |
Neg logit contributions | |
asis | -0.078 |
rig | -0.074 |
place | -0.071 |
old | -0.064 |
called | -0.063 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
anish | +0.057 |
Ow | +0.054 |
arre | +0.052 |
joy | +0.050 |
ifying | +0.049 |
Neg logit contributions | |
old | -0.042 |
rig | -0.040 |
called | -0.040 |
offer | -0.037 |
place | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
anish | +0.267 |
Ow | +0.256 |
ked | +0.247 |
joy | +0.242 |
arre | +0.239 |
Neg logit contributions | |
asis | -0.303 |
rig | -0.300 |
place | -0.283 |
row | -0.271 |
fire | -0.257 |
Token | They |
Token ID | 1119 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
anish | +0.020 |
ked | +0.020 |
tant | +0.018 |
arre | +0.018 |
anymore | +0.018 |
Neg logit contributions | |
asis | -0.029 |
rig | -0.029 |
place | -0.027 |
called | -0.025 |
old | -0.025 |
Token | have |
Token ID | 423 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
asis | +0.014 |
rig | +0.013 |
place | +0.013 |
row | +0.011 |
eh | +0.011 |
Neg logit contributions | |
ked | -0.013 |
anish | -0.013 |
Ow | -0.013 |
joy | -0.013 |
anymore | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
anish | +0.027 |
ked | +0.026 |
Ow | +0.025 |
tant | +0.025 |
adoes | +0.024 |
Neg logit contributions | |
asis | -0.025 |
place | -0.024 |
rig | -0.023 |
eh | -0.022 |
old | -0.021 |
Token | new |
Token ID | 649 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ked | +0.062 |
anish | +0.058 |
adoes | +0.057 |
Ow | +0.056 |
anymore | +0.053 |
Neg logit contributions | |
asis | -0.046 |
rig | -0.044 |
place | -0.044 |
called | -0.036 |
eh | -0.036 |
Token | They |
Token ID | 1119 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
ked | +0.029 |
anish | +0.028 |
tant | +0.027 |
ved | +0.026 |
prope | +0.026 |
Neg logit contributions | |
rig | -0.035 |
called | -0.030 |
place | -0.029 |
asis | -0.029 |
old | -0.029 |
Token | kissed |
Token ID | 27946 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
called | +0.001 |
place | +0.001 |
asis | +0.001 |
rig | +0.001 |
old | +0.001 |
Neg logit contributions | |
anish | -0.001 |
joy | -0.001 |
Ow | -0.001 |
adoes | -0.001 |
anymore | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
joy | +0.148 |
arre | +0.145 |
superstar | +0.144 |
anish | +0.143 |
yles | +0.133 |
Neg logit contributions | |
called | -0.118 |
ion | -0.101 |
aster | -0.097 |
row | -0.088 |
place | -0.088 |
Token | snow |
Token ID | 6729 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
asis | +0.049 |
place | +0.046 |
rig | +0.044 |
eh | +0.041 |
stump | +0.040 |
Neg logit contributions | |
ked | -0.045 |
anish | -0.042 |
Ow | -0.042 |
anymore | -0.041 |
joy | -0.040 |
Token | man |
Token ID | 805 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
asis | +0.056 |
row | +0.047 |
rig | +0.046 |
fire | +0.046 |
place | +0.044 |
Neg logit contributions | |
joy | -0.069 |
Ow | -0.067 |
anish | -0.064 |
arre | -0.063 |
ked | -0.062 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
Ow | +0.099 |
anish | +0.098 |
ked | +0.091 |
joy | +0.091 |
adoes | +0.087 |
Neg logit contributions | |
asis | -0.123 |
rig | -0.121 |
place | -0.117 |
row | -0.112 |
old | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
anish | +0.265 |
Ow | +0.261 |
ked | +0.243 |
Mine | +0.238 |
joy | +0.238 |
Neg logit contributions | |
asis | -0.299 |
rig | -0.296 |
row | -0.279 |
place | -0.278 |
called | -0.263 |
Token |
|
Token ID | 198 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
ked | +0.020 |
anish | +0.020 |
anymore | +0.019 |
tant | +0.018 |
Ow | +0.018 |
Neg logit contributions | |
rig | -0.032 |
asis | -0.031 |
place | -0.029 |
called | -0.028 |
old | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
Ow | +0.007 |
Look | +0.005 |
ked | +0.005 |
anish | +0.005 |
joy | +0.005 |
Neg logit contributions | |
asis | -0.022 |
place | -0.021 |
rig | -0.020 |
row | -0.019 |
at | -0.019 |
Token | They |
Token ID | 2990 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
Look | +0.001 |
anish | +0.001 |
ked | +0.001 |
Wow | +0.001 |
Ow | +0.000 |
Neg logit contributions | |
asis | -0.001 |
place | -0.001 |
rig | -0.001 |
at | -0.001 |
atmeal | -0.001 |
Token | took |
Token ID | 1718 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
asis | +0.009 |
rig | +0.009 |
place | +0.009 |
row | +0.008 |
old | +0.008 |
Neg logit contributions | |
anish | -0.008 |
ked | -0.008 |
Ow | -0.008 |
joy | -0.008 |
anymore | -0.008 |
Token | L |
Token ID | 43 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
asis | +0.020 |
rig | +0.019 |
place | +0.018 |
at | +0.017 |
eh | +0.016 |
Neg logit contributions | |
ked | -0.013 |
anish | -0.013 |
joy | -0.013 |
Ow | -0.012 |
anymore | -0.012 |
Token | ily |
Token ID | 813 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
ked | +0.010 |
anish | +0.009 |
Ow | +0.009 |
anymore | +0.009 |
joy | +0.009 |
Neg logit contributions | |
asis | -0.009 |
rig | -0.009 |
place | -0.008 |
row | -0.007 |
eh | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
rig | +0.079 |
asis | +0.078 |
place | +0.073 |
old | +0.070 |
eh | +0.067 |
Neg logit contributions | |
ked | -0.056 |
anish | -0.054 |
Ow | -0.052 |
anymore | -0.051 |
joy | -0.049 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
anish | +0.014 |
ked | +0.014 |
Ow | +0.013 |
anymore | +0.013 |
joy | +0.013 |
Neg logit contributions | |
asis | -0.022 |
rig | -0.021 |
place | -0.021 |
old | -0.020 |
eh | -0.019 |
Token | wave |
Token ID | 6769 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
ked | +0.046 |
anish | +0.046 |
Ow | +0.044 |
joy | +0.044 |
anymore | +0.043 |
Neg logit contributions | |
asis | -0.051 |
rig | -0.049 |
place | -0.048 |
old | -0.043 |
row | -0.042 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.63e+00 |
Pos logit contributions | |
anish | +0.045 |
Ow | +0.042 |
arre | +0.039 |
ifying | +0.039 |
adoes | +0.037 |
Neg logit contributions | |
old | -0.036 |
rig | -0.034 |
called | -0.033 |
place | -0.032 |
old | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
anish | +0.223 |
ked | +0.223 |
Ow | +0.215 |
joy | +0.208 |
anymore | +0.201 |
Neg logit contributions | |
asis | -0.345 |
rig | -0.336 |
place | -0.325 |
row | -0.305 |
old | -0.297 |
Token | the |
Token ID | 262 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
ked | +0.050 |
anish | +0.048 |
Ow | +0.046 |
joy | +0.045 |
anymore | +0.044 |
Neg logit contributions | |
asis | -0.069 |
rig | -0.066 |
place | -0.065 |
old | -0.059 |
row | -0.059 |
Token | z |
Token ID | 1976 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
ked | +0.008 |
joy | +0.007 |
Ow | +0.007 |
anish | +0.007 |
anymore | +0.007 |
Neg logit contributions | |
asis | -0.011 |
rig | -0.011 |
place | -0.011 |
row | -0.010 |
old | -0.010 |
Token | ebra |
Token ID | 37052 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
ked | +0.068 |
anish | +0.065 |
joy | +0.062 |
Ow | +0.062 |
anymore | +0.061 |
Neg logit contributions | |
asis | -0.073 |
rig | -0.073 |
place | -0.069 |
old | -0.062 |
row | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
ked | +0.024 |
anish | +0.023 |
anymore | +0.022 |
Ow | +0.022 |
joy | +0.022 |
Neg logit contributions | |
asis | -0.033 |
rig | -0.031 |
place | -0.031 |
row | -0.028 |
eh | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
ked | +0.130 |
anish | +0.125 |
Ow | +0.124 |
joy | +0.121 |
anymore | +0.117 |
Neg logit contributions | |
asis | -0.139 |
rig | -0.133 |
place | -0.129 |
row | -0.118 |
old | -0.116 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
ked | +0.021 |
anish | +0.020 |
tant | +0.019 |
anymore | +0.018 |
joy | +0.018 |
Neg logit contributions | |
rig | -0.025 |
asis | -0.024 |
place | -0.022 |
old | -0.022 |
aster | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
ked | +0.034 |
anish | +0.033 |
Ow | +0.032 |
joy | +0.031 |
anymore | +0.030 |
Neg logit contributions | |
asis | -0.067 |
rig | -0.064 |
place | -0.063 |
row | -0.058 |
eh | -0.058 |
Token | Mom |
Token ID | 11254 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
ked | +0.034 |
anish | +0.033 |
Ow | +0.031 |
joy | +0.031 |
anymore | +0.031 |
Neg logit contributions | |
asis | -0.043 |
rig | -0.042 |
place | -0.040 |
old | -0.038 |
eh | -0.038 |
Token | wave |
Token ID | 6769 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
ked | +0.017 |
anish | +0.016 |
Ow | +0.016 |
anymore | +0.016 |
joy | +0.015 |
Neg logit contributions | |
asis | -0.022 |
rig | -0.021 |
place | -0.021 |
row | -0.019 |
eh | -0.019 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.63e+00 |
Pos logit contributions | |
anish | +0.047 |
Ow | +0.045 |
arre | +0.043 |
adoes | +0.041 |
ifying | +0.040 |
Neg logit contributions | |
old | -0.041 |
rig | -0.039 |
called | -0.038 |
place | -0.037 |
old | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -5.60e-01 |
Pos logit contributions | |
anish | +0.231 |
ked | +0.226 |
Ow | +0.222 |
joy | +0.212 |
anymore | +0.204 |
Neg logit contributions | |
asis | -0.340 |
rig | -0.331 |
place | -0.319 |
row | -0.300 |
eh | -0.291 |
Token | They |
Token ID | 1119 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
ked | +0.020 |
anish | +0.019 |
tant | +0.018 |
anymore | +0.017 |
joy | +0.017 |
Neg logit contributions | |
asis | -0.029 |
rig | -0.028 |
place | -0.026 |
old | -0.025 |
called | -0.024 |
Token | are |
Token ID | 389 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
asis | +0.012 |
rig | +0.012 |
place | +0.012 |
row | +0.011 |
eh | +0.011 |
Neg logit contributions | |
ked | -0.010 |
anish | -0.009 |
Ow | -0.009 |
anymore | -0.009 |
joy | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
anish | +0.067 |
ked | +0.066 |
Ow | +0.064 |
tant | +0.061 |
joy | +0.061 |
Neg logit contributions | |
asis | -0.048 |
rig | -0.043 |
place | -0.042 |
eh | -0.039 |
old | -0.038 |
Token | too |
Token ID | 1165 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
ked | +0.024 |
anish | +0.024 |
Ow | +0.024 |
tant | +0.023 |
ifying | +0.022 |
Neg logit contributions | |
asis | -0.023 |
place | -0.022 |
rig | -0.021 |
called | -0.020 |
old | -0.020 |
Token | L |
Token ID | 43 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
asis | +0.014 |
rig | +0.013 |
place | +0.013 |
adow | +0.012 |
igator | +0.012 |
Neg logit contributions | |
anish | -0.005 |
ked | -0.005 |
Look | -0.005 |
Ow | -0.005 |
Wow | -0.005 |
Token | ila |
Token ID | 10102 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
ked | +0.009 |
anish | +0.009 |
Ow | +0.009 |
anymore | +0.009 |
joy | +0.009 |
Neg logit contributions | |
asis | -0.009 |
rig | -0.009 |
place | -0.008 |
fire | -0.008 |
stump | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
asis | +0.180 |
rig | +0.174 |
place | +0.170 |
row | +0.158 |
eh | +0.157 |
Neg logit contributions | |
ked | -0.091 |
anish | -0.086 |
Ow | -0.084 |
joy | -0.082 |
anymore | -0.081 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
ked | +0.012 |
anish | +0.012 |
Ow | +0.011 |
joy | +0.011 |
anymore | +0.011 |
Neg logit contributions | |
asis | -0.023 |
rig | -0.022 |
place | -0.021 |
old | -0.020 |
row | -0.020 |
Token | wave |
Token ID | 6769 |
Feature activation | -9.92e-01 |
Pos logit contributions | |
ked | +0.042 |
anish | +0.040 |
Ow | +0.039 |
joy | +0.038 |
anymore | +0.038 |
Neg logit contributions | |
asis | -0.064 |
rig | -0.062 |
place | -0.060 |
row | -0.056 |
eh | -0.055 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.60e+00 |
Pos logit contributions | |
anish | +0.044 |
Ow | +0.042 |
arre | +0.039 |
ifying | +0.038 |
adoes | +0.037 |
Neg logit contributions | |
old | -0.039 |
rig | -0.036 |
called | -0.035 |
place | -0.034 |
old | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
anish | +0.251 |
Ow | +0.242 |
ked | +0.242 |
joy | +0.230 |
arre | +0.221 |
Neg logit contributions | |
asis | -0.316 |
rig | -0.308 |
place | -0.296 |
row | -0.280 |
old | -0.269 |
Token | the |
Token ID | 262 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
ked | +0.046 |
anish | +0.043 |
Ow | +0.043 |
joy | +0.042 |
anymore | +0.042 |
Neg logit contributions | |
asis | -0.070 |
rig | -0.068 |
place | -0.066 |
row | -0.061 |
eh | -0.061 |
Token | lion |
Token ID | 18744 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ked | +0.008 |
anish | +0.008 |
Ow | +0.008 |
anymore | +0.007 |
joy | +0.007 |
Neg logit contributions | |
asis | -0.010 |
place | -0.009 |
rig | -0.009 |
eh | -0.008 |
row | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
ked | +0.105 |
anish | +0.102 |
Ow | +0.100 |
joy | +0.097 |
anymore | +0.095 |
Neg logit contributions | |
asis | -0.132 |
rig | -0.126 |
place | -0.122 |
row | -0.112 |
eh | -0.111 |
Token | They |
Token ID | 1119 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
ked | +0.014 |
anish | +0.013 |
Ow | +0.012 |
joy | +0.012 |
anymore | +0.012 |
Neg logit contributions | |
asis | -0.039 |
rig | -0.038 |
place | -0.037 |
row | -0.034 |
old | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
ked | +0.010 |
anish | +0.009 |
Ow | +0.009 |
joy | +0.009 |
anymore | +0.009 |
Neg logit contributions | |
asis | -0.012 |
rig | -0.012 |
place | -0.011 |
old | -0.010 |
row | -0.010 |
Token | car |
Token ID | 1097 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
asis | +0.024 |
rig | +0.023 |
place | +0.023 |
eh | +0.020 |
row | +0.020 |
Neg logit contributions | |
ked | -0.029 |
anish | -0.028 |
Ow | -0.027 |
joy | -0.027 |
anymore | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
ked | +0.034 |
anymore | +0.034 |
anish | +0.032 |
joy | +0.030 |
Ow | +0.029 |
Neg logit contributions | |
asis | -0.048 |
rig | -0.047 |
place | -0.044 |
isin | -0.042 |
eh | -0.042 |
Token | They |
Token ID | 1119 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
ked | +0.021 |
anish | +0.019 |
joy | +0.018 |
anymore | +0.018 |
Ow | +0.017 |
Neg logit contributions | |
rig | -0.032 |
asis | -0.032 |
place | -0.030 |
old | -0.029 |
eh | -0.027 |
Token | wave |
Token ID | 6769 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
asis | +0.010 |
rig | +0.009 |
place | +0.009 |
row | +0.008 |
eh | +0.008 |
Neg logit contributions | |
ked | -0.007 |
anish | -0.006 |
Ow | -0.006 |
anymore | -0.006 |
joy | -0.006 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
anish | +0.034 |
Ow | +0.031 |
arre | +0.030 |
ked | +0.029 |
joy | +0.028 |
Neg logit contributions | |
old | -0.033 |
rig | -0.032 |
place | -0.031 |
called | -0.030 |
asis | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
anish | +0.214 |
ked | +0.211 |
Ow | +0.206 |
joy | +0.196 |
anymore | +0.191 |
Neg logit contributions | |
asis | -0.352 |
rig | -0.343 |
place | -0.332 |
row | -0.312 |
eh | -0.305 |
Token | drive |
Token ID | 3708 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
ked | +0.024 |
anish | +0.023 |
Ow | +0.023 |
joy | +0.022 |
anymore | +0.022 |
Neg logit contributions | |
asis | -0.020 |
rig | -0.019 |
place | -0.019 |
row | -0.017 |
eh | -0.016 |
Token | away |
Token ID | 1497 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
anish | +0.073 |
ked | +0.072 |
Ow | +0.071 |
arre | +0.071 |
superstar | +0.069 |
Neg logit contributions | |
place | -0.069 |
old | -0.066 |
asis | -0.063 |
ion | -0.061 |
rig | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
ked | +0.126 |
Ow | +0.123 |
anish | +0.123 |
joy | +0.116 |
arre | +0.114 |
Neg logit contributions | |
asis | -0.094 |
rig | -0.091 |
place | -0.090 |
row | -0.077 |
fire | -0.077 |
Token | They |
Token ID | 1119 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
ked | +0.022 |
anish | +0.021 |
anymore | +0.019 |
tant | +0.019 |
joy | +0.019 |
Neg logit contributions | |
rig | -0.025 |
asis | -0.025 |
place | -0.024 |
old | -0.022 |
called | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
ked | +0.005 |
anish | +0.005 |
Ow | +0.004 |
joy | +0.004 |
anymore | +0.004 |
Neg logit contributions | |
asis | -0.007 |
rig | -0.006 |
place | -0.006 |
row | -0.006 |
eh | -0.006 |
Token | car |
Token ID | 1097 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
asis | +0.029 |
rig | +0.028 |
place | +0.026 |
row | +0.024 |
eh | +0.023 |
Neg logit contributions | |
ked | -0.035 |
anish | -0.034 |
Ow | -0.033 |
joy | -0.033 |
anymore | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
anymore | +0.026 |
ked | +0.025 |
again | +0.023 |
anish | +0.022 |
joy | +0.022 |
Neg logit contributions | |
asis | -0.044 |
rig | -0.044 |
isin | -0.041 |
place | -0.041 |
rim | -0.041 |
Token | They |
Token ID | 1119 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ked | +0.018 |
anish | +0.018 |
Ow | +0.017 |
joy | +0.016 |
anymore | +0.016 |
Neg logit contributions | |
asis | -0.029 |
rig | -0.029 |
place | -0.028 |
old | -0.025 |
eh | -0.025 |
Token | wave |
Token ID | 6769 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
asis | +0.011 |
rig | +0.011 |
place | +0.010 |
row | +0.010 |
eh | +0.010 |
Neg logit contributions | |
ked | -0.011 |
anish | -0.010 |
Ow | -0.010 |
anymore | -0.010 |
joy | -0.010 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
anish | +0.033 |
arre | +0.030 |
Ow | +0.030 |
superstar | +0.027 |
anymore | +0.027 |
Neg logit contributions | |
old | -0.030 |
rig | -0.029 |
place | -0.028 |
called | -0.028 |
ion | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
anish | +0.226 |
Ow | +0.216 |
ked | +0.215 |
joy | +0.202 |
arre | +0.197 |
Neg logit contributions | |
asis | -0.340 |
rig | -0.329 |
place | -0.322 |
row | -0.304 |
old | -0.294 |
Token | their |
Token ID | 511 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
ked | +0.048 |
anish | +0.046 |
Ow | +0.044 |
joy | +0.043 |
anymore | +0.042 |
Neg logit contributions | |
asis | -0.068 |
rig | -0.065 |
place | -0.064 |
row | -0.058 |
eh | -0.058 |
Token | old |
Token ID | 1468 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
ked | +0.094 |
anish | +0.092 |
Ow | +0.087 |
joy | +0.082 |
anymore | +0.081 |
Neg logit contributions | |
asis | -0.110 |
rig | -0.104 |
place | -0.104 |
old | -0.090 |
row | -0.090 |
Token | house |
Token ID | 2156 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
asis | +0.024 |
place | +0.022 |
rig | +0.022 |
eh | +0.020 |
row | +0.020 |
Neg logit contributions | |
ked | -0.023 |
anish | -0.022 |
Ow | -0.022 |
ifying | -0.021 |
anymore | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -8.74e-01 |
Pos logit contributions | |
asis | +0.050 |
rig | +0.049 |
place | +0.047 |
row | +0.043 |
old | +0.043 |
Neg logit contributions | |
ked | -0.045 |
anish | -0.044 |
Ow | -0.044 |
joy | -0.042 |
anymore | -0.040 |
Token | den |
Token ID | 6559 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
ked | +0.004 |
Ow | +0.004 |
anish | +0.004 |
anymore | +0.003 |
joy | +0.003 |
Neg logit contributions | |
asis | -0.004 |
rig | -0.004 |
place | -0.003 |
row | -0.003 |
old | -0.003 |
Token | hugged |
Token ID | 41130 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ked | +0.020 |
anish | +0.019 |
Ow | +0.018 |
joy | +0.018 |
anymore | +0.018 |
Neg logit contributions | |
asis | -0.029 |
rig | -0.028 |
place | -0.027 |
row | -0.025 |
eh | -0.025 |
Token | Mrs |
Token ID | 9074 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
anish | +0.078 |
ked | +0.078 |
arre | +0.075 |
Ow | +0.072 |
ifying | +0.070 |
Neg logit contributions | |
asis | -0.063 |
rig | -0.062 |
place | -0.061 |
old | -0.058 |
called | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ked | +0.059 |
anish | +0.059 |
Ow | +0.057 |
arre | +0.056 |
tant | +0.056 |
Neg logit contributions | |
asis | -0.048 |
rig | -0.047 |
place | -0.045 |
row | -0.041 |
old | -0.041 |
Token | Bell |
Token ID | 7459 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
ked | +0.005 |
anish | +0.005 |
Ow | +0.005 |
anymore | +0.005 |
tant | +0.005 |
Neg logit contributions | |
asis | -0.007 |
rig | -0.006 |
place | -0.006 |
row | -0.006 |
stump | -0.006 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
anish | +0.049 |
Ow | +0.049 |
ked | +0.048 |
joy | +0.045 |
adoes | +0.045 |
Neg logit contributions | |
asis | -0.063 |
rig | -0.061 |
place | -0.059 |
row | -0.055 |
old | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
anish | +0.236 |
ked | +0.233 |
Ow | +0.232 |
joy | +0.213 |
anymore | +0.211 |
Neg logit contributions | |
asis | -0.327 |
rig | -0.316 |
place | -0.305 |
row | -0.286 |
old | -0.279 |
Token | Jay |
Token ID | 9180 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
ked | +0.021 |
anish | +0.020 |
Ow | +0.020 |
joy | +0.020 |
anymore | +0.019 |
Neg logit contributions | |
asis | -0.031 |
rig | -0.030 |
place | -0.030 |
row | -0.027 |
eh | -0.027 |
Token | den |
Token ID | 6559 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
Ow | +0.027 |
ked | +0.026 |
anish | +0.026 |
anymore | +0.025 |
joy | +0.025 |
Neg logit contributions | |
asis | -0.032 |
rig | -0.031 |
place | -0.029 |
row | -0.028 |
old | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
ked | +0.034 |
anish | +0.032 |
Ow | +0.031 |
joy | +0.031 |
anymore | +0.031 |
Neg logit contributions | |
asis | -0.052 |
rig | -0.050 |
place | -0.048 |
row | -0.045 |
eh | -0.044 |
Token | proud |
Token ID | 6613 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
ked | +0.024 |
anish | +0.023 |
joy | +0.023 |
Ow | +0.023 |
anymore | +0.022 |
Neg logit contributions | |
asis | -0.026 |
rig | -0.025 |
place | -0.024 |
row | -0.022 |
eh | -0.022 |
Token | dog |
Token ID | 3290 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
asis | +0.025 |
rig | +0.025 |
place | +0.023 |
old | +0.022 |
eh | +0.021 |
Neg logit contributions | |
ked | -0.016 |
joy | -0.016 |
anish | -0.015 |
anymore | -0.015 |
Ow | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
ked | +0.069 |
anymore | +0.064 |
anish | +0.062 |
Ow | +0.060 |
joy | +0.060 |
Neg logit contributions | |
asis | -0.117 |
rig | -0.113 |
place | -0.110 |
isin | -0.101 |
eh | -0.101 |
Token | gave |
Token ID | 2921 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
anish | +0.034 |
ked | +0.033 |
Ow | +0.033 |
anymore | +0.032 |
joy | +0.032 |
Neg logit contributions | |
asis | -0.034 |
rig | -0.033 |
place | -0.032 |
eh | -0.029 |
row | -0.029 |
Token | it |
Token ID | 340 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
anish | +0.020 |
ked | +0.019 |
arre | +0.018 |
joy | +0.018 |
Ow | +0.018 |
Neg logit contributions | |
asis | -0.028 |
place | -0.028 |
rig | -0.027 |
old | -0.027 |
row | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -3.09e-01 |
Pos logit contributions | |
asis | +0.085 |
rig | +0.082 |
place | +0.078 |
isin | +0.075 |
rim | +0.073 |
Neg logit contributions | |
ked | -0.035 |
Ow | -0.031 |
joy | -0.030 |
anymore | -0.030 |
anish | -0.030 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.54e+00 |
Pos logit contributions | |
ked | +0.012 |
anish | +0.011 |
Ow | +0.011 |
joy | +0.011 |
anymore | +0.011 |
Neg logit contributions | |
asis | -0.015 |
rig | -0.014 |
place | -0.014 |
row | -0.013 |
old | -0.012 |
Token | hug |
Token ID | 16225 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
ked | +0.285 |
anish | +0.280 |
Ow | +0.274 |
joy | +0.264 |
anymore | +0.259 |
Neg logit contributions | |
asis | -0.283 |
rig | -0.268 |
place | -0.260 |
row | -0.238 |
eh | -0.231 |
Token | . |
Token ID | 13 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
ked | +0.116 |
Ow | +0.115 |
anish | +0.114 |
joy | +0.110 |
arre | +0.106 |
Neg logit contributions | |
asis | -0.088 |
rig | -0.081 |
place | -0.081 |
row | -0.076 |
old | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
ked | +0.012 |
Ow | +0.012 |
joy | +0.012 |
anish | +0.012 |
anymore | +0.011 |
Neg logit contributions | |
asis | -0.022 |
place | -0.021 |
rig | -0.021 |
row | -0.019 |
eh | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Ow | +0.004 |
ked | +0.003 |
anish | +0.003 |
joy | +0.003 |
Look | +0.003 |
Neg logit contributions | |
asis | -0.008 |
place | -0.008 |
rig | -0.007 |
row | -0.007 |
stump | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
asis | +0.005 |
rig | +0.005 |
place | +0.005 |
row | +0.005 |
old | +0.004 |
Neg logit contributions | |
ked | -0.004 |
anish | -0.004 |
Ow | -0.004 |
joy | -0.004 |
anymore | -0.004 |
Token | L |
Token ID | 43 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
asis | +0.015 |
rig | +0.014 |
place | +0.014 |
row | +0.013 |
eh | +0.013 |
Neg logit contributions | |
ked | -0.009 |
anish | -0.008 |
Ow | -0.008 |
joy | -0.008 |
anymore | -0.008 |
Token | ily |
Token ID | 813 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
ked | +0.011 |
anish | +0.011 |
Ow | +0.011 |
joy | +0.011 |
anymore | +0.011 |
Neg logit contributions | |
asis | -0.009 |
rig | -0.009 |
place | -0.009 |
row | -0.008 |
eh | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
asis | +0.082 |
rig | +0.079 |
place | +0.077 |
row | +0.072 |
eh | +0.071 |
Neg logit contributions | |
ked | -0.043 |
anish | -0.040 |
Ow | -0.039 |
joy | -0.038 |
anymore | -0.038 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
anish | +0.016 |
ked | +0.015 |
joy | +0.015 |
Ow | +0.014 |
superstar | +0.014 |
Neg logit contributions | |
asis | -0.026 |
rig | -0.025 |
place | -0.025 |
old | -0.024 |
aster | -0.024 |
Token | wave |
Token ID | 6769 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
ked | +0.056 |
anish | +0.053 |
Ow | +0.052 |
joy | +0.052 |
anymore | +0.051 |
Neg logit contributions | |
asis | -0.050 |
rig | -0.048 |
place | -0.046 |
row | -0.041 |
eh | -0.041 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
anish | +0.038 |
Ow | +0.037 |
ifying | +0.035 |
arre | +0.034 |
prope | +0.033 |
Neg logit contributions | |
old | -0.033 |
rig | -0.031 |
place | -0.031 |
called | -0.030 |
old | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
anish | +0.274 |
ked | +0.269 |
Ow | +0.266 |
joy | +0.256 |
superstar | +0.247 |
Neg logit contributions | |
asis | -0.284 |
rig | -0.277 |
place | -0.267 |
row | -0.249 |
old | -0.238 |
Token | They |
Token ID | 1119 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
anish | +0.015 |
ked | +0.014 |
Ow | +0.013 |
tant | +0.013 |
joy | +0.013 |
Neg logit contributions | |
rig | -0.024 |
asis | -0.023 |
place | -0.022 |
called | -0.021 |
old | -0.021 |
Token | put |
Token ID | 1234 |
Feature activation | +7.94e-01 |
Pos logit contributions | |
asis | +0.014 |
rig | +0.013 |
place | +0.013 |
row | +0.012 |
eh | +0.012 |
Neg logit contributions | |
ked | -0.012 |
Ow | -0.011 |
anymore | -0.011 |
anish | -0.011 |
joy | -0.011 |
Token | on |
Token ID | 319 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
asis | +0.036 |
place | +0.035 |
rig | +0.034 |
ion | +0.032 |
row | +0.032 |
Neg logit contributions | |
anish | -0.031 |
ked | -0.029 |
Ow | -0.029 |
arre | -0.028 |
joy | -0.028 |
Token | their |
Token ID | 511 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
anish | +0.043 |
ked | +0.040 |
superstar | +0.037 |
joy | +0.036 |
arre | +0.036 |
Neg logit contributions | |
place | -0.059 |
asis | -0.058 |
rig | -0.058 |
old | -0.054 |
aster | -0.053 |
Token | ground |
Token ID | 2323 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
ked | +0.024 |
Ow | +0.024 |
anish | +0.024 |
anymore | +0.024 |
joy | +0.023 |
Neg logit contributions | |
rig | -0.019 |
asis | -0.019 |
place | -0.017 |
old | -0.016 |
row | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
asis | +0.140 |
rig | +0.135 |
place | +0.132 |
row | +0.122 |
eh | +0.121 |
Neg logit contributions | |
ked | -0.089 |
anish | -0.085 |
Ow | -0.083 |
joy | -0.081 |
anymore | -0.079 |
Token | said |
Token ID | 531 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Ow | +0.044 |
anish | +0.043 |
ked | +0.043 |
joy | +0.043 |
anymore | +0.039 |
Neg logit contributions | |
asis | -0.049 |
place | -0.046 |
rig | -0.046 |
called | -0.046 |
fire | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
old | +0.040 |
asis | +0.039 |
place | +0.038 |
called | +0.037 |
row | +0.037 |
Neg logit contributions | |
Ow | -0.058 |
ked | -0.058 |
ifying | -0.057 |
arre | -0.056 |
joy | -0.055 |
Token | special |
Token ID | 2041 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
ked | +0.008 |
anish | +0.008 |
Ow | +0.007 |
anymore | +0.007 |
joy | +0.007 |
Neg logit contributions | |
asis | -0.009 |
rig | -0.009 |
place | -0.008 |
row | -0.007 |
eh | -0.007 |
Token | goodbye |
Token ID | 24829 |
Feature activation | -6.52e+00 |
Pos logit contributions | |
ked | +0.027 |
anish | +0.026 |
Ow | +0.025 |
joy | +0.025 |
anymore | +0.025 |
Neg logit contributions | |
asis | -0.032 |
rig | -0.031 |
place | -0.030 |
row | -0.027 |
eh | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
ked | +0.266 |
anish | +0.264 |
Ow | +0.259 |
joy | +0.246 |
anymore | +0.241 |
Neg logit contributions | |
asis | -0.296 |
rig | -0.283 |
place | -0.273 |
row | -0.254 |
eh | -0.245 |
Token |
|
Token ID | 198 |
Feature activation | +8.60e-02 |
Pos logit contributions | |
ked | +0.008 |
anish | +0.008 |
prope | +0.007 |
anymore | +0.007 |
Ow | +0.007 |
Neg logit contributions | |
rig | -0.009 |
asis | -0.009 |
place | -0.008 |
old | -0.008 |
eh | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
asis | +0.005 |
place | +0.005 |
rig | +0.005 |
row | +0.004 |
eh | +0.004 |
Neg logit contributions | |
Ow | -0.002 |
anish | -0.002 |
ked | -0.002 |
anymore | -0.002 |
joy | -0.002 |
Token | Jack |
Token ID | 14295 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
asis | +0.014 |
rig | +0.013 |
place | +0.013 |
eh | +0.012 |
old | +0.012 |
Neg logit contributions | |
ked | -0.013 |
anish | -0.013 |
Ow | -0.012 |
joy | -0.012 |
anymore | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
ked | +0.021 |
anish | +0.020 |
Ow | +0.019 |
joy | +0.018 |
anymore | +0.018 |
Neg logit contributions | |
asis | -0.035 |
rig | -0.034 |
place | -0.033 |
eh | -0.030 |
isin | -0.030 |
Token | there |
Token ID | 612 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
ked | +0.054 |
anish | +0.050 |
Ow | +0.045 |
adoes | +0.045 |
joy | +0.044 |
Neg logit contributions | |
asis | -0.099 |
rig | -0.097 |
place | -0.093 |
old | -0.091 |
row | -0.089 |
Token | was |
Token ID | 373 |
Feature activation | +4.40e-01 |
Pos logit contributions | |
ked | +0.018 |
anish | +0.017 |
Ow | +0.016 |
joy | +0.016 |
adoes | +0.016 |
Neg logit contributions | |
asis | -0.024 |
rig | -0.022 |
place | -0.022 |
old | -0.020 |
row | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
asis | +0.021 |
place | +0.020 |
rig | +0.020 |
eh | +0.019 |
old | +0.019 |
Neg logit contributions | |
ked | -0.017 |
anish | -0.016 |
joy | -0.015 |
adoes | -0.015 |
anymore | -0.015 |
Token | little |
Token ID | 1310 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
ked | +0.006 |
anish | +0.005 |
Ow | +0.005 |
joy | +0.005 |
anymore | +0.005 |
Neg logit contributions | |
asis | -0.009 |
rig | -0.009 |
place | -0.009 |
row | -0.008 |
eh | -0.008 |
Token | girl |
Token ID | 2576 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
asis | +0.033 |
rig | +0.032 |
place | +0.031 |
row | +0.029 |
eh | +0.029 |
Neg logit contributions | |
ked | -0.015 |
anish | -0.014 |
Ow | -0.014 |
joy | -0.014 |
anymore | -0.014 |
Token | called |
Token ID | 1444 |
Feature activation | +5.43e+00 |
Pos logit contributions | |
asis | +0.038 |
rig | +0.036 |
place | +0.033 |
isin | +0.032 |
row | +0.030 |
Neg logit contributions | |
anymore | -0.027 |
ked | -0.026 |
joy | -0.025 |
anish | -0.024 |
Ow | -0.023 |
Token | Penny |
Token ID | 25965 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
asis | +0.301 |
rig | +0.286 |
place | +0.278 |
row | +0.256 |
isin | +0.251 |
Neg logit contributions | |
ked | -0.178 |
anish | -0.173 |
Ow | -0.172 |
anymore | -0.167 |
joy | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
asis | +0.086 |
rig | +0.079 |
place | +0.077 |
isin | +0.076 |
rim | +0.073 |
Neg logit contributions | |
ked | -0.037 |
anymore | -0.036 |
joy | -0.032 |
again | -0.030 |
Ow | -0.029 |
Token | Penny |
Token ID | 25965 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
rig | +0.022 |
place | +0.022 |
asis | +0.022 |
row | +0.019 |
called | +0.019 |
Neg logit contributions | |
ked | -0.026 |
anish | -0.024 |
prope | -0.023 |
Ow | -0.023 |
adoes | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | +6.70e-01 |
Pos logit contributions | |
ked | +0.004 |
Ow | +0.003 |
anymore | +0.003 |
anish | +0.003 |
joy | +0.003 |
Neg logit contributions | |
asis | -0.009 |
rig | -0.009 |
place | -0.009 |
row | -0.008 |
isin | -0.008 |
Token | three |
Token ID | 1115 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
asis | +0.034 |
rig | +0.033 |
place | +0.032 |
row | +0.030 |
eh | +0.029 |
Neg logit contributions | |
ked | -0.024 |
anish | -0.023 |
Ow | -0.023 |
joy | -0.023 |
anymore | -0.022 |
Token | whispered |
Token ID | 25029 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
ked | +0.039 |
anish | +0.039 |
Ow | +0.038 |
anymore | +0.037 |
joy | +0.036 |
Neg logit contributions | |
asis | -0.040 |
rig | -0.039 |
place | -0.037 |
row | -0.034 |
eh | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
asis | +0.034 |
row | +0.033 |
place | +0.033 |
rig | +0.032 |
b | +0.030 |
Neg logit contributions | |
Ow | -0.038 |
anish | -0.038 |
arre | -0.037 |
Goal | -0.036 |
Mine | -0.035 |
Token | " |
Token ID | 366 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
asis | +0.026 |
rig | +0.025 |
place | +0.024 |
row | +0.022 |
eh | +0.022 |
Neg logit contributions | |
anish | -0.013 |
ked | -0.013 |
Ow | -0.013 |
anymore | -0.012 |
joy | -0.012 |
Token | Are |
Token ID | 8491 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
ked | +0.049 |
anymore | +0.047 |
anish | +0.047 |
joy | +0.046 |
Ow | +0.045 |
Neg logit contributions | |
asis | -0.077 |
rig | -0.075 |
place | -0.072 |
row | -0.066 |
eh | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
ked | +0.015 |
anish | +0.014 |
joy | +0.014 |
tant | +0.014 |
Ow | +0.014 |
Neg logit contributions | |
asis | -0.007 |
rig | -0.007 |
place | -0.007 |
isin | -0.006 |
row | -0.005 |
Token | leaves |
Token ID | 5667 |
Feature activation | +5.56e+00 |
Pos logit contributions | |
asis | +0.138 |
rig | +0.132 |
place | +0.128 |
row | +0.116 |
old | +0.114 |
Neg logit contributions | |
ked | -0.142 |
anish | -0.137 |
Ow | -0.135 |
joy | -0.133 |
anymore | -0.133 |
Token | talking |
Token ID | 3375 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
asis | +0.263 |
rig | +0.262 |
place | +0.250 |
old | +0.241 |
eh | +0.229 |
Neg logit contributions | |
ked | -0.205 |
anymore | -0.203 |
anish | -0.198 |
Ow | -0.193 |
adoes | -0.185 |
Token | ?" |
Token ID | 1701 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
ked | +0.047 |
joy | +0.045 |
anish | +0.044 |
Ow | +0.043 |
tant | +0.040 |
Neg logit contributions | |
asis | -0.054 |
rig | -0.052 |
place | -0.051 |
row | -0.047 |
eh | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
asis | +0.041 |
rig | +0.039 |
place | +0.039 |
row | +0.036 |
eh | +0.035 |
Neg logit contributions | |
ked | -0.024 |
joy | -0.024 |
anish | -0.023 |
Ow | -0.023 |
anymore | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
asis | +0.034 |
rig | +0.032 |
place | +0.032 |
row | +0.029 |
eh | +0.028 |
Neg logit contributions | |
Ow | -0.017 |
anish | -0.016 |
ked | -0.016 |
joy | -0.016 |
anymore | -0.015 |
Token | His |
Token ID | 6653 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
asis | +0.033 |
rig | +0.032 |
place | +0.031 |
row | +0.028 |
isin | +0.027 |
Neg logit contributions | |
anish | -0.024 |
ked | -0.024 |
Ow | -0.023 |
joy | -0.023 |
Look | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
asis | +0.029 |
rig | +0.028 |
place | +0.027 |
row | +0.024 |
eh | +0.024 |
Neg logit contributions | |
ked | -0.029 |
anish | -0.028 |
Ow | -0.028 |
joy | -0.027 |
anymore | -0.027 |
Token | Lib |
Token ID | 7980 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
asis | +0.020 |
place | +0.018 |
rig | +0.018 |
old | +0.017 |
stump | +0.015 |
Neg logit contributions | |
ked | -0.026 |
anish | -0.026 |
arre | -0.025 |
tant | -0.025 |
adoes | -0.024 |
Token | by |
Token ID | 1525 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ked | +0.005 |
anish | +0.005 |
Ow | +0.005 |
joy | +0.005 |
adoes | +0.005 |
Neg logit contributions | |
asis | -0.008 |
rig | -0.008 |
place | -0.008 |
old | -0.007 |
row | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
anish | +0.024 |
ked | +0.024 |
Ow | +0.023 |
joy | +0.022 |
anymore | +0.022 |
Neg logit contributions | |
rig | -0.061 |
asis | -0.060 |
place | -0.058 |
isin | -0.054 |
row | -0.054 |
Token | three |
Token ID | 1115 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
asis | +0.025 |
rig | +0.024 |
place | +0.023 |
row | +0.022 |
old | +0.021 |
Neg logit contributions | |
ked | -0.017 |
Ow | -0.016 |
joy | -0.016 |
anish | -0.016 |
anymore | -0.015 |
Token | years |
Token ID | 812 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
asis | +0.039 |
rig | +0.036 |
place | +0.032 |
row | +0.030 |
eh | +0.028 |
Neg logit contributions | |
anymore | -0.069 |
ked | -0.069 |
joy | -0.068 |
anish | -0.066 |
tant | -0.065 |
Token | old |
Token ID | 1468 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
asis | +0.225 |
rig | +0.206 |
eling | +0.196 |
place | +0.188 |
fire | +0.182 |
Neg logit contributions | |
joy | -0.187 |
at | -0.180 |
eyes | -0.175 |
anymore | -0.174 |
heart | -0.156 |
Token | and |
Token ID | 290 |
Feature activation | +8.98e-01 |
Pos logit contributions | |
asis | +0.167 |
place | +0.161 |
rig | +0.157 |
old | +0.143 |
row | +0.142 |
Neg logit contributions | |
anish | -0.155 |
ked | -0.155 |
Ow | -0.148 |
joy | -0.139 |
arre | -0.138 |
Token | loved |
Token ID | 6151 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
asis | +0.061 |
rig | +0.060 |
place | +0.056 |
row | +0.055 |
rim | +0.054 |
Neg logit contributions | |
ked | -0.017 |
Wow | -0.016 |
Look | -0.015 |
joy | -0.015 |
superstar | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
ked | +0.002 |
anish | +0.002 |
Ow | +0.002 |
joy | +0.002 |
anymore | +0.001 |
Neg logit contributions | |
asis | -0.003 |
rig | -0.003 |
place | -0.003 |
row | -0.003 |
eh | -0.003 |
Token | pick |
Token ID | 2298 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
rig | +0.031 |
asis | +0.031 |
place | +0.028 |
row | +0.028 |
isin | +0.027 |
Neg logit contributions | |
Ow | -0.020 |
anish | -0.020 |
ked | -0.019 |
anymore | -0.019 |
guys | -0.019 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ked | +0.010 |
anish | +0.010 |
Ow | +0.009 |
joy | +0.009 |
anymore | +0.009 |
Neg logit contributions | |
asis | -0.015 |
rig | -0.015 |
place | -0.015 |
eh | -0.013 |
row | -0.013 |
Token | two |
Token ID | 734 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
ked | +0.005 |
anish | +0.005 |
Ow | +0.005 |
joy | +0.004 |
anymore | +0.004 |
Neg logit contributions | |
asis | -0.006 |
place | -0.006 |
rig | -0.006 |
old | -0.006 |
eh | -0.006 |
Token | gates |
Token ID | 17435 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
ked | +0.028 |
anish | +0.028 |
Ow | +0.027 |
joy | +0.026 |
anymore | +0.025 |
Neg logit contributions | |
asis | -0.033 |
place | -0.031 |
rig | -0.031 |
eh | -0.028 |
row | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
asis | +0.154 |
rig | +0.147 |
place | +0.143 |
row | +0.130 |
eh | +0.129 |
Neg logit contributions | |
ked | -0.133 |
anish | -0.128 |
Ow | -0.125 |
joy | -0.123 |
anymore | -0.122 |
Token | One |
Token ID | 1881 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
ked | +0.001 |
anish | +0.001 |
Ow | +0.001 |
joy | +0.001 |
anymore | +0.001 |
Neg logit contributions | |
asis | -0.002 |
rig | -0.002 |
place | -0.002 |
old | -0.002 |
eh | -0.002 |
Token | gate |
Token ID | 8946 |
Feature activation | +4.17e+00 |
Pos logit contributions | |
asis | +0.044 |
rig | +0.041 |
isin | +0.040 |
place | +0.039 |
ands | +0.038 |
Neg logit contributions | |
anymore | -0.036 |
ked | -0.034 |
anish | -0.034 |
Ow | -0.033 |
joy | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
asis | +0.179 |
place | +0.169 |
rig | +0.165 |
row | +0.156 |
old | +0.155 |
Neg logit contributions | |
Ow | -0.179 |
ked | -0.178 |
anish | -0.173 |
joy | -0.172 |
tant | -0.164 |
Token | small |
Token ID | 1402 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
asis | +0.034 |
rig | +0.033 |
place | +0.032 |
row | +0.029 |
eh | +0.029 |
Neg logit contributions | |
ked | -0.032 |
anish | -0.031 |
Ow | -0.031 |
joy | -0.030 |
anymore | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
place | +0.127 |
asis | +0.125 |
rig | +0.120 |
called | +0.112 |
old | +0.110 |
Neg logit contributions | |
Ow | -0.122 |
ked | -0.120 |
anish | -0.119 |
joy | -0.108 |
Goal | -0.106 |
Token | blue |
Token ID | 4171 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
asis | +0.043 |
place | +0.042 |
rig | +0.041 |
called | +0.038 |
stump | +0.037 |
Neg logit contributions | |
ked | -0.044 |
anish | -0.044 |
Ow | -0.043 |
joy | -0.041 |
anymore | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
asis | +0.042 |
place | +0.040 |
rig | +0.037 |
row | +0.036 |
called | +0.035 |
Neg logit contributions | |
ked | -0.049 |
Ow | -0.048 |
joy | -0.048 |
anish | -0.047 |
tant | -0.047 |
Token | ie |
Token ID | 494 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
asis | +0.058 |
rig | +0.054 |
place | +0.052 |
row | +0.045 |
eh | +0.044 |
Neg logit contributions | |
ked | -0.124 |
anish | -0.121 |
Ow | -0.119 |
joy | -0.118 |
anymore | -0.116 |
Token | and |
Token ID | 290 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
asis | +0.150 |
rig | +0.140 |
place | +0.136 |
isin | +0.126 |
row | +0.125 |
Neg logit contributions | |
anymore | -0.082 |
ked | -0.082 |
joy | -0.073 |
anish | -0.071 |
Ow | -0.070 |
Token | she |
Token ID | 673 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
asis | +0.046 |
rig | +0.045 |
place | +0.043 |
row | +0.039 |
eh | +0.038 |
Neg logit contributions | |
ked | -0.039 |
anish | -0.037 |
Ow | -0.037 |
joy | -0.036 |
anymore | -0.036 |
Token | was |
Token ID | 373 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
ked | +0.011 |
anish | +0.010 |
anymore | +0.010 |
superstar | +0.010 |
Ow | +0.009 |
Neg logit contributions | |
asis | -0.027 |
rig | -0.027 |
place | -0.026 |
row | -0.025 |
isin | -0.024 |
Token | 3 |
Token ID | 513 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
asis | +0.008 |
rig | +0.008 |
place | +0.007 |
row | +0.007 |
old | +0.006 |
Neg logit contributions | |
ked | -0.008 |
anish | -0.008 |
Ow | -0.008 |
joy | -0.008 |
anymore | -0.008 |
Token | years |
Token ID | 812 |
Feature activation | +4.94e+00 |
Pos logit contributions | |
asis | +0.021 |
rig | +0.019 |
place | +0.018 |
row | +0.015 |
eh | +0.014 |
Neg logit contributions | |
ked | -0.048 |
anymore | -0.047 |
anish | -0.047 |
joy | -0.047 |
Ow | -0.046 |
Token | old |
Token ID | 1468 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
asis | +0.241 |
rig | +0.205 |
at | +0.198 |
eling | +0.194 |
roads | +0.194 |
Neg logit contributions | |
anymore | -0.200 |
joy | -0.200 |
eyes | -0.193 |
asleep | -0.188 |
at | -0.186 |
Token | . |
Token ID | 13 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
asis | +0.130 |
place | +0.128 |
rig | +0.124 |
called | +0.112 |
old | +0.109 |
Neg logit contributions | |
anish | -0.194 |
ked | -0.192 |
Ow | -0.186 |
arre | -0.177 |
adoes | -0.176 |
Token |
|
Token ID | 198 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
asis | +0.022 |
rig | +0.021 |
place | +0.021 |
row | +0.019 |
eh | +0.019 |
Neg logit contributions | |
ked | -0.015 |
anish | -0.014 |
Ow | -0.014 |
joy | -0.014 |
anymore | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
asis | +0.026 |
rig | +0.025 |
place | +0.025 |
old | +0.023 |
row | +0.022 |
Neg logit contributions | |
ked | -0.023 |
anish | -0.021 |
Ow | -0.021 |
joy | -0.020 |
anymore | -0.020 |
Token | One |
Token ID | 3198 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
asis | +0.038 |
rig | +0.036 |
place | +0.034 |
row | +0.032 |
eh | +0.031 |
Neg logit contributions | |
ked | -0.031 |
anish | -0.031 |
Ow | -0.030 |
joy | -0.030 |
anymore | -0.030 |
Token | appreciate |
Token ID | 9144 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ked | +0.028 |
anymore | +0.028 |
joy | +0.028 |
Ow | +0.028 |
anish | +0.027 |
Neg logit contributions | |
rig | -0.031 |
asis | -0.030 |
place | -0.028 |
row | -0.027 |
old | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
ked | +0.022 |
anish | +0.021 |
Ow | +0.021 |
joy | +0.020 |
anymore | +0.020 |
Neg logit contributions | |
asis | -0.028 |
rig | -0.027 |
place | -0.027 |
row | -0.024 |
eh | -0.024 |
Token | beauty |
Token ID | 8737 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
asis | +0.057 |
rig | +0.054 |
place | +0.052 |
row | +0.049 |
eh | +0.048 |
Neg logit contributions | |
ked | -0.059 |
anish | -0.057 |
joy | -0.057 |
Ow | -0.057 |
anymore | -0.056 |
Token | of |
Token ID | 286 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
asis | +0.008 |
rig | +0.008 |
place | +0.007 |
eh | +0.007 |
row | +0.007 |
Neg logit contributions | |
ked | -0.008 |
anymore | -0.008 |
anish | -0.007 |
joy | -0.007 |
Ow | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
ked | +0.046 |
anish | +0.044 |
Ow | +0.043 |
joy | +0.043 |
anymore | +0.043 |
Neg logit contributions | |
asis | -0.067 |
rig | -0.066 |
place | -0.063 |
row | -0.059 |
eh | -0.058 |
Token | me |
Token ID | 502 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
asis | +0.031 |
rig | +0.030 |
place | +0.028 |
row | +0.027 |
old | +0.027 |
Neg logit contributions | |
ked | -0.027 |
joy | -0.027 |
Ow | -0.027 |
anymore | -0.026 |
anish | -0.026 |
Token | adow |
Token ID | 4584 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
place | +0.028 |
rig | +0.028 |
asis | +0.028 |
pharmacy | +0.025 |
isin | +0.024 |
Neg logit contributions | |
anymore | -0.072 |
joy | -0.069 |
ked | -0.065 |
again | -0.065 |
ved | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
asis | +0.160 |
rig | +0.154 |
place | +0.150 |
row | +0.136 |
eh | +0.135 |
Neg logit contributions | |
ked | -0.132 |
anish | -0.126 |
Ow | -0.123 |
joy | -0.122 |
anymore | -0.121 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
Ow | +0.008 |
ked | +0.008 |
anish | +0.007 |
joy | +0.007 |
anymore | +0.007 |
Neg logit contributions | |
asis | -0.013 |
rig | -0.012 |
place | -0.012 |
row | -0.011 |
isin | -0.011 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ked | +0.025 |
anish | +0.023 |
adoes | +0.023 |
tant | +0.022 |
prope | +0.022 |
Neg logit contributions | |
asis | -0.021 |
rig | -0.019 |
place | -0.019 |
row | -0.017 |
eh | -0.017 |
Token | upon |
Token ID | 2402 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
ked | +0.050 |
anish | +0.046 |
Ow | +0.042 |
adoes | +0.041 |
joy | +0.041 |
Neg logit contributions | |
asis | -0.094 |
rig | -0.092 |
place | -0.089 |
old | -0.085 |
row | -0.084 |
Token | ." |
Token ID | 526 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
ked | +0.072 |
anish | +0.070 |
Ow | +0.068 |
anymore | +0.067 |
joy | +0.067 |
Neg logit contributions | |
asis | -0.077 |
rig | -0.075 |
place | -0.072 |
eh | -0.065 |
row | -0.065 |
Token | She |
Token ID | 1375 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
ked | +0.001 |
anish | +0.001 |
Ow | +0.001 |
anymore | +0.001 |
adoes | +0.001 |
Neg logit contributions | |
asis | -0.001 |
rig | -0.001 |
place | -0.001 |
old | -0.001 |
row | -0.001 |
Token | took |
Token ID | 1718 |
Feature activation | -9.78e-01 |
Pos logit contributions | |
asis | +0.053 |
rig | +0.050 |
place | +0.049 |
row | +0.044 |
old | +0.044 |
Neg logit contributions | |
ked | -0.044 |
anish | -0.041 |
Ow | -0.040 |
joy | -0.040 |
anymore | -0.039 |
Token | Ben |
Token ID | 3932 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
anish | +0.038 |
ked | +0.038 |
joy | +0.037 |
prope | +0.036 |
superstar | +0.035 |
Neg logit contributions | |
place | -0.041 |
asis | -0.041 |
aster | -0.040 |
old | -0.040 |
rig | -0.040 |
Token | 's |
Token ID | 338 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
asis | +0.029 |
rig | +0.027 |
place | +0.027 |
eh | +0.025 |
row | +0.024 |
Neg logit contributions | |
ked | -0.016 |
anish | -0.015 |
Ow | -0.015 |
anymore | -0.015 |
joy | -0.015 |
Token | hand |
Token ID | 1021 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
asis | +0.001 |
rig | +0.001 |
place | +0.001 |
row | +0.000 |
eh | +0.000 |
Neg logit contributions | |
ked | -0.000 |
anish | -0.000 |
Ow | -0.000 |
joy | -0.000 |
anymore | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -8.89e-02 |
Pos logit contributions | |
asis | +0.061 |
rig | +0.059 |
place | +0.058 |
row | +0.055 |
old | +0.054 |
Neg logit contributions | |
anish | -0.037 |
ked | -0.037 |
Ow | -0.035 |
joy | -0.035 |
anymore | -0.034 |
Token | followed |
Token ID | 3940 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
ked | +0.004 |
anish | +0.003 |
Ow | +0.003 |
joy | +0.003 |
anymore | +0.003 |
Neg logit contributions | |
asis | -0.004 |
rig | -0.004 |
place | -0.004 |
row | -0.004 |
old | -0.004 |
Token | their |
Token ID | 511 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
ked | +0.008 |
anish | +0.007 |
Ow | +0.007 |
joy | +0.007 |
anymore | +0.007 |
Neg logit contributions | |
asis | -0.013 |
rig | -0.012 |
place | -0.012 |
row | -0.011 |
old | -0.011 |
Token | trail |
Token ID | 8025 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
ked | +0.019 |
anish | +0.018 |
Ow | +0.018 |
joy | +0.017 |
anymore | +0.017 |
Neg logit contributions | |
asis | -0.037 |
rig | -0.036 |
place | -0.035 |
row | -0.032 |
eh | -0.032 |
Token | back |
Token ID | 736 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
asis | +0.138 |
rig | +0.129 |
place | +0.124 |
isin | +0.115 |
eh | +0.115 |
Neg logit contributions | |
ked | -0.098 |
anymore | -0.096 |
anish | -0.091 |
joy | -0.087 |
adoes | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
asis | +0.025 |
rig | +0.024 |
place | +0.023 |
row | +0.021 |
eh | +0.021 |
Neg logit contributions | |
ked | -0.020 |
anish | -0.019 |
Ow | -0.018 |
joy | -0.018 |
anymore | -0.018 |
Token | noise |
Token ID | 7838 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
asis | +0.019 |
rig | +0.018 |
place | +0.018 |
row | +0.016 |
eh | +0.016 |
Neg logit contributions | |
ked | -0.015 |
anish | -0.014 |
Ow | -0.014 |
joy | -0.014 |
anymore | -0.014 |
Token | made |
Token ID | 925 |
Feature activation | +5.66e-01 |
Pos logit contributions | |
asis | +0.023 |
rig | +0.022 |
place | +0.021 |
row | +0.020 |
eh | +0.019 |
Neg logit contributions | |
ked | -0.015 |
anish | -0.015 |
Ow | -0.014 |
joy | -0.014 |
anymore | -0.013 |
Token | them |
Token ID | 606 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
asis | +0.031 |
rig | +0.030 |
place | +0.029 |
row | +0.027 |
eh | +0.027 |
Neg logit contributions | |
ked | -0.018 |
anish | -0.017 |
Ow | -0.017 |
joy | -0.016 |
anymore | -0.016 |
Token | turn |
Token ID | 1210 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
asis | +0.014 |
rig | +0.014 |
place | +0.014 |
row | +0.012 |
old | +0.012 |
Neg logit contributions | |
anish | -0.018 |
ked | -0.017 |
joy | -0.017 |
Ow | -0.017 |
superstar | -0.016 |
Token | around |
Token ID | 1088 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
rig | +0.079 |
place | +0.075 |
asis | +0.073 |
row | +0.071 |
called | +0.071 |
Neg logit contributions | |
anish | -0.079 |
Ow | -0.073 |
joy | -0.069 |
ked | -0.067 |
superstar | -0.065 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
asis | +0.010 |
place | +0.010 |
rig | +0.010 |
row | +0.009 |
called | +0.009 |
Neg logit contributions | |
ked | -0.012 |
anish | -0.012 |
Ow | -0.012 |
adoes | -0.011 |
arre | -0.011 |
Token | |
Token ID | 220 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ked | +0.001 |
Ow | +0.001 |
anish | +0.000 |
joy | +0.000 |
anymore | +0.000 |
Neg logit contributions | |
asis | -0.001 |
rig | -0.001 |
place | -0.001 |
eh | -0.001 |
isin | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Ow | +0.046 |
ked | +0.045 |
anish | +0.044 |
anymore | +0.043 |
joy | +0.041 |
Neg logit contributions | |
asis | -0.087 |
place | -0.081 |
rig | -0.081 |
row | -0.075 |
eh | -0.075 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
asis | +0.009 |
rig | +0.008 |
place | +0.008 |
eh | +0.008 |
row | +0.008 |
Neg logit contributions | |
Ow | -0.004 |
anish | -0.004 |
ked | -0.004 |
joy | -0.003 |
anymore | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
asis | +0.019 |
rig | +0.018 |
place | +0.018 |
old | +0.017 |
eh | +0.016 |
Neg logit contributions | |
ked | -0.014 |
anish | -0.013 |
Ow | -0.013 |
joy | -0.012 |
Look | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
ked | +0.021 |
anish | +0.020 |
Ow | +0.019 |
joy | +0.019 |
anymore | +0.019 |
Neg logit contributions | |
asis | -0.028 |
rig | -0.027 |
place | -0.026 |
row | -0.024 |
eh | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Ow | +0.004 |
anish | +0.004 |
ked | +0.004 |
joy | +0.004 |
anymore | +0.004 |
Neg logit contributions | |
asis | -0.010 |
place | -0.010 |
rig | -0.010 |
row | -0.009 |
eh | -0.009 |
Token | Billy |
Token ID | 49640 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
asis | +0.005 |
rig | +0.005 |
place | +0.004 |
row | +0.004 |
eh | +0.004 |
Neg logit contributions | |
ked | -0.004 |
anish | -0.004 |
Ow | -0.004 |
joy | -0.004 |
anymore | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -5.00e-01 |
Pos logit contributions | |
ked | +0.031 |
anish | +0.028 |
Ow | +0.027 |
joy | +0.027 |
anymore | +0.026 |
Neg logit contributions | |
asis | -0.052 |
rig | -0.050 |
place | -0.049 |
eh | -0.046 |
row | -0.045 |
Token | mesmer |
Token ID | 46814 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
ked | +0.021 |
joy | +0.020 |
anymore | +0.020 |
anish | +0.019 |
Ow | +0.019 |
Neg logit contributions | |
asis | -0.023 |
rig | -0.022 |
place | -0.022 |
row | -0.020 |
eh | -0.019 |
Token | ized |
Token ID | 1143 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
anish | +0.063 |
ked | +0.061 |
Ow | +0.060 |
joy | +0.056 |
anymore | +0.056 |
Neg logit contributions | |
asis | -0.046 |
rig | -0.044 |
place | -0.044 |
old | -0.037 |
row | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
rig | +0.014 |
place | +0.014 |
asis | +0.014 |
old | +0.012 |
row | +0.012 |
Neg logit contributions | |
anish | -0.016 |
ked | -0.016 |
Ow | -0.016 |
prope | -0.015 |
superstar | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
ked | +0.004 |
anish | +0.003 |
Ow | +0.003 |
joy | +0.003 |
anymore | +0.003 |
Neg logit contributions | |
asis | -0.004 |
rig | -0.004 |
place | -0.004 |
row | -0.004 |
eh | -0.004 |
Token | couldn |
Token ID | 3521 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ked | +0.005 |
anish | +0.004 |
joy | +0.004 |
Ow | +0.004 |
anymore | +0.004 |
Neg logit contributions | |
asis | -0.008 |
rig | -0.008 |
place | -0.008 |
eh | -0.007 |
row | -0.007 |
Token | 't |
Token ID | 470 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
ked | +0.055 |
anish | +0.052 |
Ow | +0.051 |
joy | +0.050 |
anymore | +0.049 |
Neg logit contributions | |
asis | -0.098 |
rig | -0.095 |
place | -0.092 |
row | -0.086 |
eh | -0.085 |
Token | believe |
Token ID | 1975 |
Feature activation | -9.62e-02 |
Pos logit contributions | |
ked | +0.074 |
anymore | +0.072 |
anish | +0.071 |
Ow | +0.068 |
superstar | +0.067 |
Neg logit contributions | |
asis | -0.042 |
rig | -0.040 |
place | -0.035 |
eh | -0.035 |
row | -0.033 |
Token | next |
Token ID | 1306 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
ked | +0.068 |
Ow | +0.067 |
anish | +0.067 |
adoes | +0.062 |
joy | +0.062 |
Neg logit contributions | |
asis | -0.071 |
rig | -0.067 |
place | -0.066 |
row | -0.060 |
eh | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | -2.06e-02 |
Pos logit contributions | |
ked | +0.060 |
anish | +0.058 |
joy | +0.055 |
Ow | +0.055 |
anymore | +0.055 |
Neg logit contributions | |
asis | -0.128 |
rig | -0.123 |
place | -0.120 |
eh | -0.112 |
row | -0.112 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
ked | +0.001 |
anish | +0.001 |
adoes | +0.001 |
Ow | +0.001 |
arre | +0.001 |
Neg logit contributions | |
asis | -0.001 |
rig | -0.001 |
place | -0.001 |
aster | -0.001 |
eh | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
asis | +0.106 |
rig | +0.103 |
place | +0.103 |
isin | +0.093 |
rim | +0.093 |
Neg logit contributions | |
ked | -0.044 |
anymore | -0.043 |
joy | -0.037 |
again | -0.037 |
anish | -0.036 |
Token | He |
Token ID | 679 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
ked | +0.015 |
anish | +0.014 |
Ow | +0.014 |
joy | +0.013 |
anymore | +0.013 |
Neg logit contributions | |
asis | -0.020 |
rig | -0.020 |
place | -0.019 |
row | -0.018 |
eh | -0.017 |
Token | looked |
Token ID | 3114 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ked | +0.013 |
anish | +0.012 |
Ow | +0.012 |
joy | +0.012 |
anymore | +0.012 |
Neg logit contributions | |
asis | -0.014 |
rig | -0.013 |
place | -0.013 |
row | -0.011 |
eh | -0.011 |
Token | at |
Token ID | 379 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
asis | +0.024 |
rig | +0.024 |
place | +0.023 |
eh | +0.022 |
old | +0.022 |
Neg logit contributions | |
anish | -0.010 |
ked | -0.010 |
Ow | -0.009 |
joy | -0.008 |
adoes | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
ked | +0.048 |
anish | +0.047 |
joy | +0.044 |
Ow | +0.044 |
anymore | +0.043 |
Neg logit contributions | |
asis | -0.061 |
rig | -0.058 |
place | -0.057 |
row | -0.052 |
old | -0.052 |
Token | book |
Token ID | 1492 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
asis | +0.080 |
place | +0.072 |
rig | +0.070 |
eh | +0.067 |
stump | +0.064 |
Neg logit contributions | |
ked | -0.067 |
anish | -0.062 |
Ow | -0.059 |
arre | -0.058 |
joy | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
ked | +0.047 |
anish | +0.045 |
Ow | +0.044 |
joy | +0.043 |
anymore | +0.042 |
Neg logit contributions | |
asis | -0.081 |
rig | -0.078 |
place | -0.076 |
row | -0.070 |
eh | -0.070 |
Token | said |
Token ID | 531 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
anish | +0.041 |
ked | +0.040 |
Ow | +0.039 |
anymore | +0.038 |
joy | +0.038 |
Neg logit contributions | |
asis | -0.033 |
rig | -0.032 |
place | -0.031 |
eh | -0.028 |
old | -0.027 |
Token | in |
Token ID | 287 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
ked | +0.027 |
anymore | +0.026 |
anish | +0.025 |
Ow | +0.022 |
joy | +0.022 |
Neg logit contributions | |
rig | -0.066 |
asis | -0.065 |
place | -0.061 |
old | -0.059 |
eh | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
ked | +0.015 |
anish | +0.014 |
Ow | +0.014 |
joy | +0.013 |
anymore | +0.013 |
Neg logit contributions | |
asis | -0.020 |
rig | -0.019 |
place | -0.019 |
row | -0.017 |
eh | -0.017 |
Token | street |
Token ID | 4675 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
Ow | +0.019 |
anish | +0.019 |
ked | +0.019 |
anymore | +0.018 |
joy | +0.018 |
Neg logit contributions | |
rig | -0.017 |
asis | -0.016 |
place | -0.015 |
row | -0.014 |
old | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
asis | +0.172 |
rig | +0.168 |
place | +0.159 |
eh | +0.151 |
isin | +0.149 |
Neg logit contributions | |
anymore | -0.103 |
ked | -0.100 |
anish | -0.096 |
joy | -0.095 |
Ow | -0.088 |
Token | Sam |
Token ID | 3409 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
asis | +0.021 |
place | +0.020 |
rig | +0.019 |
isin | +0.019 |
rim | +0.018 |
Neg logit contributions | |
Ow | -0.009 |
ked | -0.008 |
anish | -0.008 |
joy | -0.008 |
anymore | -0.007 |
Token | thought |
Token ID | 1807 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
asis | +0.025 |
rig | +0.025 |
place | +0.024 |
row | +0.022 |
isin | +0.022 |
Neg logit contributions | |
ked | -0.011 |
Ow | -0.009 |
anish | -0.009 |
anymore | -0.009 |
joy | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
ked | +0.011 |
anish | +0.010 |
Ow | +0.010 |
joy | +0.010 |
anymore | +0.010 |
Neg logit contributions | |
asis | -0.024 |
rig | -0.023 |
place | -0.023 |
row | -0.021 |
eh | -0.021 |
Token | would |
Token ID | 561 |
Feature activation | -1.69e+00 |
Pos logit contributions | |
asis | +0.066 |
rig | +0.063 |
place | +0.062 |
row | +0.057 |
eh | +0.055 |
Neg logit contributions | |
ked | -0.046 |
anish | -0.044 |
joy | -0.043 |
Ow | -0.043 |
anymore | -0.041 |
Token | be |
Token ID | 307 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
anymore | +0.065 |
anish | +0.063 |
Ow | +0.061 |
ked | +0.060 |
joy | +0.055 |
Neg logit contributions | |
rig | -0.082 |
asis | -0.081 |
old | -0.074 |
eh | -0.073 |
place | -0.073 |
Token | y |
Token ID | 331 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
asis | +0.064 |
rig | +0.061 |
place | +0.058 |
row | +0.053 |
old | +0.053 |
Neg logit contributions | |
ked | -0.064 |
anymore | -0.061 |
Ow | -0.060 |
anish | -0.060 |
joy | -0.060 |
Token | ummy |
Token ID | 13513 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
anymore | +0.010 |
Ow | +0.010 |
anish | +0.010 |
ked | +0.010 |
joy | +0.009 |
Neg logit contributions | |
asis | -0.012 |
rig | -0.011 |
place | -0.010 |
isin | -0.010 |
eh | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
asis | +0.099 |
rig | +0.096 |
place | +0.094 |
row | +0.083 |
old | +0.083 |
Neg logit contributions | |
ked | -0.130 |
Ow | -0.126 |
anish | -0.124 |
superstar | -0.116 |
prope | -0.115 |
Token | She |
Token ID | 1375 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
ked | +0.008 |
anish | +0.008 |
Ow | +0.008 |
joy | +0.007 |
anymore | +0.007 |
Neg logit contributions | |
asis | -0.014 |
rig | -0.014 |
place | -0.013 |
row | -0.012 |
eh | -0.012 |
Token | sees |
Token ID | 7224 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
asis | +0.057 |
rig | +0.054 |
place | +0.053 |
row | +0.051 |
eh | +0.050 |
Neg logit contributions | |
ked | -0.021 |
joy | -0.020 |
anish | -0.019 |
Ow | -0.019 |
anymore | -0.019 |
Token | Sara |
Token ID | 24799 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
place | +0.002 |
asis | +0.002 |
rig | +0.002 |
old | +0.002 |
ion | +0.002 |
Neg logit contributions | |
anish | -0.002 |
ked | -0.002 |
joy | -0.002 |
superstar | -0.002 |
ved | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
asis | +0.100 |
rig | +0.097 |
place | +0.094 |
row | +0.089 |
old | +0.089 |
Neg logit contributions | |
ked | -0.061 |
anish | -0.060 |
Ow | -0.058 |
joy | -0.058 |
anymore | -0.054 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
ked | +0.004 |
anish | +0.004 |
Ow | +0.004 |
joy | +0.004 |
anymore | +0.004 |
Neg logit contributions | |
asis | -0.008 |
rig | -0.008 |
place | -0.008 |
old | -0.007 |
row | -0.007 |
Token | fighting |
Token ID | 4330 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
ked | +0.054 |
anish | +0.052 |
Ow | +0.050 |
joy | +0.050 |
superstar | +0.047 |
Neg logit contributions | |
asis | -0.076 |
rig | -0.073 |
place | -0.072 |
row | -0.067 |
old | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
ked | +0.122 |
joy | +0.118 |
Ow | +0.115 |
anish | +0.114 |
superstar | +0.112 |
Neg logit contributions | |
rig | -0.082 |
asis | -0.078 |
place | -0.078 |
old | -0.070 |
row | -0.070 |
Token | She |
Token ID | 1375 |
Feature activation | +9.54e-01 |
Pos logit contributions | |
ked | +0.012 |
anish | +0.011 |
Ow | +0.011 |
anymore | +0.011 |
joy | +0.011 |
Neg logit contributions | |
asis | -0.017 |
rig | -0.017 |
place | -0.016 |
old | -0.015 |
row | -0.015 |
Token | sees |
Token ID | 7224 |
Feature activation | +8.12e-02 |
Pos logit contributions | |
asis | +0.055 |
rig | +0.052 |
place | +0.051 |
row | +0.048 |
eh | +0.047 |
Neg logit contributions | |
ked | -0.029 |
anish | -0.027 |
Ow | -0.027 |
joy | -0.026 |
anymore | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
asis | +0.004 |
rig | +0.004 |
place | +0.004 |
old | +0.004 |
row | +0.003 |
Neg logit contributions | |
ked | -0.003 |
anish | -0.003 |
joy | -0.003 |
Ow | -0.003 |
anymore | -0.003 |
Token | because |
Token ID | 780 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
place | +0.026 |
rig | +0.026 |
asis | +0.026 |
row | +0.023 |
old | +0.023 |
Neg logit contributions | |
ked | -0.032 |
anish | -0.031 |
Ow | -0.031 |
joy | -0.029 |
prope | -0.029 |
Token | he |
Token ID | 339 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
asis | +0.062 |
rig | +0.058 |
place | +0.058 |
row | +0.050 |
old | +0.050 |
Neg logit contributions | |
ked | -0.087 |
anish | -0.085 |
Ow | -0.083 |
joy | -0.081 |
anymore | -0.079 |
Token | was |
Token ID | 373 |
Feature activation | -5.84e-01 |
Pos logit contributions | |
ked | +0.069 |
anish | +0.062 |
Ow | +0.062 |
anymore | +0.060 |
joy | +0.060 |
Neg logit contributions | |
asis | -0.127 |
rig | -0.121 |
place | -0.119 |
row | -0.110 |
eh | -0.109 |
Token | taking |
Token ID | 2263 |
Feature activation | +5.78e-01 |
Pos logit contributions | |
anish | +0.026 |
ked | +0.026 |
Ow | +0.025 |
joy | +0.024 |
anymore | +0.023 |
Neg logit contributions | |
asis | -0.024 |
rig | -0.023 |
place | -0.023 |
eh | -0.021 |
old | -0.020 |
Token | dance |
Token ID | 9280 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
asis | +0.026 |
place | +0.026 |
rig | +0.026 |
row | +0.023 |
old | +0.023 |
Neg logit contributions | |
ked | -0.023 |
anish | -0.022 |
Ow | -0.021 |
joy | -0.021 |
anymore | -0.020 |
Token | lessons |
Token ID | 11658 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
asis | +0.019 |
rig | +0.019 |
place | +0.018 |
row | +0.017 |
eh | +0.016 |
Neg logit contributions | |
ked | -0.017 |
Ow | -0.017 |
anish | -0.017 |
joy | -0.016 |
adoes | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
ked | +0.072 |
anymore | +0.069 |
anish | +0.069 |
joy | +0.067 |
Ow | +0.065 |
Neg logit contributions | |
asis | -0.096 |
rig | -0.090 |
place | -0.088 |
eh | -0.081 |
row | -0.081 |
Token | H |
Token ID | 367 |
Feature activation | -7.87e-01 |
Pos logit contributions | |
ked | +0.008 |
Ow | +0.008 |
anish | +0.008 |
joy | +0.008 |
anymore | +0.008 |
Neg logit contributions | |
asis | -0.012 |
rig | -0.011 |
place | -0.011 |
eh | -0.010 |
row | -0.010 |
Token | oot |
Token ID | 1025 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
ked | +0.042 |
anish | +0.039 |
Ow | +0.039 |
anymore | +0.038 |
joy | +0.038 |
Neg logit contributions | |
asis | -0.028 |
rig | -0.025 |
place | -0.025 |
eh | -0.022 |
aster | -0.022 |
Token | ie |
Token ID | 494 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
asis | +0.012 |
rig | +0.011 |
place | +0.011 |
row | +0.010 |
eh | +0.009 |
Neg logit contributions | |
ked | -0.022 |
anish | -0.022 |
Ow | -0.021 |
joy | -0.021 |
anymore | -0.021 |
Token | 's |
Token ID | 338 |
Feature activation | -8.24e-01 |
Pos logit contributions | |
asis | +0.002 |
rig | +0.002 |
place | +0.002 |
row | +0.002 |
eh | +0.002 |
Neg logit contributions | |
ked | -0.002 |
anish | -0.002 |
Ow | -0.002 |
joy | -0.002 |
anymore | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
asis | +0.050 |
rig | +0.048 |
place | +0.046 |
ands | +0.044 |
isin | +0.042 |
Neg logit contributions | |
Ow | -0.045 |
anymore | -0.045 |
anish | -0.041 |
joy | -0.041 |
ked | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +5.54e-02 |
Pos logit contributions | |
asis | +0.012 |
place | +0.011 |
eh | +0.011 |
row | +0.011 |
old | +0.011 |
Neg logit contributions | |
ked | -0.018 |
anish | -0.017 |
adoes | -0.017 |
joy | -0.017 |
prope | -0.016 |
Token | she |
Token ID | 673 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
called | +0.001 |
aster | +0.001 |
eh | +0.001 |
place | +0.001 |
asis | +0.001 |
Neg logit contributions | |
arre | -0.003 |
anish | -0.003 |
ked | -0.003 |
prope | -0.003 |
joy | -0.003 |
Token | went |
Token ID | 1816 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
asis | +0.010 |
rig | +0.009 |
place | +0.009 |
eh | +0.009 |
old | +0.009 |
Neg logit contributions | |
ked | -0.008 |
anish | -0.008 |
joy | -0.008 |
Ow | -0.008 |
anymore | -0.008 |
Token | for |
Token ID | 329 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
asis | +0.084 |
rig | +0.083 |
place | +0.078 |
isin | +0.077 |
rim | +0.074 |
Neg logit contributions | |
ked | -0.027 |
joy | -0.025 |
anymore | -0.024 |
on | -0.021 |
Ow | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
asis | +0.045 |
rig | +0.043 |
place | +0.042 |
row | +0.039 |
eh | +0.039 |
Neg logit contributions | |
ked | -0.025 |
anish | -0.023 |
Ow | -0.023 |
joy | -0.022 |
anymore | -0.022 |
Token | walk |
Token ID | 2513 |
Feature activation | -3.35e-01 |
Pos logit contributions | |
ked | +0.007 |
anish | +0.007 |
Ow | +0.007 |
joy | +0.007 |
anymore | +0.007 |
Neg logit contributions | |
asis | -0.006 |
rig | -0.006 |
place | -0.006 |
row | -0.005 |
eh | -0.005 |
Token | with |
Token ID | 351 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
ked | +0.009 |
anish | +0.009 |
anymore | +0.008 |
joy | +0.008 |
Ow | +0.008 |
Neg logit contributions | |
asis | -0.020 |
rig | -0.019 |
place | -0.019 |
row | -0.017 |
isin | -0.017 |
Token | her |
Token ID | 607 |
Feature activation | +6.80e-01 |
Pos logit contributions | |
ked | +0.002 |
Ow | +0.002 |
anish | +0.002 |
joy | +0.002 |
anymore | +0.002 |
Neg logit contributions | |
asis | -0.004 |
rig | -0.004 |
place | -0.004 |
row | -0.004 |
eh | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
asis | +0.033 |
place | +0.033 |
rig | +0.032 |
called | +0.029 |
eh | +0.029 |
Neg logit contributions | |
anish | -0.025 |
ked | -0.025 |
Ow | -0.023 |
arre | -0.022 |
joy | -0.022 |
Token | in |
Token ID | 287 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
ked | +0.016 |
anymore | +0.016 |
joy | +0.015 |
Ow | +0.014 |
anish | +0.014 |
Neg logit contributions | |
asis | -0.030 |
rig | -0.029 |
place | -0.027 |
isin | -0.026 |
eh | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
asis | +0.045 |
rig | +0.043 |
place | +0.043 |
row | +0.038 |
eh | +0.038 |
Neg logit contributions | |
ked | -0.046 |
anish | -0.044 |
Ow | -0.043 |
joy | -0.043 |
anymore | -0.041 |
Token | We |
Token ID | 775 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
asis | +0.004 |
rig | +0.004 |
place | +0.004 |
row | +0.004 |
eh | +0.004 |
Neg logit contributions | |
ked | -0.003 |
anish | -0.003 |
Ow | -0.003 |
joy | -0.002 |
anymore | -0.002 |
Token | can |
Token ID | 460 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ked | +0.016 |
anish | +0.015 |
Ow | +0.015 |
joy | +0.014 |
anymore | +0.014 |
Neg logit contributions | |
asis | -0.034 |
rig | -0.033 |
place | -0.032 |
row | -0.030 |
eh | -0.030 |
Token | float |
Token ID | 12178 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ked | +0.049 |
anish | +0.047 |
Ow | +0.046 |
anymore | +0.046 |
joy | +0.044 |
Neg logit contributions | |
asis | -0.047 |
rig | -0.046 |
place | -0.044 |
row | -0.040 |
eh | -0.040 |
Token | on |
Token ID | 319 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
asis | +0.009 |
place | +0.009 |
rig | +0.009 |
row | +0.009 |
b | +0.008 |
Neg logit contributions | |
ked | -0.007 |
joy | -0.007 |
anish | -0.007 |
Ow | -0.006 |
arre | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
ked | +0.099 |
anish | +0.097 |
joy | +0.090 |
arre | +0.088 |
ved | +0.087 |
Neg logit contributions | |
asis | -0.088 |
place | -0.084 |
rig | -0.084 |
eh | -0.074 |
aster | -0.073 |
Token | raft |
Token ID | 31812 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
ked | +0.027 |
Ow | +0.026 |
anish | +0.025 |
anymore | +0.025 |
joy | +0.025 |
Neg logit contributions | |
asis | -0.019 |
rig | -0.019 |
place | -0.018 |
old | -0.017 |
row | -0.016 |
Token | together |
Token ID | 1978 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
asis | +0.044 |
rig | +0.043 |
place | +0.042 |
old | +0.040 |
eh | +0.039 |
Neg logit contributions | |
anymore | -0.030 |
ked | -0.029 |
anish | -0.027 |
Ow | -0.025 |
again | -0.025 |
Token | ," |
Token ID | 553 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
ked | +0.092 |
anish | +0.088 |
Ow | +0.086 |
joy | +0.086 |
anymore | +0.082 |
Neg logit contributions | |
asis | -0.085 |
rig | -0.081 |
place | -0.080 |
row | -0.072 |
eh | -0.070 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
ked | +0.072 |
anish | +0.071 |
Ow | +0.066 |
adoes | +0.065 |
anymore | +0.064 |
Neg logit contributions | |
asis | -0.081 |
rig | -0.079 |
place | -0.078 |
old | -0.072 |
called | -0.070 |
Token | says |
Token ID | 1139 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
asis | +0.025 |
rig | +0.023 |
place | +0.023 |
row | +0.021 |
eh | +0.020 |
Neg logit contributions | |
ked | -0.023 |
anish | -0.022 |
Ow | -0.022 |
joy | -0.021 |
anymore | -0.021 |
Token | unt |
Token ID | 1418 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
asis | +0.002 |
rig | +0.002 |
place | +0.002 |
eh | +0.001 |
old | +0.001 |
Neg logit contributions | |
ked | -0.001 |
anish | -0.001 |
Ow | -0.001 |
anymore | -0.001 |
joy | -0.001 |
Token | ies |
Token ID | 444 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
ked | +0.078 |
anish | +0.075 |
Ow | +0.074 |
joy | +0.072 |
anymore | +0.072 |
Neg logit contributions | |
asis | -0.074 |
rig | -0.071 |
place | -0.069 |
row | -0.062 |
eh | -0.061 |
Token | the |
Token ID | 262 |
Feature activation | +8.92e-01 |
Pos logit contributions | |
asis | +0.050 |
place | +0.048 |
rig | +0.047 |
row | +0.044 |
old | +0.043 |
Neg logit contributions | |
ked | -0.047 |
joy | -0.044 |
Ow | -0.044 |
anish | -0.044 |
superstar | -0.041 |
Token | rope |
Token ID | 17182 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
asis | +0.033 |
place | +0.032 |
rig | +0.032 |
row | +0.028 |
stump | +0.027 |
Neg logit contributions | |
ked | -0.043 |
anish | -0.042 |
anymore | -0.041 |
joy | -0.040 |
Ow | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
asis | +0.152 |
rig | +0.148 |
place | +0.144 |
row | +0.134 |
eh | +0.131 |
Neg logit contributions | |
ked | -0.095 |
anish | -0.090 |
Ow | -0.089 |
joy | -0.088 |
anymore | -0.084 |
Token | fre |
Token ID | 2030 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
ked | +0.043 |
anish | +0.043 |
Ow | +0.041 |
joy | +0.041 |
anymore | +0.041 |
Neg logit contributions | |
asis | -0.043 |
rig | -0.042 |
place | -0.041 |
old | -0.037 |
eh | -0.036 |
Token | es |
Token ID | 274 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
joy | +0.148 |
ked | +0.141 |
anymore | +0.139 |
Ow | +0.138 |
anish | +0.138 |
Neg logit contributions | |
asis | -0.259 |
place | -0.247 |
rig | -0.244 |
row | -0.239 |
old | -0.230 |
Token | Ben |
Token ID | 3932 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
anish | +0.066 |
ked | +0.065 |
joy | +0.064 |
Ow | +0.064 |
superstar | +0.060 |
Neg logit contributions | |
asis | -0.083 |
place | -0.081 |
rig | -0.081 |
row | -0.077 |
old | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
ked | +0.037 |
anish | +0.035 |
Ow | +0.034 |
anymore | +0.034 |
joy | +0.034 |
Neg logit contributions | |
asis | -0.045 |
rig | -0.043 |
place | -0.042 |
row | -0.038 |
eh | -0.038 |
Token | He |
Token ID | 679 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ked | +0.020 |
anish | +0.019 |
joy | +0.018 |
anymore | +0.018 |
Ow | +0.018 |
Neg logit contributions | |
asis | -0.022 |
rig | -0.022 |
place | -0.021 |
old | -0.019 |
eh | -0.018 |
Token | lifts |
Token ID | 27103 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
ked | +0.022 |
anish | +0.021 |
Ow | +0.021 |
joy | +0.021 |
anymore | +0.020 |
Neg logit contributions | |
asis | -0.028 |
rig | -0.027 |
place | -0.026 |
row | -0.024 |
eh | -0.024 |
Token | He |
Token ID | 679 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
asis | +0.003 |
rig | +0.003 |
place | +0.003 |
row | +0.003 |
eh | +0.003 |
Neg logit contributions | |
ked | -0.003 |
anish | -0.003 |
Ow | -0.003 |
joy | -0.003 |
anymore | -0.003 |
Token | gives |
Token ID | 3607 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
ked | +0.009 |
anish | +0.009 |
Ow | +0.009 |
joy | +0.008 |
anymore | +0.008 |
Neg logit contributions | |
asis | -0.012 |
rig | -0.012 |
place | -0.012 |
row | -0.011 |
eh | -0.011 |
Token | them |
Token ID | 606 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
place | +0.007 |
asis | +0.007 |
old | +0.007 |
ion | +0.007 |
called | +0.007 |
Neg logit contributions | |
anish | -0.004 |
prope | -0.004 |
ked | -0.004 |
arre | -0.004 |
joy | -0.004 |
Token | each |
Token ID | 1123 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
asis | +0.107 |
rig | +0.104 |
place | +0.102 |
row | +0.094 |
old | +0.094 |
Neg logit contributions | |
ked | -0.062 |
anish | -0.060 |
Ow | -0.057 |
joy | -0.057 |
anymore | -0.056 |
Token | a |
Token ID | 257 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
place | +0.067 |
asis | +0.066 |
rig | +0.066 |
old | +0.062 |
eh | +0.061 |
Neg logit contributions | |
anish | -0.060 |
ked | -0.059 |
joy | -0.057 |
adoes | -0.056 |
anymore | -0.055 |
Token | kiss |
Token ID | 9245 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
ked | +0.010 |
anish | +0.010 |
Ow | +0.009 |
anymore | +0.009 |
joy | +0.009 |
Neg logit contributions | |
asis | -0.012 |
rig | -0.012 |
place | -0.011 |
row | -0.010 |
eh | -0.010 |
Token | on |
Token ID | 319 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
Ow | +0.157 |
joy | +0.155 |
anish | +0.152 |
ked | +0.152 |
arre | +0.146 |
Neg logit contributions | |
asis | -0.161 |
place | -0.150 |
row | -0.147 |
rig | -0.146 |
called | -0.137 |
Token | the |
Token ID | 262 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
ked | +0.072 |
anish | +0.071 |
joy | +0.069 |
arre | +0.067 |
superstar | +0.065 |
Neg logit contributions | |
place | -0.072 |
aster | -0.072 |
asis | -0.070 |
rig | -0.068 |
called | -0.068 |
Token | lip |
Token ID | 10645 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ked | +0.011 |
anish | +0.010 |
Ow | +0.010 |
joy | +0.010 |
anymore | +0.010 |
Neg logit contributions | |
asis | -0.009 |
rig | -0.008 |
place | -0.008 |
row | -0.007 |
eh | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
ked | +0.062 |
anish | +0.059 |
anymore | +0.059 |
Ow | +0.057 |
joy | +0.054 |
Neg logit contributions | |
asis | -0.079 |
rig | -0.076 |
place | -0.074 |
eh | -0.067 |
old | -0.066 |
Token | Lily |
Token ID | 20037 |
Feature activation | +3.26e-02 |
Pos logit contributions | |
ked | +0.009 |
anish | +0.008 |
joy | +0.008 |
anymore | +0.008 |
Ow | +0.008 |
Neg logit contributions | |
rig | -0.008 |
asis | -0.008 |
place | -0.008 |
old | -0.007 |
called | -0.007 |
Token | ." |
Token ID | 526 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
asis | +0.006 |
rig | +0.006 |
place | +0.006 |
row | +0.005 |
old | +0.005 |
Neg logit contributions | |
ked | -0.007 |
anish | -0.006 |
Ow | -0.006 |
joy | -0.006 |
adoes | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
ked | +0.021 |
anish | +0.020 |
Ow | +0.019 |
joy | +0.019 |
anymore | +0.019 |
Neg logit contributions | |
asis | -0.031 |
rig | -0.030 |
place | -0.029 |
row | -0.027 |
eh | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
Ow | +0.003 |
ked | +0.003 |
anish | +0.003 |
anymore | +0.003 |
joy | +0.003 |
Neg logit contributions | |
asis | -0.009 |
place | -0.008 |
rig | -0.008 |
row | -0.007 |
eh | -0.007 |
Token | The |
Token ID | 464 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
asis | +0.002 |
rig | +0.002 |
place | +0.002 |
at | +0.002 |
row | +0.002 |
Neg logit contributions | |
anish | -0.001 |
ked | -0.001 |
Ow | -0.001 |
Look | -0.001 |
joy | -0.001 |
Token | mushroom |
Token ID | 28520 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
asis | +0.013 |
rig | +0.012 |
place | +0.012 |
eh | +0.011 |
row | +0.010 |
Neg logit contributions | |
ked | -0.016 |
anish | -0.014 |
Ow | -0.014 |
joy | -0.014 |
anymore | -0.014 |
Token | softened |
Token ID | 41534 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
ked | +0.034 |
anish | +0.032 |
Ow | +0.032 |
joy | +0.031 |
anymore | +0.030 |
Neg logit contributions | |
asis | -0.052 |
rig | -0.050 |
place | -0.049 |
row | -0.045 |
eh | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
ked | +0.181 |
ifying | +0.174 |
Ow | +0.173 |
joy | +0.173 |
arre | +0.172 |
Neg logit contributions | |
rig | -0.116 |
called | -0.116 |
place | -0.115 |
asis | -0.111 |
row | -0.110 |
Token | It |
Token ID | 632 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
ked | +0.014 |
anish | +0.012 |
Ow | +0.012 |
joy | +0.012 |
anymore | +0.012 |
Neg logit contributions | |
asis | -0.031 |
rig | -0.030 |
place | -0.029 |
old | -0.027 |
row | -0.027 |
Token | saw |
Token ID | 2497 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
asis | +0.022 |
rig | +0.021 |
place | +0.021 |
row | +0.019 |
eh | +0.019 |
Neg logit contributions | |
ked | -0.018 |
anish | -0.017 |
Ow | -0.017 |
joy | -0.017 |
anymore | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
anish | +0.034 |
joy | +0.033 |
ked | +0.032 |
arre | +0.031 |
superstar | +0.030 |
Neg logit contributions | |
rig | -0.039 |
place | -0.039 |
asis | -0.038 |
ion | -0.038 |
called | -0.037 |
Token | they |
Token ID | 484 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
ked | +0.024 |
joy | +0.023 |
arre | +0.022 |
anish | +0.022 |
tant | +0.022 |
Neg logit contributions | |
asis | -0.024 |
called | -0.023 |
place | -0.023 |
rig | -0.023 |
ion | -0.022 |
Token | f |
Token ID | 277 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
rig | +0.031 |
asis | +0.031 |
place | +0.028 |
eh | +0.027 |
aling | +0.027 |
Neg logit contributions | |
joy | -0.027 |
anymore | -0.026 |
ked | -0.026 |
adoes | -0.025 |
anish | -0.025 |
Token | auc |
Token ID | 14272 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
arre | +0.016 |
ked | +0.015 |
ifying | +0.014 |
apped | +0.014 |
ed | +0.014 |
Neg logit contributions | |
asis | -0.018 |
place | -0.017 |
stump | -0.016 |
pharmacy | -0.016 |
rig | -0.015 |
Token | et |
Token ID | 316 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
ked | +0.021 |
anymore | +0.020 |
anish | +0.020 |
arre | +0.019 |
tant | +0.019 |
Neg logit contributions | |
asis | -0.025 |
rig | -0.025 |
place | -0.024 |
old | -0.023 |
stump | -0.023 |
Token | all |
Token ID | 477 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
asis | +0.038 |
rig | +0.037 |
place | +0.036 |
eh | +0.033 |
old | +0.033 |
Neg logit contributions | |
ked | -0.026 |
anish | -0.025 |
anymore | -0.024 |
Ow | -0.024 |
joy | -0.023 |
Token | over |
Token ID | 625 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
asis | +0.018 |
rig | +0.017 |
place | +0.017 |
row | +0.015 |
eh | +0.015 |
Neg logit contributions | |
ked | -0.016 |
anish | -0.015 |
anymore | -0.015 |
joy | -0.015 |
Ow | -0.015 |
Token | again |
Token ID | 757 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
ked | +0.047 |
anish | +0.044 |
Ow | +0.043 |
adoes | +0.040 |
arre | +0.039 |
Neg logit contributions | |
asis | -0.051 |
place | -0.050 |
rig | -0.048 |
old | -0.044 |
row | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
ked | +0.180 |
anish | +0.172 |
Ow | +0.169 |
joy | +0.165 |
anymore | +0.163 |
Neg logit contributions | |
asis | -0.201 |
rig | -0.193 |
place | -0.187 |
row | -0.170 |
eh | -0.168 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
ked | +0.026 |
anish | +0.025 |
Ow | +0.025 |
joy | +0.024 |
anymore | +0.024 |
Neg logit contributions | |
asis | -0.040 |
rig | -0.039 |
place | -0.038 |
row | -0.035 |
eh | -0.034 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ked | +0.031 |
anish | +0.028 |
adoes | +0.028 |
tant | +0.028 |
prope | +0.028 |
Neg logit contributions | |
asis | -0.024 |
rig | -0.021 |
place | -0.021 |
row | -0.019 |
old | -0.019 |
Token | upon |
Token ID | 2402 |
Feature activation | -5.30e-01 |
Pos logit contributions | |
ked | +0.051 |
anish | +0.047 |
Ow | +0.043 |
adoes | +0.043 |
prope | +0.041 |
Neg logit contributions | |
asis | -0.092 |
rig | -0.091 |
place | -0.087 |
old | -0.085 |
row | -0.082 |
Token | a |
Token ID | 257 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
ked | +0.023 |
anish | +0.022 |
adoes | +0.021 |
joy | +0.021 |
tant | +0.020 |
Neg logit contributions | |
place | -0.023 |
asis | -0.023 |
rig | -0.023 |
eh | -0.021 |
old | -0.020 |
Token | But |
Token ID | 1537 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
asis | +0.009 |
rig | +0.009 |
place | +0.008 |
eh | +0.007 |
row | +0.007 |
Neg logit contributions | |
ked | -0.010 |
anish | -0.010 |
joy | -0.009 |
Ow | -0.009 |
anymore | -0.009 |
Token | then |
Token ID | 788 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
called | +0.036 |
asis | +0.032 |
place | +0.030 |
eh | +0.028 |
aster | +0.026 |
Neg logit contributions | |
anish | -0.102 |
ked | -0.099 |
joy | -0.099 |
Ow | -0.099 |
arre | -0.096 |
Token | , |
Token ID | 11 |
Feature activation | -5.79e-01 |
Pos logit contributions | |
called | +0.020 |
place | +0.017 |
asis | +0.016 |
lly | +0.015 |
aster | +0.015 |
Neg logit contributions | |
ked | -0.047 |
ifying | -0.045 |
anish | -0.045 |
tant | -0.043 |
prope | -0.043 |
Token | something |
Token ID | 1223 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
anish | +0.031 |
ked | +0.031 |
prope | +0.031 |
joy | +0.030 |
arre | +0.029 |
Neg logit contributions | |
called | -0.020 |
aster | -0.016 |
place | -0.015 |
eh | -0.014 |
exercise | -0.014 |
Token | bad |
Token ID | 2089 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
ked | +0.044 |
anymore | +0.041 |
anish | +0.040 |
Ow | +0.039 |
joy | +0.038 |
Neg logit contributions | |
asis | -0.070 |
rig | -0.065 |
place | -0.062 |
row | -0.059 |
old | -0.058 |
Token | happened |
Token ID | 3022 |
Feature activation | -4.16e+00 |
Pos logit contributions | |
joy | +0.096 |
ked | +0.085 |
Ow | +0.082 |
anish | +0.082 |
prope | +0.079 |
Neg logit contributions | |
asis | -0.201 |
place | -0.198 |
called | -0.191 |
row | -0.190 |
rig | -0.189 |
Token | . |
Token ID | 13 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
ked | +0.206 |
Ow | +0.201 |
anish | +0.200 |
tant | +0.192 |
prope | +0.189 |
Neg logit contributions | |
asis | -0.152 |
rig | -0.144 |
place | -0.140 |
row | -0.126 |
eh | -0.125 |
Token | One |
Token ID | 1881 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
place | +0.005 |
eh | +0.005 |
rig | +0.005 |
called | +0.005 |
asis | +0.004 |
Neg logit contributions | |
ked | -0.005 |
joy | -0.005 |
anish | -0.005 |
prope | -0.004 |
ved | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
asis | +0.035 |
rig | +0.033 |
place | +0.033 |
row | +0.029 |
eh | +0.028 |
Neg logit contributions | |
ked | -0.046 |
anish | -0.044 |
Ow | -0.043 |
joy | -0.043 |
anymore | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
ked | +0.032 |
anish | +0.030 |
joy | +0.029 |
Ow | +0.029 |
anymore | +0.027 |
Neg logit contributions | |
asis | -0.040 |
place | -0.040 |
rig | -0.039 |
eh | -0.036 |
row | -0.036 |
Token | balloons |
Token ID | 35485 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
asis | +0.035 |
place | +0.034 |
rig | +0.032 |
eh | +0.029 |
row | +0.028 |
Neg logit contributions | |
ked | -0.039 |
Ow | -0.037 |
anish | -0.037 |
joy | -0.035 |
adoes | -0.033 |