Token | 's |
Token ID | 338 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
�� | +0.032 |
� | +0.032 |
dra | +0.032 |
srf | +0.030 |
�士 | +0.030 |
Neg logit contributions | |
sim | -0.018 |
Buchanan | -0.017 |
Cain | -0.017 |
quit | -0.017 |
kitten | -0.017 |
Token | Treasure |
Token ID | 20215 |
Feature activation | -7.77e-02 |
Pos logit contributions | |
�� | +0.043 |
� | +0.043 |
dra | +0.042 |
srf | +0.039 |
�士 | +0.039 |
Neg logit contributions | |
sim | -0.030 |
Buchanan | -0.029 |
kitten | -0.029 |
Cain | -0.028 |
quit | -0.028 |
Token | Island |
Token ID | 5451 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
sim | +0.031 |
Buchanan | +0.030 |
Cain | +0.029 |
kitten | +0.029 |
quit | +0.029 |
Neg logit contributions | |
�� | -0.095 |
dra | -0.094 |
� | -0.093 |
srf | -0.088 |
�士 | -0.088 |
Token | begins |
Token ID | 6140 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
sim | +0.014 |
Buchanan | +0.014 |
kitten | +0.014 |
quit | +0.014 |
Cain | +0.014 |
Neg logit contributions | |
� | -0.028 |
�� | -0.027 |
dra | -0.027 |
�士 | -0.025 |
srf | -0.025 |
Token | serial |
Token ID | 11389 |
Feature activation | +4.64e-04 |
Pos logit contributions | |
�� | +0.019 |
dra | +0.018 |
� | +0.018 |
�士 | +0.017 |
srf | +0.017 |
Neg logit contributions | |
sim | -0.010 |
Buchanan | -0.010 |
quit | -0.010 |
kitten | -0.009 |
Cain | -0.009 |
Token | ized |
Token ID | 1143 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
�� | +0.000 |
� | +0.000 |
dra | +0.000 |
�士 | +0.000 |
srf | +0.000 |
Neg logit contributions | |
sim | -0.000 |
kitten | -0.000 |
quit | -0.000 |
Buchanan | -0.000 |
Cain | -0.000 |
Token | publication |
Token ID | 9207 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
�� | +0.333 |
dra | +0.330 |
� | +0.326 |
�士 | +0.310 |
srf | +0.308 |
Neg logit contributions | |
sim | -0.139 |
kitten | -0.130 |
Buchanan | -0.130 |
Cain | -0.128 |
quit | -0.128 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
�� | +0.049 |
dra | +0.049 |
� | +0.049 |
�士 | +0.046 |
srf | +0.046 |
Neg logit contributions | |
sim | -0.024 |
Buchanan | -0.023 |
quit | -0.023 |
kitten | -0.023 |
Cain | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -1.00e-03 |
Pos logit contributions | |
dra | +0.017 |
� | +0.016 |
�� | +0.016 |
�士 | +0.015 |
#$ | +0.015 |
Neg logit contributions | |
quit | -0.012 |
sim | -0.012 |
kitten | -0.012 |
keley | -0.012 |
shame | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -5.40e-03 |
Pos logit contributions | |
sim | +0.000 |
Buchanan | +0.000 |
quit | +0.000 |
Cain | +0.000 |
Kap | +0.000 |
Neg logit contributions | |
� | -0.001 |
� | -0.001 |
srf | -0.001 |
� | -0.001 |
�� | -0.001 |
Token | T |
Token ID | 51 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
sim | +0.004 |
quit | +0.004 |
Buchanan | +0.004 |
Cain | +0.004 |
keley | +0.004 |
Neg logit contributions | |
�� | -0.005 |
srf | -0.005 |
dra | -0.005 |
� | -0.005 |
� | -0.005 |
Token | see |
Token ID | 766 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
�� | +0.009 |
� | +0.009 |
dra | +0.009 |
� | +0.009 |
srf | +0.008 |
Neg logit contributions | |
sim | -0.006 |
shame | -0.006 |
kitten | -0.005 |
Buchanan | -0.005 |
Cain | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
�� | +0.030 |
� | +0.030 |
dra | +0.030 |
EStreamFrame | +0.028 |
srf | +0.028 |
Neg logit contributions | |
sim | -0.018 |
Buchanan | -0.017 |
Cain | -0.017 |
kitten | -0.017 |
Kap | -0.017 |
Token | handcuffed |
Token ID | 41529 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
� | +0.013 |
�� | +0.013 |
dra | +0.013 |
EStreamFrame | +0.012 |
srf | +0.012 |
Neg logit contributions | |
sim | -0.008 |
kitten | -0.008 |
Buchanan | -0.008 |
Cain | -0.007 |
shame | -0.007 |
Token | man |
Token ID | 582 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
sim | +0.019 |
kitten | +0.018 |
Buchanan | +0.017 |
Cain | +0.017 |
Kap | +0.017 |
Neg logit contributions | |
� | -0.042 |
�� | -0.041 |
dra | -0.040 |
EStreamFrame | -0.039 |
srf | -0.039 |
Token | reapp |
Token ID | 24578 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
sim | +0.007 |
Buchanan | +0.006 |
kitten | +0.006 |
quit | +0.006 |
Cain | +0.006 |
Neg logit contributions | |
�� | -0.012 |
� | -0.012 |
dra | -0.012 |
�士 | -0.011 |
EStreamFrame | -0.011 |
Token | ear |
Token ID | 451 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
quit | +0.031 |
sim | +0.031 |
Buchanan | +0.031 |
keley | +0.030 |
kitten | +0.030 |
Neg logit contributions | |
�� | -0.027 |
� | -0.027 |
dra | -0.026 |
�士 | -0.025 |
srf | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
�� | +0.316 |
� | +0.315 |
dra | +0.314 |
�士 | +0.295 |
srf | +0.294 |
Neg logit contributions | |
sim | -0.150 |
Buchanan | -0.144 |
kitten | -0.141 |
Cain | -0.141 |
quit | -0.141 |
Token | He |
Token ID | 679 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
�� | +0.011 |
srf | +0.011 |
� | +0.010 |
dra | +0.010 |
� | +0.010 |
Neg logit contributions | |
Cain | -0.007 |
Buchanan | -0.007 |
sim | -0.007 |
Kap | -0.007 |
quit | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +4.50e-03 |
Pos logit contributions | |
sim | +0.012 |
Buchanan | +0.012 |
spat | +0.012 |
shame | +0.012 |
kitten | +0.012 |
Neg logit contributions | |
�� | -0.021 |
� | -0.021 |
dra | -0.020 |
srf | -0.020 |
� | -0.020 |
Token | accompanied |
Token ID | 11791 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
�� | +0.005 |
� | +0.005 |
dra | +0.005 |
srf | +0.004 |
EStreamFrame | +0.004 |
Neg logit contributions | |
sim | -0.003 |
Buchanan | -0.003 |
Cain | -0.003 |
kitten | -0.002 |
shame | -0.002 |
Token | by |
Token ID | 416 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
quit | +0.014 |
sim | +0.014 |
Buchanan | +0.013 |
Cain | +0.013 |
keley | +0.013 |
Neg logit contributions | |
� | -0.026 |
dra | -0.026 |
�� | -0.026 |
srf | -0.024 |
�士 | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
sim | +0.006 |
Buchanan | +0.006 |
Cain | +0.006 |
keley | +0.006 |
kitten | +0.006 |
Neg logit contributions | |
� | -0.012 |
dra | -0.012 |
�� | -0.012 |
srf | -0.011 |
�士 | -0.011 |
Token | Department |
Token ID | 2732 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
sim | +0.011 |
Buchanan | +0.011 |
kitten | +0.010 |
shame | +0.010 |
Kap | +0.010 |
Neg logit contributions | |
� | -0.019 |
�� | -0.018 |
dra | -0.018 |
� | -0.017 |
srf | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
dra | +0.013 |
�� | +0.013 |
� | +0.013 |
�士 | +0.013 |
EStreamFrame | +0.012 |
Neg logit contributions | |
quit | -0.010 |
keley | -0.009 |
sim | -0.009 |
kitten | -0.009 |
Cain | -0.009 |
Token | Education |
Token ID | 7868 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
Buchanan | +0.019 |
Cain | +0.018 |
Kap | +0.018 |
sim | +0.018 |
shame | +0.018 |
Neg logit contributions | |
� | -0.025 |
�� | -0.025 |
dra | -0.024 |
srf | -0.023 |
EStreamFrame | -0.023 |
Token | recons |
Token ID | 23898 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
�� | +0.064 |
� | +0.064 |
dra | +0.063 |
srf | +0.060 |
� | +0.059 |
Neg logit contributions | |
sim | -0.034 |
Buchanan | -0.033 |
Cain | -0.032 |
kitten | -0.032 |
quit | -0.031 |
Token | iders |
Token ID | 4157 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
sim | +0.042 |
quit | +0.041 |
keley | +0.040 |
Buchanan | +0.040 |
kitten | +0.040 |
Neg logit contributions | |
�� | -0.036 |
� | -0.034 |
dra | -0.034 |
�士 | -0.033 |
srf | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | +1.32e-03 |
Pos logit contributions | |
� | +0.285 |
�� | +0.283 |
dra | +0.277 |
srf | +0.262 |
� | +0.260 |
Neg logit contributions | |
sim | -0.165 |
Buchanan | -0.164 |
kitten | -0.158 |
Cain | -0.158 |
keley | -0.157 |
Token | guidance |
Token ID | 11154 |
Feature activation | +3.11e-04 |
Pos logit contributions | |
� | +0.001 |
�� | +0.001 |
dra | +0.001 |
srf | +0.001 |
� | +0.001 |
Neg logit contributions | |
Buchanan | -0.001 |
sim | -0.001 |
Cain | -0.001 |
shame | -0.001 |
kitten | -0.001 |
Token | provided |
Token ID | 2810 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
� | +0.000 |
�� | +0.000 |
dra | +0.000 |
srf | +0.000 |
� | +0.000 |
Neg logit contributions | |
sim | -0.000 |
Buchanan | -0.000 |
kitten | -0.000 |
Cain | -0.000 |
quit | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
sim | +0.010 |
Buchanan | +0.009 |
kitten | +0.009 |
Cain | +0.009 |
quit | +0.009 |
Neg logit contributions | |
� | -0.025 |
�� | -0.025 |
dra | -0.024 |
�士 | -0.023 |
srf | -0.023 |
Token | schools |
Token ID | 4266 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
Buchanan | +0.024 |
sim | +0.024 |
Cain | +0.023 |
shame | +0.023 |
keley | +0.022 |
Neg logit contributions | |
� | -0.041 |
�� | -0.040 |
dra | -0.040 |
�士 | -0.037 |
� | -0.037 |
Token | man |
Token ID | 582 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
sim | +0.002 |
Buchanan | +0.002 |
Kap | +0.002 |
kitten | +0.002 |
shame | +0.002 |
Neg logit contributions | |
�� | -0.004 |
� | -0.003 |
dra | -0.003 |
srf | -0.003 |
�士 | -0.003 |
Token | gro |
Token ID | 27333 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
�� | +0.042 |
� | +0.042 |
dra | +0.041 |
�士 | +0.039 |
srf | +0.039 |
Neg logit contributions | |
sim | -0.020 |
quit | -0.020 |
Buchanan | -0.019 |
keley | -0.019 |
kitten | -0.019 |
Token | ves |
Token ID | 1158 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
dra | +0.026 |
� | +0.026 |
�� | +0.026 |
EStreamFrame | +0.023 |
srf | +0.023 |
Neg logit contributions | |
sim | -0.024 |
Buchanan | -0.024 |
quit | -0.023 |
kitten | -0.023 |
Cain | -0.023 |
Token | in |
Token ID | 287 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
�� | +0.039 |
� | +0.039 |
dra | +0.039 |
srf | +0.036 |
�士 | +0.036 |
Neg logit contributions | |
sim | -0.023 |
Buchanan | -0.021 |
quit | -0.021 |
kitten | -0.021 |
Cain | -0.021 |
Token | Kan |
Token ID | 14248 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
�� | +0.031 |
dra | +0.031 |
� | +0.031 |
srf | +0.028 |
�士 | +0.028 |
Neg logit contributions | |
sim | -0.020 |
Buchanan | -0.019 |
Cain | -0.019 |
quit | -0.019 |
Kap | -0.019 |
Token | akia |
Token ID | 21897 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
� | +0.054 |
� | +0.051 |
� | +0.051 |
�� | +0.050 |
�士 | +0.048 |
Neg logit contributions | |
quit | -0.062 |
keley | -0.061 |
sim | -0.060 |
Buchanan | -0.059 |
shame | -0.059 |
Token | area |
Token ID | 1989 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
�� | +0.275 |
dra | +0.273 |
� | +0.273 |
srf | +0.253 |
�士 | +0.253 |
Neg logit contributions | |
sim | -0.161 |
Buchanan | -0.155 |
quit | -0.153 |
Cain | -0.152 |
kitten | -0.150 |
Token | , |
Token ID | 11 |
Feature activation | +4.56e-02 |
Pos logit contributions | |
�� | +0.039 |
� | +0.039 |
dra | +0.038 |
srf | +0.036 |
�士 | +0.036 |
Neg logit contributions | |
sim | -0.024 |
Buchanan | -0.023 |
quit | -0.022 |
Cain | -0.022 |
kitten | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
�� | +0.046 |
� | +0.045 |
dra | +0.045 |
EStreamFrame | +0.042 |
�士 | +0.042 |
Neg logit contributions | |
sim | -0.029 |
Kap | -0.027 |
Buchanan | -0.027 |
Cain | -0.027 |
quit | -0.027 |
Token | massive |
Token ID | 4858 |
Feature activation | +6.19e-02 |
Pos logit contributions | |
�� | +0.031 |
� | +0.031 |
dra | +0.031 |
�士 | +0.029 |
srf | +0.029 |
Neg logit contributions | |
sim | -0.019 |
kitten | -0.018 |
quit | -0.018 |
Buchanan | -0.018 |
shame | -0.018 |
Token | residential |
Token ID | 12420 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
�� | +0.063 |
� | +0.062 |
dra | +0.061 |
srf | +0.058 |
� | +0.057 |
Neg logit contributions | |
sim | -0.039 |
Buchanan | -0.037 |
kitten | -0.037 |
Cain | -0.037 |
shame | -0.036 |
Token | afterwards |
Token ID | 12979 |
Feature activation | -8.26e-03 |
Pos logit contributions | |
�� | +0.039 |
� | +0.039 |
dra | +0.038 |
�士 | +0.037 |
srf | +0.037 |
Neg logit contributions | |
sim | -0.019 |
kitten | -0.018 |
Buchanan | -0.018 |
Cain | -0.018 |
shame | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
sim | +0.004 |
quit | +0.004 |
Buchanan | +0.004 |
kitten | +0.004 |
Cain | +0.004 |
Neg logit contributions | |
�� | -0.009 |
� | -0.009 |
dra | -0.009 |
�士 | -0.008 |
srf | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -9.88e-03 |
Pos logit contributions | |
�� | +0.018 |
� | +0.018 |
dra | +0.018 |
srf | +0.018 |
EStreamFrame | +0.017 |
Neg logit contributions | |
Cain | -0.010 |
Buchanan | -0.010 |
sim | -0.010 |
Kap | -0.009 |
quit | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -8.91e-03 |
Pos logit contributions | |
sim | +0.003 |
Buchanan | +0.003 |
quit | +0.003 |
Cain | +0.003 |
Kap | +0.003 |
Neg logit contributions | |
� | -0.014 |
� | -0.014 |
srf | -0.014 |
� | -0.014 |
�� | -0.014 |
Token | Reg |
Token ID | 8081 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
quit | +0.007 |
sim | +0.006 |
Cain | +0.006 |
Buchanan | +0.006 |
Kap | +0.006 |
Neg logit contributions | |
srf | -0.008 |
� | -0.008 |
� | -0.008 |
� | -0.008 |
�� | -0.008 |
Token | ulators |
Token ID | 24325 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
�� | +0.038 |
� | +0.038 |
dra | +0.036 |
srf | +0.035 |
�士 | +0.035 |
Neg logit contributions | |
sim | -0.036 |
Buchanan | -0.036 |
quit | -0.035 |
keley | -0.035 |
kitten | -0.035 |
Token | estimate |
Token ID | 8636 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
�� | +0.306 |
� | +0.293 |
dra | +0.290 |
� | +0.281 |
�士 | +0.280 |
Neg logit contributions | |
sim | -0.142 |
shame | -0.135 |
Buchanan | -0.134 |
quit | -0.134 |
spat | -0.132 |
Token | consumers |
Token ID | 7008 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
sim | +0.010 |
Buchanan | +0.010 |
Cain | +0.010 |
quit | +0.010 |
kitten | +0.010 |
Neg logit contributions | |
�� | -0.018 |
� | -0.018 |
dra | -0.018 |
srf | -0.017 |
EStreamFrame | -0.017 |
Token | have |
Token ID | 423 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
sim | +0.014 |
shame | +0.014 |
quit | +0.013 |
spat | +0.013 |
Buchanan | +0.013 |
Neg logit contributions | |
�� | -0.028 |
� | -0.027 |
dra | -0.027 |
srf | -0.026 |
� | -0.026 |
Token | been |
Token ID | 587 |
Feature activation | +1.96e-03 |
Pos logit contributions | |
sim | +0.008 |
shame | +0.007 |
spat | +0.007 |
Cain | +0.007 |
Buchanan | +0.007 |
Neg logit contributions | |
�� | -0.015 |
� | -0.014 |
dra | -0.014 |
srf | -0.014 |
� | -0.013 |
Token | over |
Token ID | 625 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
�� | +0.002 |
dra | +0.002 |
� | +0.002 |
srf | +0.002 |
� | +0.002 |
Neg logit contributions | |
sim | -0.001 |
shame | -0.001 |
spat | -0.001 |
Cain | -0.001 |
Buchanan | -0.001 |
Token | learned |
Token ID | 4499 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
sim | +0.005 |
Buchanan | +0.005 |
shame | +0.005 |
quit | +0.005 |
Cain | +0.005 |
Neg logit contributions | |
�� | -0.006 |
dra | -0.006 |
� | -0.006 |
srf | -0.005 |
�士 | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
� | +0.059 |
dra | +0.059 |
�� | +0.059 |
srf | +0.054 |
EStreamFrame | +0.053 |
Neg logit contributions | |
quit | -0.036 |
sim | -0.036 |
Buchanan | -0.036 |
keley | -0.036 |
Cain | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
Cain | +0.008 |
sim | +0.008 |
Kap | +0.008 |
Buchanan | +0.008 |
quit | +0.007 |
Neg logit contributions | |
�� | -0.014 |
dra | -0.013 |
� | -0.013 |
srf | -0.013 |
EStreamFrame | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
sim | +0.007 |
Buchanan | +0.006 |
quit | +0.006 |
Kap | +0.006 |
Cain | +0.006 |
Neg logit contributions | |
� | -0.028 |
� | -0.027 |
srf | -0.027 |
� | -0.027 |
�� | -0.026 |
Token | Reg |
Token ID | 8081 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
quit | +0.018 |
sim | +0.018 |
keley | +0.018 |
Kap | +0.017 |
Cain | +0.017 |
Neg logit contributions | |
� | -0.021 |
srf | -0.021 |
� | -0.021 |
�� | -0.021 |
� | -0.021 |
Token | ulators |
Token ID | 24325 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
�� | +0.035 |
� | +0.034 |
dra | +0.033 |
�士 | +0.031 |
srf | +0.031 |
Neg logit contributions | |
sim | -0.043 |
Buchanan | -0.042 |
quit | -0.042 |
keley | -0.042 |
kitten | -0.041 |
Token | are |
Token ID | 389 |
Feature activation | -2.19e-03 |
Pos logit contributions | |
�� | +0.295 |
� | +0.287 |
dra | +0.283 |
�士 | +0.269 |
� | +0.269 |
Neg logit contributions | |
sim | -0.150 |
Buchanan | -0.142 |
quit | -0.141 |
Cain | -0.141 |
shame | -0.140 |
Token | apparently |
Token ID | 5729 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
sim | +0.001 |
kitten | +0.001 |
shame | +0.001 |
Cain | +0.001 |
Buchanan | +0.001 |
Neg logit contributions | |
�� | -0.002 |
� | -0.002 |
dra | -0.002 |
� | -0.002 |
srf | -0.002 |
Token | interested |
Token ID | 4609 |
Feature activation | -4.21e-03 |
Pos logit contributions | |
�� | +0.036 |
� | +0.035 |
dra | +0.035 |
srf | +0.033 |
� | +0.032 |
Neg logit contributions | |
sim | -0.022 |
kitten | -0.020 |
Buchanan | -0.020 |
shame | -0.020 |
Cain | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | +6.91e-03 |
Pos logit contributions | |
keley | +0.003 |
kitten | +0.003 |
quit | +0.003 |
sim | +0.002 |
Buchanan | +0.002 |
Neg logit contributions | |
� | -0.004 |
�� | -0.004 |
dra | -0.004 |
EStreamFrame | -0.004 |
srf | -0.004 |
Token | information |
Token ID | 1321 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
dra | +0.007 |
�� | +0.007 |
� | +0.007 |
srf | +0.006 |
� | +0.006 |
Neg logit contributions | |
sim | -0.005 |
Cain | -0.004 |
Buchanan | -0.004 |
shame | -0.004 |
kitten | -0.004 |
Token | company |
Token ID | 1664 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
sim | +0.007 |
shame | +0.007 |
Buchanan | +0.007 |
Cain | +0.007 |
kitten | +0.007 |
Neg logit contributions | |
�� | -0.010 |
� | -0.010 |
dra | -0.010 |
EStreamFrame | -0.010 |
�士 | -0.010 |
Token | tries |
Token ID | 8404 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
�� | +0.030 |
� | +0.029 |
dra | +0.029 |
srf | +0.028 |
� | +0.028 |
Neg logit contributions | |
sim | -0.017 |
shame | -0.016 |
quit | -0.016 |
Buchanan | -0.016 |
Cain | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +6.08e-03 |
Pos logit contributions | |
� | +0.017 |
dra | +0.017 |
�� | +0.017 |
�士 | +0.016 |
srf | +0.016 |
Neg logit contributions | |
quit | -0.009 |
Buchanan | -0.009 |
sim | -0.009 |
keley | -0.009 |
Cain | -0.009 |
Token | discredit |
Token ID | 34019 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
�� | +0.006 |
dra | +0.006 |
� | +0.006 |
� | +0.006 |
�士 | +0.006 |
Neg logit contributions | |
sim | -0.004 |
shame | -0.004 |
kitten | -0.004 |
quit | -0.004 |
Cain | -0.004 |
Token | Oliv |
Token ID | 40019 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
sim | +0.021 |
Buchanan | +0.021 |
Cain | +0.021 |
quit | +0.020 |
kitten | +0.020 |
Neg logit contributions | |
dra | -0.032 |
�� | -0.032 |
� | -0.032 |
srf | -0.030 |
EStreamFrame | -0.030 |
Token | ieri |
Token ID | 29864 |
Feature activation | +2.61e-01 |
Pos logit contributions | |
sim | +0.015 |
quit | +0.015 |
keley | +0.014 |
Buchanan | +0.014 |
kitten | +0.014 |
Neg logit contributions | |
� | -0.010 |
� | -0.010 |
�� | -0.010 |
� | -0.009 |
srf | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
�� | +0.284 |
dra | +0.284 |
� | +0.281 |
�士 | +0.266 |
srf | +0.264 |
Neg logit contributions | |
sim | -0.138 |
Buchanan | -0.133 |
quit | -0.131 |
Cain | -0.131 |
kitten | -0.130 |
Token | have |
Token ID | 423 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
sim | +0.010 |
Cain | +0.010 |
shame | +0.010 |
Buchanan | +0.010 |
kitten | +0.010 |
Neg logit contributions | |
�� | -0.016 |
dra | -0.016 |
� | -0.016 |
� | -0.015 |
srf | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
sim | +0.023 |
Cain | +0.023 |
quit | +0.023 |
Buchanan | +0.023 |
kitten | +0.022 |
Neg logit contributions | |
�� | -0.046 |
dra | -0.045 |
� | -0.045 |
srf | -0.043 |
�士 | -0.042 |
Token | fired |
Token ID | 6294 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
sim | +0.009 |
shame | +0.008 |
quit | +0.008 |
Buchanan | +0.008 |
spat | +0.008 |
Neg logit contributions | |
�� | -0.015 |
dra | -0.015 |
� | -0.015 |
srf | -0.014 |
� | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
�� | +0.024 |
� | +0.024 |
dra | +0.023 |
�士 | +0.022 |
srf | +0.022 |
Neg logit contributions | |
sim | -0.011 |
quit | -0.011 |
Buchanan | -0.010 |
Cain | -0.010 |
shame | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
�� | +0.062 |
� | +0.060 |
srf | +0.059 |
dra | +0.059 |
� | +0.059 |
Neg logit contributions | |
Buchanan | -0.017 |
sim | -0.016 |
kitten | -0.015 |
quit | -0.015 |
Cain | -0.015 |
Token | proposed |
Token ID | 5150 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
sim | +0.009 |
Buchanan | +0.009 |
kitten | +0.009 |
shame | +0.009 |
Cain | +0.009 |
Neg logit contributions | |
dra | -0.014 |
�� | -0.014 |
� | -0.014 |
EStreamFrame | -0.013 |
srf | -0.013 |
Token | � |
Token ID | 564 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
sim | +0.022 |
kitten | +0.021 |
Buchanan | +0.021 |
shame | +0.021 |
Cain | +0.021 |
Neg logit contributions | |
dra | -0.030 |
�� | -0.030 |
� | -0.030 |
EStreamFrame | -0.029 |
srf | -0.028 |
Token | � |
Token ID | 250 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
dra | +0.010 |
� | +0.010 |
�� | +0.010 |
srf | +0.010 |
EStreamFrame | +0.009 |
Neg logit contributions | |
Buchanan | -0.008 |
quit | -0.008 |
sim | -0.008 |
kitten | -0.008 |
keley | -0.008 |
Token | bath |
Token ID | 37648 |
Feature activation | -1.36e-04 |
Pos logit contributions | |
�� | +0.036 |
� | +0.035 |
dra | +0.034 |
srf | +0.034 |
� | +0.033 |
Neg logit contributions | |
quit | -0.028 |
sim | -0.026 |
keley | -0.026 |
kitten | -0.026 |
Buchanan | -0.026 |
Token | room |
Token ID | 3823 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
sim | +0.000 |
Buchanan | +0.000 |
kitten | +0.000 |
shame | +0.000 |
quit | +0.000 |
Neg logit contributions | |
� | -0.000 |
�� | -0.000 |
dra | -0.000 |
EStreamFrame | -0.000 |
srf | -0.000 |
Token | bills |
Token ID | 9024 |
Feature activation | -7.10e-02 |
Pos logit contributions | |
�� | +0.277 |
� | +0.274 |
dra | +0.274 |
EStreamFrame | +0.258 |
srf | +0.255 |
Neg logit contributions | |
sim | -0.148 |
kitten | -0.136 |
Buchanan | -0.136 |
shame | -0.134 |
keley | -0.132 |
Token | , |
Token ID | 11 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
sim | +0.039 |
Buchanan | +0.037 |
kitten | +0.037 |
quit | +0.037 |
Cain | +0.036 |
Neg logit contributions | |
dra | -0.076 |
�� | -0.075 |
� | -0.074 |
�士 | -0.070 |
srf | -0.070 |
Token | � |
Token ID | 447 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
dra | +0.029 |
�� | +0.029 |
� | +0.029 |
EStreamFrame | +0.027 |
�士 | +0.027 |
Neg logit contributions | |
sim | -0.019 |
Buchanan | -0.019 |
shame | -0.019 |
kitten | -0.018 |
Cain | -0.018 |
Token | � |
Token ID | 251 |
Feature activation | +3.30e-02 |
Pos logit contributions | |
dra | +0.022 |
� | +0.021 |
�� | +0.021 |
srf | +0.020 |
EStreamFrame | +0.019 |
Neg logit contributions | |
Buchanan | -0.019 |
sim | -0.019 |
quit | -0.018 |
keley | -0.018 |
kitten | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +6.88e-03 |
Pos logit contributions | |
� | +0.032 |
�� | +0.032 |
dra | +0.032 |
�士 | +0.031 |
EStreamFrame | +0.031 |
Neg logit contributions | |
sim | -0.021 |
Buchanan | -0.020 |
shame | -0.020 |
Cain | -0.020 |
kitten | -0.020 |
Token | Long |
Token ID | 5882 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
� | +0.041 |
dra | +0.041 |
�� | +0.041 |
srf | +0.040 |
�士 | +0.040 |
Neg logit contributions | |
Buchanan | -0.016 |
sim | -0.016 |
quit | -0.016 |
keley | -0.016 |
Kap | -0.015 |
Token | Way |
Token ID | 6378 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
Buchanan | +0.014 |
sim | +0.014 |
quit | +0.014 |
Cain | +0.014 |
keley | +0.013 |
Neg logit contributions | |
� | -0.022 |
�� | -0.022 |
dra | -0.022 |
srf | -0.021 |
�士 | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
sim | +0.008 |
Buchanan | +0.007 |
quit | +0.007 |
Cain | +0.007 |
Kap | +0.007 |
Neg logit contributions | |
�� | -0.017 |
� | -0.016 |
dra | -0.016 |
�士 | -0.016 |
srf | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
� | +0.029 |
� | +0.029 |
srf | +0.028 |
� | +0.028 |
�� | +0.028 |
Neg logit contributions | |
sim | -0.008 |
Buchanan | -0.007 |
quit | -0.007 |
Cain | -0.007 |
Kap | -0.007 |
Token | Con |
Token ID | 3103 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
srf | +0.019 |
� | +0.019 |
� | +0.019 |
�� | +0.019 |
� | +0.018 |
Neg logit contributions | |
quit | -0.015 |
sim | -0.014 |
keley | -0.014 |
Cain | -0.014 |
Buchanan | -0.014 |
Token | ventions |
Token ID | 16593 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
�� | +0.015 |
� | +0.015 |
dra | +0.014 |
srf | +0.014 |
�士 | +0.013 |
Neg logit contributions | |
quit | -0.015 |
sim | -0.015 |
keley | -0.015 |
Buchanan | -0.015 |
kitten | -0.015 |
Token | usually |
Token ID | 3221 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
�� | +0.279 |
� | +0.274 |
dra | +0.273 |
�士 | +0.260 |
srf | +0.259 |
Neg logit contributions | |
sim | -0.145 |
quit | -0.137 |
Buchanan | -0.135 |
kitten | -0.134 |
Cain | -0.134 |
Token | give |
Token ID | 1577 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
�� | +0.058 |
� | +0.057 |
dra | +0.056 |
� | +0.055 |
srf | +0.054 |
Neg logit contributions | |
sim | -0.033 |
kitten | -0.031 |
shame | -0.031 |
quit | -0.030 |
Buchanan | -0.030 |
Token | out |
Token ID | 503 |
Feature activation | +5.19e-03 |
Pos logit contributions | |
�� | +0.012 |
� | +0.012 |
dra | +0.012 |
srf | +0.011 |
EStreamFrame | +0.011 |
Neg logit contributions | |
sim | -0.006 |
kitten | -0.005 |
Cain | -0.005 |
shame | -0.005 |
Buchanan | -0.005 |
Token | guide |
Token ID | 5698 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
�� | +0.005 |
� | +0.005 |
dra | +0.005 |
srf | +0.005 |
� | +0.005 |
Neg logit contributions | |
sim | -0.003 |
kitten | -0.003 |
shame | -0.003 |
Buchanan | -0.003 |
Cain | -0.003 |
Token | books |
Token ID | 12106 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
�� | +0.066 |
� | +0.065 |
dra | +0.062 |
�士 | +0.061 |
EStreamFrame | +0.061 |
Neg logit contributions | |
sim | -0.045 |
kitten | -0.042 |
quit | -0.042 |
Buchanan | -0.040 |
kittens | -0.040 |
Token | – |
Token ID | 784 |
Feature activation | +8.13e-02 |
Pos logit contributions | |
�� | +0.004 |
� | +0.004 |
dra | +0.004 |
EStreamFrame | +0.004 |
srf | +0.003 |
Neg logit contributions | |
sim | -0.002 |
Cain | -0.002 |
kitten | -0.002 |
Buchanan | -0.002 |
quit | -0.002 |
Token | one |
Token ID | 530 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
�� | +0.083 |
� | +0.082 |
dra | +0.080 |
EStreamFrame | +0.075 |
�士 | +0.075 |
Neg logit contributions | |
sim | -0.051 |
Cain | -0.049 |
quit | -0.048 |
kitten | -0.048 |
Buchanan | -0.048 |
Token | from |
Token ID | 422 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
�� | +0.027 |
� | +0.027 |
dra | +0.027 |
srf | +0.025 |
EStreamFrame | +0.025 |
Neg logit contributions | |
sim | -0.015 |
Buchanan | -0.014 |
kitten | -0.014 |
Cain | -0.014 |
quit | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
�� | +0.017 |
� | +0.017 |
dra | +0.017 |
srf | +0.015 |
�士 | +0.015 |
Neg logit contributions | |
sim | -0.011 |
Buchanan | -0.010 |
Cain | -0.010 |
quit | -0.010 |
kitten | -0.010 |
Token | Kimber |
Token ID | 36015 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
�� | +0.029 |
� | +0.028 |
dra | +0.028 |
srf | +0.026 |
�士 | +0.026 |
Neg logit contributions | |
sim | -0.019 |
Buchanan | -0.019 |
Cain | -0.019 |
kitten | -0.018 |
Kap | -0.018 |
Token | ley |
Token ID | 1636 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
�� | +0.022 |
� | +0.022 |
dra | +0.021 |
�士 | +0.021 |
srf | +0.020 |
Neg logit contributions | |
sim | -0.017 |
keley | -0.017 |
Buchanan | -0.016 |
quit | -0.016 |
kitten | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
�� | +0.275 |
� | +0.274 |
dra | +0.271 |
�士 | +0.256 |
srf | +0.254 |
Neg logit contributions | |
sim | -0.132 |
Buchanan | -0.128 |
quit | -0.126 |
Cain | -0.124 |
kitten | -0.123 |
Token | western |
Token ID | 8830 |
Feature activation | +4.63e-02 |
Pos logit contributions | |
�� | +0.022 |
� | +0.022 |
dra | +0.022 |
srf | +0.020 |
EStreamFrame | +0.020 |
Neg logit contributions | |
sim | -0.015 |
Buchanan | -0.014 |
quit | -0.014 |
Cain | -0.014 |
kitten | -0.014 |
Token | Northern |
Token ID | 8342 |
Feature activation | +8.14e-02 |
Pos logit contributions | |
�� | +0.048 |
� | +0.048 |
dra | +0.047 |
srf | +0.045 |
�士 | +0.044 |
Neg logit contributions | |
sim | -0.027 |
Buchanan | -0.027 |
Cain | -0.026 |
Kap | -0.026 |
kitten | -0.026 |
Token | Territory |
Token ID | 25219 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
� | +0.084 |
�� | +0.084 |
dra | +0.081 |
srf | +0.077 |
�士 | +0.077 |
Neg logit contributions | |
sim | -0.049 |
Buchanan | -0.048 |
Cain | -0.047 |
Kap | -0.047 |
kitten | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
sim | +0.003 |
Buchanan | +0.002 |
quit | +0.002 |
kitten | +0.002 |
Cain | +0.002 |
Neg logit contributions | |
�� | -0.005 |
� | -0.005 |
dra | -0.005 |
srf | -0.004 |
�士 | -0.004 |
Token | wiret |
Token ID | 33509 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
�� | +0.038 |
dra | +0.038 |
� | +0.037 |
�士 | +0.035 |
srf | +0.035 |
Neg logit contributions | |
sim | -0.039 |
kitten | -0.036 |
Buchanan | -0.036 |
Cain | -0.036 |
quit | -0.036 |
Token | apping |
Token ID | 5912 |
Feature activation | -2.42e-01 |
Pos logit contributions | |
�� | +0.032 |
� | +0.032 |
dra | +0.031 |
srf | +0.030 |
�士 | +0.030 |
Neg logit contributions | |
sim | -0.015 |
quit | -0.015 |
keley | -0.014 |
Buchanan | -0.014 |
Cain | -0.014 |
Token | program |
Token ID | 1430 |
Feature activation | -8.69e-03 |
Pos logit contributions | |
sim | +0.138 |
Cain | +0.123 |
Buchanan | +0.123 |
shame | +0.122 |
kitten | +0.121 |
Neg logit contributions | |
�� | -0.266 |
dra | -0.260 |
� | -0.260 |
�士 | -0.251 |
srf | -0.248 |
Token | was |
Token ID | 373 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
sim | +0.005 |
Buchanan | +0.005 |
Cain | +0.005 |
quit | +0.005 |
shame | +0.005 |
Neg logit contributions | |
�� | -0.009 |
� | -0.009 |
dra | -0.009 |
�士 | -0.009 |
srf | -0.009 |
Token | unjust |
Token ID | 21218 |
Feature activation | -9.42e-02 |
Pos logit contributions | |
�� | +0.026 |
dra | +0.026 |
� | +0.026 |
srf | +0.025 |
� | +0.024 |
Neg logit contributions | |
sim | -0.015 |
Buchanan | -0.014 |
Cain | -0.014 |
shame | -0.014 |
kitten | -0.014 |
Token | ified |
Token ID | 1431 |
Feature activation | +2.51e-01 |
Pos logit contributions | |
sim | +0.061 |
Buchanan | +0.059 |
quit | +0.059 |
keley | +0.058 |
Cain | +0.058 |
Neg logit contributions | |
� | -0.090 |
dra | -0.090 |
�� | -0.089 |
srf | -0.083 |
�士 | -0.083 |
Token | and |
Token ID | 290 |
Feature activation | +4.49e-02 |
Pos logit contributions | |
dra | +0.266 |
� | +0.266 |
�� | +0.265 |
�士 | +0.251 |
srf | +0.250 |
Neg logit contributions | |
sim | -0.136 |
Buchanan | -0.131 |
quit | -0.131 |
Cain | -0.128 |
shame | -0.127 |
Token | undermined |
Token ID | 31256 |
Feature activation | +7.58e-02 |
Pos logit contributions | |
dra | +0.045 |
� | +0.044 |
�� | +0.044 |
srf | +0.043 |
EStreamFrame | +0.041 |
Neg logit contributions | |
sim | -0.029 |
Buchanan | -0.028 |
shame | -0.028 |
Cain | -0.027 |
kitten | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
dra | +0.075 |
� | +0.074 |
�� | +0.073 |
srf | +0.070 |
EStreamFrame | +0.069 |
Neg logit contributions | |
sim | -0.049 |
Buchanan | -0.047 |
Cain | -0.047 |
shame | -0.046 |
Kap | -0.046 |
Token | rule |
Token ID | 3896 |
Feature activation | +5.85e-02 |
Pos logit contributions | |
dra | +0.027 |
� | +0.027 |
�� | +0.027 |
srf | +0.026 |
� | +0.025 |
Neg logit contributions | |
sim | -0.020 |
shame | -0.019 |
Buchanan | -0.019 |
Kap | -0.018 |
Cain | -0.018 |
Token | of |
Token ID | 286 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
� | +0.059 |
�� | +0.059 |
dra | +0.059 |
�士 | +0.054 |
srf | +0.053 |
Neg logit contributions | |
quit | -0.033 |
keley | -0.033 |
sim | -0.033 |
Buchanan | -0.033 |
kitten | -0.032 |
Token | ot |
Token ID | 313 |
Feature activation | -2.66e-02 |
Pos logit contributions | |
�� | +0.026 |
� | +0.025 |
dra | +0.025 |
EStreamFrame | +0.023 |
�士 | +0.023 |
Neg logit contributions | |
sim | -0.020 |
quit | -0.020 |
Cain | -0.020 |
keley | -0.019 |
kitten | -0.019 |
Token | ex |
Token ID | 1069 |
Feature activation | -7.42e-02 |
Pos logit contributions | |
sim | +0.015 |
quit | +0.014 |
Buchanan | +0.014 |
Cain | +0.014 |
keley | +0.014 |
Neg logit contributions | |
�� | -0.028 |
� | -0.028 |
dra | -0.027 |
srf | -0.026 |
EStreamFrame | -0.026 |
Token | forces |
Token ID | 3386 |
Feature activation | -8.16e-02 |
Pos logit contributions | |
sim | +0.050 |
quit | +0.048 |
Cain | +0.048 |
kitten | +0.047 |
Buchanan | +0.047 |
Neg logit contributions | |
�� | -0.072 |
� | -0.071 |
dra | -0.071 |
srf | -0.066 |
EStreamFrame | -0.066 |
Token | Nancy |
Token ID | 18496 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
sim | +0.056 |
Cain | +0.055 |
Buchanan | +0.055 |
kitten | +0.054 |
quit | +0.053 |
Neg logit contributions | |
�� | -0.077 |
dra | -0.077 |
� | -0.076 |
EStreamFrame | -0.071 |
�士 | -0.071 |
Token | Oliv |
Token ID | 40019 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
�� | +0.044 |
� | +0.044 |
dra | +0.043 |
EStreamFrame | +0.041 |
srf | +0.041 |
Neg logit contributions | |
Buchanan | -0.030 |
Cain | -0.030 |
sim | -0.029 |
quit | -0.028 |
Kap | -0.028 |
Token | ieri |
Token ID | 29864 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
sim | +0.014 |
quit | +0.014 |
Buchanan | +0.014 |
Cain | +0.014 |
keley | +0.014 |
Neg logit contributions | |
�� | -0.015 |
� | -0.015 |
dra | -0.014 |
srf | -0.014 |
�士 | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -7.21e-03 |
Pos logit contributions | |
� | +0.253 |
dra | +0.253 |
�� | +0.253 |
srf | +0.232 |
�士 | +0.232 |
Neg logit contributions | |
sim | -0.140 |
quit | -0.137 |
Buchanan | -0.135 |
keley | -0.135 |
kitten | -0.134 |
Token | a |
Token ID | 257 |
Feature activation | -7.96e-03 |
Pos logit contributions | |
sim | +0.004 |
Buchanan | +0.004 |
Cain | +0.004 |
kitten | +0.004 |
quit | +0.004 |
Neg logit contributions | |
dra | -0.007 |
� | -0.007 |
�� | -0.007 |
EStreamFrame | -0.007 |
�士 | -0.007 |
Token | clinical |
Token ID | 8668 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
sim | +0.005 |
Buchanan | +0.005 |
kitten | +0.005 |
Cain | +0.005 |
shame | +0.005 |
Neg logit contributions | |
�� | -0.008 |
dra | -0.008 |
� | -0.008 |
srf | -0.007 |
�士 | -0.007 |
Token | researcher |
Token ID | 13453 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
sim | +0.035 |
kitten | +0.033 |
Buchanan | +0.032 |
shame | +0.032 |
Cain | +0.031 |
Neg logit contributions | |
�� | -0.057 |
� | -0.057 |
dra | -0.056 |
�士 | -0.053 |
EStreamFrame | -0.053 |
Token | at |
Token ID | 379 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
sim | +0.007 |
Buchanan | +0.007 |
quit | +0.007 |
kitten | +0.007 |
Cain | +0.007 |
Neg logit contributions | |
dra | -0.016 |
�� | -0.016 |
� | -0.016 |
srf | -0.015 |
�士 | -0.015 |
Token | for |
Token ID | 1640 |
Feature activation | +5.96e-02 |
Pos logit contributions | |
�� | +0.011 |
� | +0.011 |
dra | +0.011 |
�士 | +0.010 |
srf | +0.010 |
Neg logit contributions | |
sim | -0.009 |
quit | -0.009 |
Buchanan | -0.009 |
kitten | -0.009 |
Cain | -0.009 |
Token | maximum |
Token ID | 5415 |
Feature activation | +1.20e-03 |
Pos logit contributions | |
� | +0.058 |
�� | +0.058 |
dra | +0.058 |
�士 | +0.054 |
srf | +0.053 |
Neg logit contributions | |
sim | -0.040 |
Buchanan | -0.037 |
Cain | -0.037 |
kitten | -0.037 |
shame | -0.037 |
Token | strength |
Token ID | 4202 |
Feature activation | -1.91e-02 |
Pos logit contributions | |
� | +0.001 |
�� | +0.001 |
dra | +0.001 |
�士 | +0.001 |
� | +0.001 |
Neg logit contributions | |
sim | -0.001 |
Buchanan | -0.001 |
Cain | -0.001 |
shame | -0.001 |
kitten | -0.001 |
Token | ). |
Token ID | 737 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
sim | +0.011 |
quit | +0.011 |
Buchanan | +0.011 |
Cain | +0.011 |
kitten | +0.011 |
Neg logit contributions | |
�� | -0.020 |
� | -0.020 |
dra | -0.020 |
�士 | -0.018 |
srf | -0.018 |
Token | Ch |
Token ID | 609 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
sim | +0.015 |
Cain | +0.014 |
Buchanan | +0.014 |
Kap | +0.014 |
Mazda | +0.013 |
Neg logit contributions | |
�� | -0.023 |
� | -0.022 |
srf | -0.021 |
dra | -0.021 |
� | -0.021 |
Token | assis |
Token ID | 20297 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
�� | +0.006 |
� | +0.006 |
dra | +0.006 |
srf | +0.005 |
�士 | +0.005 |
Neg logit contributions | |
sim | -0.013 |
quit | -0.013 |
Buchanan | -0.013 |
keley | -0.013 |
Cain | -0.013 |
Token | conversion |
Token ID | 11315 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
� | +0.237 |
�� | +0.237 |
dra | +0.230 |
�士 | +0.219 |
EStreamFrame | +0.215 |
Neg logit contributions | |
sim | -0.170 |
Buchanan | -0.161 |
Cain | -0.161 |
kitten | -0.158 |
quit | -0.156 |
Token | allows |
Token ID | 3578 |
Feature activation | -2.19e-02 |
Pos logit contributions | |
�� | +0.033 |
� | +0.033 |
dra | +0.032 |
�士 | +0.031 |
EStreamFrame | +0.030 |
Neg logit contributions | |
sim | -0.019 |
kitten | -0.018 |
Buchanan | -0.018 |
Cain | -0.018 |
quit | -0.018 |
Token | you |
Token ID | 345 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
sim | +0.012 |
Buchanan | +0.011 |
Cain | +0.011 |
quit | +0.011 |
kitten | +0.011 |
Neg logit contributions | |
� | -0.023 |
�� | -0.023 |
dra | -0.023 |
�士 | -0.022 |
EStreamFrame | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
quit | +0.027 |
Buchanan | +0.026 |
keley | +0.026 |
kitten | +0.025 |
Cain | +0.025 |
Neg logit contributions | |
� | -0.039 |
dra | -0.039 |
�� | -0.039 |
srf | -0.036 |
�士 | -0.036 |
Token | make |
Token ID | 787 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
sim | +0.021 |
shame | +0.020 |
kitten | +0.020 |
Buchanan | +0.019 |
Cain | +0.019 |
Neg logit contributions | |
�� | -0.031 |
� | -0.030 |
dra | -0.029 |
� | -0.029 |
�士 | -0.028 |
Token | girls |
Token ID | 4813 |
Feature activation | +3.09e-03 |
Pos logit contributions | |
sim | +0.043 |
Cain | +0.042 |
Buchanan | +0.042 |
shame | +0.041 |
kitten | +0.041 |
Neg logit contributions | |
dra | -0.066 |
�� | -0.066 |
� | -0.065 |
srf | -0.060 |
�士 | -0.060 |
Token | up |
Token ID | 510 |
Feature activation | +7.68e-03 |
Pos logit contributions | |
�� | +0.004 |
dra | +0.003 |
� | +0.003 |
�士 | +0.003 |
srf | +0.003 |
Neg logit contributions | |
sim | -0.002 |
kitten | -0.001 |
Buchanan | -0.001 |
Cain | -0.001 |
quit | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +4.89e-04 |
Pos logit contributions | |
�� | +0.009 |
dra | +0.009 |
� | +0.009 |
�士 | +0.008 |
srf | +0.008 |
Neg logit contributions | |
sim | -0.004 |
Buchanan | -0.004 |
quit | -0.004 |
kitten | -0.004 |
Cain | -0.003 |
Token | for |
Token ID | 329 |
Feature activation | +7.86e-04 |
Pos logit contributions | |
�� | +0.001 |
dra | +0.001 |
� | +0.001 |
�士 | +0.000 |
srf | +0.000 |
Neg logit contributions | |
sim | -0.000 |
shame | -0.000 |
kitten | -0.000 |
quit | -0.000 |
Cain | -0.000 |
Token | prom |
Token ID | 1552 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
�� | +0.001 |
� | +0.001 |
dra | +0.001 |
srf | +0.001 |
EStreamFrame | +0.001 |
Neg logit contributions | |
sim | -0.000 |
quit | -0.000 |
Buchanan | -0.000 |
kitten | -0.000 |
Cain | -0.000 |
Token | isc |
Token ID | 2304 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
sim | +0.012 |
quit | +0.011 |
Buchanan | +0.011 |
shame | +0.011 |
Cain | +0.011 |
Neg logit contributions | |
�� | -0.016 |
dra | -0.016 |
� | -0.016 |
srf | -0.015 |
�士 | -0.015 |
Token | uous |
Token ID | 5623 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
�� | +0.173 |
� | +0.169 |
dra | +0.168 |
srf | +0.152 |
�士 | +0.151 |
Neg logit contributions | |
sim | -0.223 |
quit | -0.221 |
Buchanan | -0.219 |
Cain | -0.216 |
kitten | -0.215 |
Token | behaviour |
Token ID | 9172 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
�� | +0.136 |
dra | +0.135 |
� | +0.132 |
�士 | +0.127 |
srf | +0.126 |
Neg logit contributions | |
sim | -0.079 |
kitten | -0.074 |
shame | -0.073 |
quit | -0.073 |
Cain | -0.073 |
Token | . |
Token ID | 13 |
Feature activation | +6.83e-03 |
Pos logit contributions | |
sim | +0.010 |
quit | +0.010 |
kitten | +0.010 |
Cain | +0.010 |
Buchanan | +0.010 |
Neg logit contributions | |
�� | -0.020 |
dra | -0.020 |
� | -0.020 |
�士 | -0.019 |
srf | -0.019 |
Token | � |
Token ID | 447 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
�� | +0.008 |
dra | +0.007 |
srf | +0.007 |
� | +0.007 |
� | +0.007 |
Neg logit contributions | |
Buchanan | -0.004 |
sim | -0.004 |
Cain | -0.004 |
quit | -0.003 |
Kap | -0.003 |
Token | � |
Token ID | 251 |
Feature activation | -4.72e-02 |
Pos logit contributions | |
sim | +0.007 |
quit | +0.007 |
Cain | +0.007 |
Buchanan | +0.007 |
kitten | +0.007 |
Neg logit contributions | |
�� | -0.005 |
� | -0.005 |
dra | -0.005 |
�士 | -0.005 |
srf | -0.004 |
Token | Prom |
Token ID | 10335 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
�� | +0.026 |
� | +0.026 |
dra | +0.026 |
srf | +0.024 |
�士 | +0.024 |
Neg logit contributions | |
sim | -0.017 |
Cain | -0.016 |
Buchanan | -0.016 |
kitten | -0.016 |
shame | -0.016 |
Token | ethe |
Token ID | 10567 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
sim | +0.022 |
Buchanan | +0.022 |
Cain | +0.021 |
quit | +0.021 |
keley | +0.021 |
Neg logit contributions | |
�� | -0.020 |
� | -0.019 |
dra | -0.019 |
srf | -0.017 |
�士 | -0.017 |
Token | a |
Token ID | 64 |
Feature activation | +4.41e-02 |
Pos logit contributions | |
�� | +0.041 |
� | +0.041 |
dra | +0.040 |
srf | +0.039 |
EStreamFrame | +0.038 |
Neg logit contributions | |
quit | -0.017 |
sim | -0.017 |
Buchanan | -0.017 |
keley | -0.017 |
Cain | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
�� | +0.046 |
dra | +0.046 |
� | +0.046 |
�士 | +0.043 |
srf | +0.043 |
Neg logit contributions | |
sim | -0.025 |
quit | -0.024 |
Buchanan | -0.024 |
Cain | -0.024 |
kitten | -0.024 |
Token | serial |
Token ID | 11389 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
�� | +0.027 |
dra | +0.026 |
� | +0.026 |
�士 | +0.024 |
srf | +0.024 |
Neg logit contributions | |
sim | -0.016 |
Cain | -0.015 |
Buchanan | -0.015 |
kitten | -0.015 |
quit | -0.015 |
Token | ized |
Token ID | 1143 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
sim | +0.011 |
kitten | +0.011 |
Cain | +0.011 |
quit | +0.011 |
Buchanan | +0.011 |
Neg logit contributions | |
�� | -0.020 |
� | -0.020 |
dra | -0.020 |
�士 | -0.019 |
EStreamFrame | -0.018 |
Token | from |
Token ID | 422 |
Feature activation | +6.87e-03 |
Pos logit contributions | |
�� | +0.278 |
dra | +0.275 |
� | +0.270 |
�士 | +0.258 |
srf | +0.255 |
Neg logit contributions | |
sim | -0.115 |
Cain | -0.107 |
kitten | -0.107 |
Buchanan | -0.105 |
shame | -0.104 |
Token | 1999 |
Token ID | 7358 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
�� | +0.007 |
dra | +0.007 |
� | +0.007 |
srf | +0.006 |
�士 | +0.006 |
Neg logit contributions | |
sim | -0.004 |
Cain | -0.004 |
Buchanan | -0.004 |
kitten | -0.004 |
shame | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
sim | +0.005 |
Buchanan | +0.005 |
quit | +0.005 |
Cain | +0.005 |
kitten | +0.005 |
Neg logit contributions | |
�� | -0.012 |
dra | -0.012 |
� | -0.012 |
srf | -0.011 |
�士 | -0.011 |
Token | 2005 |
Token ID | 5075 |
Feature activation | +5.07e-04 |
Pos logit contributions | |
sim | +0.007 |
Cain | +0.007 |
Buchanan | +0.006 |
shame | +0.006 |
kitten | +0.006 |
Neg logit contributions | |
�� | -0.014 |
dra | -0.014 |
� | -0.013 |
� | -0.013 |
�士 | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
dra | +0.001 |
�� | +0.001 |
� | +0.001 |
srf | +0.001 |
�士 | +0.001 |
Neg logit contributions | |
sim | -0.000 |
quit | -0.000 |
Buchanan | -0.000 |
Cain | -0.000 |
kitten | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
�� | +0.051 |
dra | +0.051 |
� | +0.051 |
srf | +0.048 |
�士 | +0.047 |
Neg logit contributions | |
sim | -0.025 |
quit | -0.024 |
kitten | -0.024 |
Buchanan | -0.024 |
Cain | -0.024 |
Token | if |
Token ID | 611 |
Feature activation | +3.61e-02 |
Pos logit contributions | |
�� | +0.019 |
� | +0.019 |
dra | +0.019 |
�士 | +0.017 |
srf | +0.017 |
Neg logit contributions | |
sim | -0.011 |
Cain | -0.011 |
shame | -0.011 |
kitten | -0.011 |
Buchanan | -0.011 |
Token | you |
Token ID | 345 |
Feature activation | -1.32e-03 |
Pos logit contributions | |
�� | +0.041 |
� | +0.041 |
dra | +0.040 |
�士 | +0.038 |
srf | +0.038 |
Neg logit contributions | |
sim | -0.017 |
Buchanan | -0.017 |
Cain | -0.016 |
kitten | -0.016 |
shame | -0.016 |
Token | like |
Token ID | 588 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
sim | +0.001 |
quit | +0.001 |
shame | +0.001 |
kitten | +0.001 |
Buchanan | +0.001 |
Neg logit contributions | |
�� | -0.001 |
� | -0.001 |
dra | -0.001 |
� | -0.001 |
srf | -0.001 |
Token | Sab |
Token ID | 9910 |
Feature activation | -8.24e-02 |
Pos logit contributions | |
�� | +0.019 |
� | +0.019 |
dra | +0.019 |
�士 | +0.018 |
� | +0.018 |
Neg logit contributions | |
sim | -0.012 |
kitten | -0.012 |
Buchanan | -0.011 |
Cain | -0.011 |
shame | -0.011 |
Token | rina |
Token ID | 22267 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
quit | +0.063 |
sim | +0.063 |
keley | +0.061 |
Buchanan | +0.061 |
Cain | +0.061 |
Neg logit contributions | |
�� | -0.074 |
� | -0.071 |
� | -0.068 |
� | -0.067 |
�士 | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | +2.07e-02 |
Pos logit contributions | |
�� | +0.250 |
dra | +0.245 |
� | +0.245 |
�士 | +0.230 |
srf | +0.230 |
Neg logit contributions | |
sim | -0.131 |
Buchanan | -0.128 |
Cain | -0.125 |
kitten | -0.125 |
quit | -0.125 |
Token | check |
Token ID | 2198 |
Feature activation | +5.54e-03 |
Pos logit contributions | |
�� | +0.022 |
� | +0.022 |
dra | +0.022 |
�士 | +0.021 |
EStreamFrame | +0.021 |
Neg logit contributions | |
sim | -0.012 |
Buchanan | -0.011 |
shame | -0.011 |
kitten | -0.011 |
Cain | -0.011 |
Token | out |
Token ID | 503 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
� | +0.006 |
�� | +0.006 |
dra | +0.006 |
EStreamFrame | +0.006 |
srf | +0.005 |
Neg logit contributions | |
sim | -0.003 |
Buchanan | -0.003 |
Cain | -0.003 |
kitten | -0.003 |
quit | -0.003 |
Token | my |
Token ID | 616 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
sim | +0.018 |
Buchanan | +0.017 |
Cain | +0.017 |
kitten | +0.017 |
Kap | +0.016 |
Neg logit contributions | |
�� | -0.028 |
� | -0.028 |
dra | -0.027 |
�士 | -0.025 |
srf | -0.025 |
Token | own |
Token ID | 898 |
Feature activation | +1.61e-03 |
Pos logit contributions | |
sim | +0.002 |
Buchanan | +0.002 |
kitten | +0.002 |
Cain | +0.002 |
shame | +0.002 |
Neg logit contributions | |
�� | -0.003 |
� | -0.003 |
dra | -0.003 |
�士 | -0.003 |
� | -0.003 |
Token | belts |
Token ID | 28617 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
�� | +0.038 |
� | +0.038 |
dra | +0.038 |
srf | +0.035 |
�士 | +0.035 |
Neg logit contributions | |
sim | -0.022 |
Buchanan | -0.021 |
kitten | -0.020 |
quit | -0.020 |
Kap | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | +3.68e-02 |
Pos logit contributions | |
�� | +0.024 |
� | +0.024 |
dra | +0.024 |
srf | +0.022 |
�士 | +0.022 |
Neg logit contributions | |
sim | -0.013 |
Buchanan | -0.012 |
quit | -0.012 |
Cain | -0.012 |
kitten | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
�� | +0.037 |
dra | +0.037 |
� | +0.037 |
srf | +0.035 |
�士 | +0.034 |
Neg logit contributions | |
sim | -0.022 |
Buchanan | -0.022 |
Cain | -0.021 |
Kap | -0.021 |
quit | -0.021 |
Token | around |
Token ID | 1088 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
�� | +0.018 |
dra | +0.018 |
� | +0.017 |
�士 | +0.017 |
srf | +0.016 |
Neg logit contributions | |
sim | -0.010 |
quit | -0.009 |
Buchanan | -0.009 |
kitten | -0.009 |
Kap | -0.009 |
Token | Kan |
Token ID | 14248 |
Feature activation | +6.18e-02 |
Pos logit contributions | |
dra | +0.022 |
�� | +0.022 |
� | +0.022 |
srf | +0.021 |
�士 | +0.021 |
Neg logit contributions | |
sim | -0.013 |
Buchanan | -0.013 |
quit | -0.013 |
Cain | -0.013 |
keley | -0.013 |
Token | akia |
Token ID | 21897 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
� | +0.049 |
� | +0.046 |
� | +0.046 |
�� | +0.046 |
srf | +0.044 |
Neg logit contributions | |
quit | -0.057 |
keley | -0.056 |
sim | -0.055 |
Buchanan | -0.054 |
shame | -0.054 |
Token | Complex |
Token ID | 19157 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
�� | +0.241 |
dra | +0.240 |
� | +0.239 |
�士 | +0.224 |
srf | +0.224 |
Neg logit contributions | |
sim | -0.137 |
Buchanan | -0.132 |
quit | -0.130 |
Cain | -0.130 |
Kap | -0.128 |
Token | are |
Token ID | 389 |
Feature activation | +9.46e-03 |
Pos logit contributions | |
dra | +0.072 |
�� | +0.071 |
� | +0.071 |
srf | +0.067 |
�士 | +0.066 |
Neg logit contributions | |
sim | -0.042 |
Buchanan | -0.040 |
Kap | -0.039 |
Cain | -0.039 |
quit | -0.039 |
Token | being |
Token ID | 852 |
Feature activation | +4.16e-03 |
Pos logit contributions | |
�� | +0.010 |
dra | +0.009 |
� | +0.009 |
srf | +0.009 |
EStreamFrame | +0.009 |
Neg logit contributions | |
sim | -0.006 |
Buchanan | -0.006 |
Cain | -0.006 |
kitten | -0.006 |
Kap | -0.006 |
Token | systematically |
Token ID | 25735 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
�� | +0.004 |
� | +0.004 |
dra | +0.004 |
srf | +0.004 |
� | +0.004 |
Neg logit contributions | |
sim | -0.003 |
Buchanan | -0.002 |
spat | -0.002 |
kitten | -0.002 |
quit | -0.002 |
Token | destruct |
Token ID | 15256 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
�� | +0.015 |
� | +0.015 |
dra | +0.015 |
srf | +0.014 |
� | +0.014 |
Neg logit contributions | |
sim | -0.009 |
Buchanan | -0.008 |
Cain | -0.008 |
kitten | -0.008 |
spat | -0.008 |
Token | up |
Token ID | 929 |
Feature activation | -6.65e-02 |
Pos logit contributions | |
�� | +0.023 |
� | +0.023 |
dra | +0.022 |
�士 | +0.022 |
srf | +0.022 |
Neg logit contributions | |
sim | -0.007 |
quit | -0.007 |
Buchanan | -0.006 |
kitten | -0.006 |
Cain | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
sim | +0.032 |
kitten | +0.030 |
Cain | +0.029 |
quit | +0.029 |
Buchanan | +0.029 |
Neg logit contributions | |
�� | -0.078 |
� | -0.077 |
dra | -0.076 |
�士 | -0.074 |
srf | -0.072 |
Token | But |
Token ID | 887 |
Feature activation | +3.94e-02 |
Pos logit contributions | |
�� | +0.025 |
srf | +0.024 |
� | +0.023 |
� | +0.023 |
� | +0.023 |
Neg logit contributions | |
Cain | -0.016 |
Buchanan | -0.015 |
sim | -0.015 |
Kap | -0.015 |
quit | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
� | +0.043 |
�� | +0.043 |
dra | +0.042 |
� | +0.041 |
srf | +0.041 |
Neg logit contributions | |
sim | -0.022 |
Cain | -0.021 |
Buchanan | -0.020 |
shame | -0.020 |
kitten | -0.020 |
Token | unpredict |
Token ID | 20378 |
Feature activation | -8.22e-03 |
Pos logit contributions | |
sim | +0.009 |
Cain | +0.008 |
shame | +0.008 |
Buchanan | +0.008 |
kitten | +0.008 |
Neg logit contributions | |
� | -0.014 |
�� | -0.014 |
dra | -0.014 |
�士 | -0.013 |
srf | -0.013 |
Token | ability |
Token ID | 1799 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
quit | +0.007 |
Buchanan | +0.007 |
sim | +0.007 |
kitten | +0.007 |
keley | +0.007 |
Neg logit contributions | |
�� | -0.006 |
� | -0.006 |
�士 | -0.006 |
srf | -0.006 |
� | -0.006 |
Token | is |
Token ID | 318 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
�� | +0.260 |
� | +0.258 |
dra | +0.258 |
srf | +0.243 |
�士 | +0.242 |
Neg logit contributions | |
sim | -0.115 |
kitten | -0.109 |
Buchanan | -0.109 |
quit | -0.108 |
Cain | -0.108 |
Token | mit |
Token ID | 10255 |
Feature activation | +5.68e-02 |
Pos logit contributions | |
dra | +0.029 |
�� | +0.029 |
� | +0.029 |
srf | +0.028 |
�士 | +0.028 |
Neg logit contributions | |
sim | -0.016 |
shame | -0.015 |
Cain | -0.015 |
Buchanan | -0.015 |
kitten | -0.015 |
Token | igated |
Token ID | 26963 |
Feature activation | +3.84e-02 |
Pos logit contributions | |
�� | +0.067 |
� | +0.066 |
srf | +0.066 |
�士 | +0.066 |
� | +0.065 |
Neg logit contributions | |
keley | -0.029 |
sim | -0.029 |
quit | -0.029 |
Buchanan | -0.028 |
Cain | -0.027 |
Token | by |
Token ID | 416 |
Feature activation | +4.06e-02 |
Pos logit contributions | |
dra | +0.044 |
�� | +0.044 |
� | +0.044 |
�士 | +0.042 |
srf | +0.041 |
Neg logit contributions | |
sim | -0.019 |
Buchanan | -0.018 |
quit | -0.018 |
Cain | -0.018 |
kitten | -0.017 |
Token | Netflix |
Token ID | 12074 |
Feature activation | +4.25e-03 |
Pos logit contributions | |
� | +0.041 |
�� | +0.041 |
dra | +0.040 |
�士 | +0.038 |
srf | +0.038 |
Neg logit contributions | |
sim | -0.025 |
Cain | -0.024 |
Buchanan | -0.024 |
kitten | -0.024 |
shame | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | +2.25e-02 |
Pos logit contributions | |
�� | +0.024 |
dra | +0.024 |
� | +0.024 |
srf | +0.022 |
�士 | +0.022 |
Neg logit contributions | |
sim | -0.014 |
Buchanan | -0.014 |
Cain | -0.014 |
quit | -0.013 |
kitten | -0.013 |
Token | midst |
Token ID | 15925 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
�� | +0.026 |
� | +0.025 |
dra | +0.025 |
srf | +0.024 |
�士 | +0.024 |
Neg logit contributions | |
sim | -0.011 |
Buchanan | -0.011 |
Cain | -0.011 |
kitten | -0.011 |
shame | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | +5.65e-02 |
Pos logit contributions | |
sim | +0.010 |
Buchanan | +0.009 |
Cain | +0.009 |
quit | +0.009 |
kitten | +0.009 |
Neg logit contributions | |
�� | -0.036 |
� | -0.035 |
� | -0.034 |
� | -0.034 |
srf | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
�� | +0.059 |
dra | +0.058 |
� | +0.058 |
srf | +0.054 |
�士 | +0.054 |
Neg logit contributions | |
sim | -0.033 |
Buchanan | -0.032 |
Cain | -0.032 |
kitten | -0.032 |
quit | -0.031 |
Token | parad |
Token ID | 11497 |
Feature activation | +2.73e-03 |
Pos logit contributions | |
�� | +0.020 |
� | +0.020 |
dra | +0.020 |
srf | +0.019 |
�士 | +0.019 |
Neg logit contributions | |
sim | -0.013 |
Buchanan | -0.012 |
kitten | -0.012 |
Cain | -0.012 |
shame | -0.012 |
Token | igmatic |
Token ID | 38860 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
�� | +0.001 |
� | +0.001 |
dra | +0.001 |
srf | +0.001 |
�士 | +0.001 |
Neg logit contributions | |
sim | -0.003 |
quit | -0.003 |
Buchanan | -0.003 |
keley | -0.003 |
Cain | -0.003 |
Token | shift |
Token ID | 6482 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
�� | +0.238 |
� | +0.233 |
dra | +0.232 |
srf | +0.220 |
�士 | +0.218 |
Neg logit contributions | |
sim | -0.138 |
Buchanan | -0.135 |
Cain | -0.132 |
kitten | -0.132 |
shame | -0.131 |
Token | in |
Token ID | 287 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
sim | +0.017 |
Buchanan | +0.016 |
quit | +0.016 |
kitten | +0.016 |
Cain | +0.016 |
Neg logit contributions | |
�� | -0.041 |
dra | -0.041 |
� | -0.041 |
�士 | -0.039 |
srf | -0.038 |
Token | urban |
Token ID | 7876 |
Feature activation | +2.65e-02 |
Pos logit contributions | |
�� | +0.052 |
dra | +0.051 |
� | +0.051 |
srf | +0.048 |
�士 | +0.048 |
Neg logit contributions | |
sim | -0.032 |
Buchanan | -0.031 |
Cain | -0.031 |
shame | -0.031 |
kitten | -0.030 |
Token | governance |
Token ID | 18848 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
�� | +0.028 |
� | +0.027 |
dra | +0.027 |
srf | +0.026 |
�士 | +0.025 |
Neg logit contributions | |
sim | -0.016 |
Buchanan | -0.015 |
shame | -0.015 |
kitten | -0.015 |
Cain | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
�� | +0.012 |
� | +0.012 |
dra | +0.012 |
�士 | +0.011 |
srf | +0.011 |
Neg logit contributions | |
sim | -0.006 |
Buchanan | -0.005 |
quit | -0.005 |
Cain | -0.005 |
kitten | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
�� | +0.042 |
� | +0.041 |
dra | +0.040 |
srf | +0.038 |
�士 | +0.038 |
Neg logit contributions | |
sim | -0.025 |
Buchanan | -0.024 |
kitten | -0.024 |
Cain | -0.023 |
quit | -0.023 |
Token | Top |
Token ID | 5849 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
�� | +0.027 |
� | +0.027 |
dra | +0.026 |
�士 | +0.025 |
srf | +0.024 |
Neg logit contributions | |
sim | -0.015 |
Buchanan | -0.014 |
kitten | -0.014 |
Cain | -0.014 |
quit | -0.014 |
Token | End |
Token ID | 5268 |
Feature activation | +2.70e-02 |
Pos logit contributions | |
�� | +0.041 |
� | +0.040 |
dra | +0.039 |
srf | +0.037 |
EStreamFrame | +0.037 |
Neg logit contributions | |
sim | -0.028 |
quit | -0.027 |
Cain | -0.027 |
Buchanan | -0.027 |
keley | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +5.11e-03 |
Pos logit contributions | |
�� | +0.027 |
� | +0.026 |
dra | +0.025 |
srf | +0.024 |
�士 | +0.024 |
Neg logit contributions | |
sim | -0.017 |
quit | -0.017 |
Buchanan | -0.017 |
kitten | -0.017 |
Cain | -0.017 |
Token | Kimber |
Token ID | 36015 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
� | +0.005 |
�� | +0.005 |
dra | +0.005 |
srf | +0.004 |
�士 | +0.004 |
Neg logit contributions | |
sim | -0.003 |
Buchanan | -0.003 |
Cain | -0.003 |
quit | -0.003 |
kitten | -0.003 |
Token | ley |
Token ID | 1636 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
�� | +0.016 |
� | +0.016 |
dra | +0.016 |
�士 | +0.015 |
srf | +0.015 |
Neg logit contributions | |
sim | -0.012 |
keley | -0.012 |
quit | -0.012 |
Buchanan | -0.012 |
kitten | -0.012 |
Token | rock |
Token ID | 3881 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
�� | +0.225 |
� | +0.222 |
dra | +0.216 |
�士 | +0.205 |
srf | +0.205 |
Neg logit contributions | |
sim | -0.150 |
quit | -0.144 |
Buchanan | -0.144 |
kitten | -0.142 |
Cain | -0.142 |
Token | - |
Token ID | 12 |
Feature activation | +3.08e-02 |
Pos logit contributions | |
dra | +0.058 |
� | +0.058 |
�� | +0.056 |
�士 | +0.051 |
EStreamFrame | +0.051 |
Neg logit contributions | |
Buchanan | -0.042 |
Cain | -0.042 |
sim | -0.041 |
keley | -0.041 |
kitten | -0.041 |
Token | wall |
Token ID | 11930 |
Feature activation | -1.60e-03 |
Pos logit contributions | |
dra | +0.023 |
� | +0.022 |
�� | +0.022 |
EStreamFrame | +0.020 |
�士 | +0.019 |
Neg logit contributions | |
sim | -0.027 |
Buchanan | -0.027 |
Cain | -0.027 |
kitten | -0.026 |
keley | -0.026 |
Token | aby |
Token ID | 3930 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
quit | +0.001 |
sim | +0.001 |
keley | +0.001 |
Buchanan | +0.001 |
kitten | +0.001 |
Neg logit contributions | |
�� | -0.002 |
� | -0.002 |
srf | -0.002 |
� | -0.002 |
� | -0.002 |
Token | populations |
Token ID | 9684 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
�� | +0.054 |
� | +0.053 |
dra | +0.052 |
�士 | +0.050 |
srf | +0.049 |
Neg logit contributions | |
sim | -0.036 |
quit | -0.034 |
Buchanan | -0.034 |
Cain | -0.034 |
kitten | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
sim | +0.014 |
Buchanan | +0.013 |
quit | +0.013 |
Cain | +0.013 |
Kap | +0.012 |
Neg logit contributions | |
� | -0.060 |
� | -0.059 |
srf | -0.058 |
� | -0.058 |
�� | -0.057 |
Token | S |
Token ID | 50 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
quit | +0.033 |
sim | +0.031 |
keley | +0.031 |
Buchanan | +0.031 |
Cain | +0.031 |
Neg logit contributions | |
srf | -0.036 |
�� | -0.036 |
� | -0.035 |
� | -0.035 |
� | -0.034 |
Token | overe |
Token ID | 33518 |
Feature activation | -6.86e-02 |
Pos logit contributions | |
�� | +0.002 |
� | +0.002 |
dra | +0.002 |
srf | +0.002 |
EStreamFrame | +0.002 |
Neg logit contributions | |
quit | -0.001 |
sim | -0.001 |
keley | -0.001 |
Buchanan | -0.001 |
kitten | -0.001 |
Token | ign |
Token ID | 570 |
Feature activation | -5.62e-02 |
Pos logit contributions | |
sim | +0.039 |
quit | +0.039 |
Buchanan | +0.037 |
kitten | +0.037 |
keley | +0.037 |
Neg logit contributions | |
�� | -0.072 |
� | -0.072 |
dra | -0.070 |
srf | -0.067 |
�士 | -0.067 |
Token | Lux |
Token ID | 17145 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
sim | +0.040 |
Buchanan | +0.039 |
kitten | +0.038 |
quit | +0.038 |
Cain | +0.037 |
Neg logit contributions | |
� | -0.052 |
�� | -0.052 |
dra | -0.051 |
srf | -0.048 |
EStreamFrame | -0.047 |
Token | ury |
Token ID | 1601 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
sim | +0.006 |
quit | +0.005 |
Buchanan | +0.005 |
kitten | +0.005 |
Cain | +0.005 |
Neg logit contributions | |
� | -0.023 |
�� | -0.023 |
dra | -0.022 |
EStreamFrame | -0.021 |
srf | -0.021 |
Token | Travel |
Token ID | 13524 |
Feature activation | +4.21e-02 |
Pos logit contributions | |
sim | +0.265 |
Buchanan | +0.259 |
kitten | +0.256 |
quit | +0.254 |
Cain | +0.253 |
Neg logit contributions | |
� | -0.347 |
�� | -0.340 |
dra | -0.337 |
srf | -0.318 |
EStreamFrame | -0.311 |
Token | ( |
Token ID | 357 |
Feature activation | -1.21e-02 |
Pos logit contributions | |
� | +0.041 |
�� | +0.041 |
dra | +0.040 |
EStreamFrame | +0.038 |
srf | +0.038 |
Neg logit contributions | |
sim | -0.028 |
quit | -0.027 |
Buchanan | -0.027 |
Cain | -0.027 |
kitten | -0.026 |
Token | 08 |
Token ID | 2919 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
quit | +0.009 |
sim | +0.009 |
Buchanan | +0.009 |
kitten | +0.009 |
Cain | +0.009 |
Neg logit contributions | |
�� | -0.010 |
� | -0.010 |
dra | -0.010 |
� | -0.009 |
srf | -0.009 |
Token | 44 |
Token ID | 2598 |
Feature activation | -4.58e-02 |
Pos logit contributions | |
sim | +0.034 |
Buchanan | +0.033 |
Cain | +0.033 |
quit | +0.032 |
kitten | +0.032 |
Neg logit contributions | |
�� | -0.053 |
� | -0.053 |
dra | -0.052 |
srf | -0.050 |
EStreamFrame | -0.049 |
Token | 415 |
Token ID | 40643 |
Feature activation | -4.32e-02 |
Pos logit contributions | |
sim | +0.029 |
Buchanan | +0.028 |
Cain | +0.028 |
quit | +0.027 |
Kap | +0.027 |
Neg logit contributions | |
�� | -0.046 |
� | -0.045 |
dra | -0.045 |
srf | -0.044 |
� | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
sim | +0.029 |
Buchanan | +0.028 |
Cain | +0.028 |
quit | +0.028 |
shame | +0.027 |
Neg logit contributions | |
�� | -0.058 |
dra | -0.057 |
� | -0.056 |
srf | -0.053 |
�士 | -0.053 |
Token | than |
Token ID | 621 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
Buchanan | +0.029 |
sim | +0.029 |
Cain | +0.028 |
Kap | +0.027 |
kitten | +0.027 |
Neg logit contributions | |
�� | -0.049 |
dra | -0.048 |
� | -0.047 |
srf | -0.045 |
� | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
sim | +0.015 |
Buchanan | +0.014 |
Cain | +0.014 |
kitten | +0.014 |
shame | +0.014 |
Neg logit contributions | |
�� | -0.033 |
dra | -0.033 |
� | -0.033 |
srf | -0.031 |
�士 | -0.031 |
Token | bully |
Token ID | 27410 |
Feature activation | -7.82e-03 |
Pos logit contributions | |
sim | +0.027 |
Buchanan | +0.026 |
shame | +0.025 |
Cain | +0.025 |
kitten | +0.025 |
Neg logit contributions | |
�� | -0.043 |
dra | -0.042 |
� | -0.042 |
srf | -0.040 |
�士 | -0.039 |
Token | pul |
Token ID | 17472 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
sim | +0.005 |
Buchanan | +0.005 |
quit | +0.005 |
shame | +0.005 |
kitten | +0.005 |
Neg logit contributions | |
�� | -0.008 |
dra | -0.007 |
� | -0.007 |
�士 | -0.007 |
srf | -0.007 |
Token | pit |
Token ID | 15544 |
Feature activation | -3.36e-01 |
Pos logit contributions | |
�� | +0.051 |
dra | +0.049 |
� | +0.049 |
srf | +0.049 |
�士 | +0.048 |
Neg logit contributions | |
sim | -0.001 |
keley | -0.001 |
quit | -0.000 |
pit | -0.000 |
kitten | +0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
sim | +0.180 |
Buchanan | +0.171 |
Cain | +0.170 |
quit | +0.168 |
kitten | +0.167 |
Neg logit contributions | |
�� | -0.372 |
dra | -0.369 |
� | -0.366 |
srf | -0.353 |
EStreamFrame | -0.349 |
Token | PK |
Token ID | 29673 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
Buchanan | +0.012 |
Cain | +0.012 |
Kap | +0.012 |
sim | +0.011 |
quit | +0.011 |
Neg logit contributions | |
�� | -0.016 |
srf | -0.015 |
dra | -0.015 |
� | -0.015 |
� | -0.015 |
Token | claims |
Token ID | 3667 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
sim | +0.047 |
Buchanan | +0.046 |
Cain | +0.044 |
quit | +0.044 |
shame | +0.044 |
Neg logit contributions | |
�� | -0.079 |
dra | -0.078 |
� | -0.078 |
srf | -0.074 |
�士 | -0.072 |
Token | that |
Token ID | 326 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
sim | +0.009 |
Buchanan | +0.009 |
Cain | +0.009 |
quit | +0.009 |
kitten | +0.009 |
Neg logit contributions | |
�� | -0.016 |
dra | -0.016 |
� | -0.016 |
srf | -0.015 |
EStreamFrame | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | -6.22e-02 |
Pos logit contributions | |
Buchanan | +0.019 |
sim | +0.019 |
Cain | +0.019 |
shame | +0.018 |
kitten | +0.018 |
Neg logit contributions | |
�� | -0.030 |
dra | -0.030 |
� | -0.030 |
srf | -0.028 |
� | -0.028 |
Token | percent |
Token ID | 1411 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
sim | +0.007 |
quit | +0.006 |
Buchanan | +0.006 |
kitten | +0.006 |
Cain | +0.006 |
Neg logit contributions | |
�� | -0.012 |
dra | -0.012 |
� | -0.012 |
srf | -0.011 |
�士 | -0.011 |
Token | wheat |
Token ID | 17135 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
sim | +0.024 |
Cain | +0.023 |
kitten | +0.023 |
Buchanan | +0.023 |
keley | +0.023 |
Neg logit contributions | |
�� | -0.035 |
� | -0.035 |
dra | -0.035 |
�士 | -0.033 |
srf | -0.033 |
Token | IPA |
Token ID | 27966 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
sim | +0.022 |
Buchanan | +0.021 |
kitten | +0.021 |
Cain | +0.021 |
quit | +0.020 |
Neg logit contributions | |
�� | -0.035 |
� | -0.035 |
dra | -0.035 |
�士 | -0.034 |
srf | -0.032 |
Token | made |
Token ID | 925 |
Feature activation | +7.69e-03 |
Pos logit contributions | |
�� | +0.021 |
� | +0.021 |
dra | +0.021 |
�士 | +0.020 |
srf | +0.020 |
Neg logit contributions | |
sim | -0.011 |
quit | -0.010 |
Buchanan | -0.010 |
Cain | -0.010 |
kitten | -0.010 |
Token | with |
Token ID | 351 |
Feature activation | +2.31e-02 |
Pos logit contributions | |
�� | +0.009 |
dra | +0.009 |
� | +0.008 |
srf | +0.008 |
�士 | +0.008 |
Neg logit contributions | |
sim | -0.004 |
Buchanan | -0.004 |
quit | -0.004 |
Cain | -0.004 |
keley | -0.004 |
Token | Chin |
Token ID | 22604 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
�� | +0.023 |
dra | +0.022 |
� | +0.022 |
srf | +0.021 |
EStreamFrame | +0.021 |
Neg logit contributions | |
sim | -0.015 |
Buchanan | -0.015 |
Cain | -0.014 |
kitten | -0.014 |
quit | -0.014 |
Token | ook |
Token ID | 566 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
quit | +0.215 |
Buchanan | +0.211 |
keley | +0.211 |
Cain | +0.209 |
sim | +0.207 |
Neg logit contributions | |
�� | -0.262 |
� | -0.255 |
dra | -0.245 |
srf | -0.237 |
�士 | -0.233 |
Token | and |
Token ID | 290 |
Feature activation | -2.51e-03 |
Pos logit contributions | |
�� | +0.081 |
� | +0.078 |
dra | +0.077 |
srf | +0.074 |
EStreamFrame | +0.073 |
Neg logit contributions | |
sim | -0.058 |
Buchanan | -0.056 |
quit | -0.056 |
Cain | -0.056 |
kitten | -0.055 |
Token | Cit |
Token ID | 15792 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
sim | +0.002 |
Buchanan | +0.002 |
Cain | +0.002 |
kitten | +0.002 |
Kap | +0.001 |
Neg logit contributions | |
�� | -0.003 |
� | -0.002 |
dra | -0.002 |
srf | -0.002 |
EStreamFrame | -0.002 |
Token | ra |
Token ID | 430 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
sim | +0.046 |
Buchanan | +0.046 |
quit | +0.046 |
keley | +0.045 |
Cain | +0.044 |
Neg logit contributions | |
�� | -0.074 |
� | -0.071 |
srf | -0.067 |
EStreamFrame | -0.066 |
dra | -0.065 |
Token | hops |
Token ID | 29438 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
sim | +0.024 |
quit | +0.023 |
Buchanan | +0.023 |
Cain | +0.022 |
keley | +0.022 |
Neg logit contributions | |
�� | -0.029 |
dra | -0.028 |
� | -0.028 |
srf | -0.027 |
�士 | -0.026 |
Token | way |
Token ID | 835 |
Feature activation | -6.54e-02 |
Pos logit contributions | |
sim | +0.005 |
Buchanan | +0.004 |
kitten | +0.004 |
Cain | +0.004 |
shame | +0.004 |
Neg logit contributions | |
�� | -0.008 |
dra | -0.008 |
� | -0.008 |
srf | -0.008 |
�士 | -0.008 |
Token | too |
Token ID | 1165 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
sim | +0.035 |
quit | +0.034 |
Buchanan | +0.034 |
kitten | +0.034 |
Cain | +0.034 |
Neg logit contributions | |
�� | -0.070 |
� | -0.070 |
dra | -0.070 |
srf | -0.066 |
�士 | -0.065 |
Token | early |
Token ID | 1903 |
Feature activation | -6.19e-02 |
Pos logit contributions | |
sim | +0.048 |
Buchanan | +0.045 |
kitten | +0.045 |
Cain | +0.044 |
shame | +0.044 |
Neg logit contributions | |
�� | -0.073 |
dra | -0.072 |
� | -0.072 |
srf | -0.067 |
�士 | -0.066 |
Token | to |
Token ID | 284 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
sim | +0.032 |
quit | +0.032 |
Buchanan | +0.032 |
keley | +0.031 |
kitten | +0.031 |
Neg logit contributions | |
� | -0.066 |
dra | -0.066 |
�� | -0.066 |
srf | -0.061 |
EStreamFrame | -0.060 |
Token | handic |
Token ID | 29103 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
sim | +0.016 |
shame | +0.015 |
kitten | +0.015 |
Buchanan | +0.015 |
quit | +0.014 |
Neg logit contributions | |
�� | -0.027 |
dra | -0.026 |
� | -0.026 |
� | -0.025 |
srf | -0.025 |
Token | ap |
Token ID | 499 |
Feature activation | -2.78e-01 |
Pos logit contributions | |
�� | +0.087 |
� | +0.087 |
srf | +0.084 |
�士 | +0.084 |
� | +0.084 |
Neg logit contributions | |
quit | -0.011 |
sim | -0.010 |
Buchanan | -0.010 |
keley | -0.009 |
kitten | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
Buchanan | +0.164 |
sim | +0.162 |
Cain | +0.160 |
kitten | +0.157 |
quit | +0.156 |
Neg logit contributions | |
dra | -0.286 |
�� | -0.285 |
� | -0.282 |
srf | -0.268 |
�士 | -0.265 |
Token | 2017 |
Token ID | 2177 |
Feature activation | +3.23e-02 |
Pos logit contributions | |
sim | +0.026 |
Buchanan | +0.025 |
kitten | +0.025 |
Cain | +0.024 |
shame | +0.024 |
Neg logit contributions | |
�� | -0.059 |
� | -0.059 |
dra | -0.058 |
srf | -0.055 |
�士 | -0.054 |
Token | Oscars |
Token ID | 46485 |
Feature activation | -3.13e-02 |
Pos logit contributions | |
� | +0.036 |
�� | +0.035 |
dra | +0.035 |
srf | +0.033 |
�士 | +0.033 |
Neg logit contributions | |
sim | -0.017 |
Buchanan | -0.016 |
kitten | -0.016 |
Cain | -0.016 |
quit | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
sim | +0.017 |
Cain | +0.016 |
Buchanan | +0.016 |
quit | +0.016 |
kitten | +0.016 |
Neg logit contributions | |
�� | -0.034 |
dra | -0.034 |
� | -0.034 |
srf | -0.032 |
�士 | -0.032 |
Token | but |
Token ID | 475 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
sim | +0.029 |
Buchanan | +0.028 |
Cain | +0.028 |
kitten | +0.028 |
shame | +0.027 |
Neg logit contributions | |
�� | -0.048 |
dra | -0.047 |
� | -0.046 |
�士 | -0.045 |
srf | -0.044 |
Token | perks |
Token ID | 28429 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
�� | +0.035 |
dra | +0.034 |
� | +0.034 |
srf | +0.033 |
�士 | +0.033 |
Neg logit contributions | |
sim | -0.022 |
shame | -0.020 |
kitten | -0.020 |
Buchanan | -0.020 |
Cain | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +8.66e-03 |
Pos logit contributions | |
sim | +0.005 |
Buchanan | +0.005 |
kitten | +0.005 |
quit | +0.005 |
Cain | +0.004 |
Neg logit contributions | |
� | -0.010 |
�� | -0.010 |
dra | -0.010 |
srf | -0.009 |
�士 | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
�� | +0.010 |
srf | +0.009 |
� | +0.009 |
dra | +0.009 |
� | +0.009 |
Neg logit contributions | |
Cain | -0.005 |
Buchanan | -0.005 |
sim | -0.005 |
Kap | -0.004 |
quit | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
� | +0.027 |
� | +0.027 |
� | +0.027 |
srf | +0.027 |
�� | +0.026 |
Neg logit contributions | |
sim | -0.007 |
Buchanan | -0.007 |
quit | -0.007 |
Cain | -0.006 |
Kap | -0.006 |
Token | Integ |
Token ID | 34500 |
Feature activation | +8.59e-02 |
Pos logit contributions | |
srf | +0.016 |
� | +0.016 |
� | +0.016 |
� | +0.016 |
�� | +0.015 |
Neg logit contributions | |
quit | -0.013 |
sim | -0.012 |
Cain | -0.012 |
keley | -0.012 |
Buchanan | -0.012 |
Token | rity |
Token ID | 10138 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
�� | +0.094 |
� | +0.093 |
dra | +0.093 |
srf | +0.087 |
�士 | +0.087 |
Neg logit contributions | |
sim | -0.044 |
Buchanan | -0.043 |
quit | -0.043 |
keley | -0.042 |
Cain | -0.041 |
Token | of |
Token ID | 286 |
Feature activation | +5.28e-03 |
Pos logit contributions | |
sim | +0.150 |
Buchanan | +0.141 |
Cain | +0.140 |
quit | +0.140 |
kitten | +0.139 |
Neg logit contributions | |
�� | -0.302 |
� | -0.299 |
dra | -0.297 |
�士 | -0.285 |
srf | -0.282 |
Token | a |
Token ID | 257 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
dra | +0.005 |
�� | +0.005 |
� | +0.005 |
�士 | +0.005 |
srf | +0.005 |
Neg logit contributions | |
sim | -0.003 |
Cain | -0.003 |
Buchanan | -0.003 |
shame | -0.003 |
kitten | -0.003 |
Token | tournament |
Token ID | 7756 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
�� | +0.009 |
dra | +0.009 |
� | +0.009 |
�士 | +0.009 |
� | +0.009 |
Neg logit contributions | |
sim | -0.005 |
shame | -0.005 |
Cain | -0.005 |
spat | -0.005 |
kitten | -0.005 |
Token | should |
Token ID | 815 |
Feature activation | +8.00e-03 |
Pos logit contributions | |
�� | +0.019 |
dra | +0.018 |
� | +0.018 |
�士 | +0.018 |
srf | +0.018 |
Neg logit contributions | |
sim | -0.009 |
Buchanan | -0.009 |
Cain | -0.009 |
kitten | -0.008 |
shame | -0.008 |
Token | always |
Token ID | 1464 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
�� | +0.009 |
� | +0.009 |
dra | +0.008 |
�士 | +0.008 |
� | +0.008 |
Neg logit contributions | |
sim | -0.005 |
shame | -0.004 |
kitten | -0.004 |
Cain | -0.004 |
quit | -0.004 |
Token | blame |
Token ID | 8138 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
sim | +0.004 |
Buchanan | +0.003 |
Cain | +0.003 |
kitten | +0.003 |
shame | +0.003 |
Neg logit contributions | |
dra | -0.006 |
�� | -0.006 |
� | -0.006 |
srf | -0.006 |
�士 | -0.005 |
Token | towards |
Token ID | 3371 |
Feature activation | +1.87e-04 |
Pos logit contributions | |
�� | +0.013 |
� | +0.013 |
dra | +0.013 |
srf | +0.012 |
�士 | +0.012 |
Neg logit contributions | |
sim | -0.006 |
Buchanan | -0.006 |
quit | -0.006 |
kitten | -0.006 |
Cain | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
�� | +0.000 |
� | +0.000 |
dra | +0.000 |
srf | +0.000 |
�士 | +0.000 |
Neg logit contributions | |
sim | -0.000 |
Buchanan | -0.000 |
Cain | -0.000 |
kitten | -0.000 |
shame | -0.000 |
Token | dis |
Token ID | 595 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
sim | +0.012 |
Buchanan | +0.012 |
kitten | +0.012 |
shame | +0.012 |
Cain | +0.012 |
Neg logit contributions | |
�� | -0.020 |
� | -0.020 |
dra | -0.020 |
srf | -0.019 |
�士 | -0.019 |
Token | ench |
Token ID | 24421 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
sim | +0.015 |
quit | +0.015 |
Buchanan | +0.015 |
kitten | +0.014 |
keley | +0.014 |
Neg logit contributions | |
�� | -0.016 |
� | -0.016 |
dra | -0.015 |
srf | -0.015 |
�士 | -0.015 |
Token | anted |
Token ID | 4126 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
sim | +0.013 |
quit | +0.013 |
Buchanan | +0.013 |
Cain | +0.012 |
shame | +0.012 |
Neg logit contributions | |
�� | -0.026 |
� | -0.026 |
srf | -0.025 |
dra | -0.025 |
�士 | -0.025 |
Token | , |
Token ID | 11 |
Feature activation | -3.07e-03 |
Pos logit contributions | |
sim | +0.160 |
Buchanan | +0.154 |
kitten | +0.154 |
Cain | +0.152 |
quit | +0.150 |
Neg logit contributions | |
�� | -0.291 |
� | -0.288 |
dra | -0.288 |
�士 | -0.273 |
srf | -0.272 |
Token | j |
Token ID | 474 |
Feature activation | +7.41e-03 |
Pos logit contributions | |
sim | +0.002 |
Buchanan | +0.002 |
shame | +0.002 |
Cain | +0.002 |
kitten | +0.002 |
Neg logit contributions | |
�� | -0.003 |
dra | -0.003 |
� | -0.003 |
�士 | -0.003 |
srf | -0.003 |
Token | aded |
Token ID | 5286 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
�� | +0.007 |
� | +0.006 |
dra | +0.006 |
srf | +0.006 |
�士 | +0.006 |
Neg logit contributions | |
sim | -0.006 |
quit | -0.006 |
Buchanan | -0.006 |
keley | -0.005 |
kitten | -0.005 |
Token | young |
Token ID | 1862 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
sim | +0.040 |
Buchanan | +0.038 |
kitten | +0.038 |
Cain | +0.038 |
quit | +0.037 |
Neg logit contributions | |
�� | -0.075 |
� | -0.075 |
dra | -0.074 |
�士 | -0.070 |
srf | -0.070 |
Token | people |
Token ID | 661 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
sim | +0.033 |
Buchanan | +0.031 |
Cain | +0.031 |
kitten | +0.031 |
quit | +0.031 |
Neg logit contributions | |
�� | -0.060 |
� | -0.059 |
dra | -0.059 |
�士 | -0.056 |
srf | -0.055 |
Token | trained |
Token ID | 8776 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
�� | +0.029 |
dra | +0.029 |
� | +0.029 |
srf | +0.027 |
�士 | +0.027 |
Neg logit contributions | |
sim | -0.017 |
kitten | -0.016 |
Buchanan | -0.016 |
keley | -0.016 |
Cain | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
�� | +0.042 |
� | +0.041 |
dra | +0.041 |
�士 | +0.039 |
srf | +0.039 |
Neg logit contributions | |
sim | -0.017 |
Buchanan | -0.016 |
kitten | -0.016 |
keley | -0.016 |
quit | -0.016 |
Token | drive |
Token ID | 3708 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
�� | +0.029 |
� | +0.029 |
dra | +0.028 |
� | +0.027 |
�士 | +0.027 |
Neg logit contributions | |
sim | -0.020 |
kitten | -0.019 |
Buchanan | -0.019 |
shame | -0.019 |
quit | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
�� | +0.037 |
� | +0.037 |
dra | +0.036 |
�士 | +0.034 |
EStreamFrame | +0.034 |
Neg logit contributions | |
sim | -0.019 |
Buchanan | -0.017 |
kitten | -0.017 |
quit | -0.017 |
shame | -0.017 |
Token | handic |
Token ID | 29103 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
� | +0.044 |
�� | +0.043 |
dra | +0.043 |
�士 | +0.040 |
� | +0.039 |
Neg logit contributions | |
sim | -0.024 |
kitten | -0.023 |
Buchanan | -0.023 |
quit | -0.022 |
shame | -0.022 |
Token | apped |
Token ID | 6320 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
�� | +0.109 |
� | +0.109 |
dra | +0.107 |
srf | +0.104 |
�士 | +0.103 |
Neg logit contributions | |
sim | -0.024 |
kitten | -0.021 |
Buchanan | -0.021 |
quit | -0.021 |
keley | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
sim | +0.151 |
kitten | +0.143 |
Buchanan | +0.135 |
shame | +0.131 |
Kap | +0.130 |
Neg logit contributions | |
� | -0.310 |
�� | -0.306 |
dra | -0.302 |
�士 | -0.287 |
� | -0.287 |
Token | young |
Token ID | 1862 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
� | +0.041 |
�� | +0.041 |
dra | +0.041 |
srf | +0.038 |
�士 | +0.038 |
Neg logit contributions | |
sim | -0.027 |
kitten | -0.026 |
Buchanan | -0.025 |
shame | -0.024 |
spat | -0.024 |
Token | human |
Token ID | 1692 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
sim | +0.022 |
kitten | +0.021 |
quit | +0.019 |
Buchanan | +0.019 |
Cain | +0.019 |
Neg logit contributions | |
� | -0.044 |
�� | -0.043 |
dra | -0.042 |
�士 | -0.040 |
srf | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
� | +0.030 |
�� | +0.030 |
dra | +0.029 |
�士 | +0.028 |
srf | +0.028 |
Neg logit contributions | |
sim | -0.016 |
kitten | -0.015 |
Buchanan | -0.014 |
Cain | -0.014 |
shame | -0.014 |
Token | motor |
Token ID | 5584 |
Feature activation | +7.68e-04 |
Pos logit contributions | |
� | +0.043 |
�� | +0.042 |
dra | +0.042 |
�士 | +0.039 |
� | +0.039 |
Neg logit contributions | |
sim | -0.024 |
kitten | -0.023 |
Buchanan | -0.022 |
Cain | -0.021 |
Kap | -0.021 |
Token | 37 |
Token ID | 2718 |
Feature activation | -8.82e-03 |
Pos logit contributions | |
sim | +0.016 |
kitten | +0.016 |
Cain | +0.016 |
Buchanan | +0.016 |
keley | +0.016 |
Neg logit contributions | |
�� | -0.012 |
dra | -0.012 |
� | -0.012 |
�士 | -0.010 |
EStreamFrame | -0.010 |
Token | ] |
Token ID | 60 |
Feature activation | +4.25e-03 |
Pos logit contributions | |
sim | +0.003 |
Buchanan | +0.003 |
quit | +0.003 |
Cain | +0.003 |
shame | +0.002 |
Neg logit contributions | |
� | -0.012 |
�� | -0.012 |
� | -0.012 |
� | -0.012 |
srf | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -8.59e-03 |
Pos logit contributions | |
dra | +0.004 |
� | +0.004 |
�� | +0.004 |
�士 | +0.004 |
EStreamFrame | +0.004 |
Neg logit contributions | |
sim | -0.003 |
quit | -0.003 |
kitten | -0.003 |
keley | -0.003 |
Cain | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
sim | +0.003 |
Buchanan | +0.003 |
quit | +0.003 |
Cain | +0.003 |
Kap | +0.003 |
Neg logit contributions | |
� | -0.012 |
� | -0.012 |
srf | -0.012 |
� | -0.012 |
�� | -0.012 |
Token | Hill |
Token ID | 36369 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
quit | +0.011 |
Buchanan | +0.011 |
keley | +0.011 |
sim | +0.011 |
Cain | +0.010 |
Neg logit contributions | |
srf | -0.013 |
� | -0.013 |
� | -0.013 |
�� | -0.012 |
� | -0.012 |
Token | quit |
Token ID | 47391 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
�� | +0.052 |
� | +0.052 |
srf | +0.051 |
dra | +0.051 |
� | +0.051 |
Neg logit contributions | |
quit | -0.000 |
Buchanan | +0.003 |
sim | +0.003 |
keley | +0.003 |
kitten | +0.004 |
Token | was |
Token ID | 373 |
Feature activation | -5.90e-03 |
Pos logit contributions | |
sim | +0.156 |
Buchanan | +0.153 |
quit | +0.149 |
Cain | +0.149 |
kitten | +0.145 |
Neg logit contributions | |
�� | -0.292 |
� | -0.291 |
dra | -0.287 |
srf | -0.274 |
� | -0.270 |
Token | challenged |
Token ID | 12827 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
sim | +0.004 |
Buchanan | +0.004 |
Cain | +0.003 |
quit | +0.003 |
kitten | +0.003 |
Neg logit contributions | |
�� | -0.006 |
dra | -0.006 |
� | -0.006 |
srf | -0.006 |
EStreamFrame | -0.006 |
Token | at |
Token ID | 379 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
sim | +0.008 |
Buchanan | +0.008 |
Cain | +0.007 |
quit | +0.007 |
kitten | +0.007 |
Neg logit contributions | |
�� | -0.020 |
dra | -0.020 |
� | -0.020 |
srf | -0.019 |
�士 | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
dra | +0.025 |
� | +0.025 |
�� | +0.025 |
srf | +0.024 |
�士 | +0.023 |
Neg logit contributions | |
sim | -0.016 |
Buchanan | -0.016 |
Cain | -0.016 |
quit | -0.015 |
kitten | -0.015 |
Token | 1932 |
Token ID | 32471 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
� | +0.011 |
�� | +0.011 |
dra | +0.011 |
srf | +0.010 |
� | +0.010 |
Neg logit contributions | |
Buchanan | -0.006 |
sim | -0.006 |
Cain | -0.006 |
kitten | -0.006 |
keley | -0.005 |
Token | Rue |
Token ID | 45363 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
sim | +0.014 |
Buchanan | +0.014 |
quit | +0.014 |
Cain | +0.014 |
shame | +0.013 |
Neg logit contributions | |
�� | -0.019 |
� | -0.018 |
� | -0.018 |
�士 | -0.018 |
srf | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -1.60e-02 |
Pos logit contributions | |
�� | +0.046 |
� | +0.046 |
dra | +0.045 |
srf | +0.043 |
� | +0.043 |
Neg logit contributions | |
sim | -0.026 |
Buchanan | -0.025 |
Cain | -0.025 |
quit | -0.024 |
shame | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
Buchanan | +0.009 |
sim | +0.009 |
Cain | +0.008 |
Kap | +0.008 |
shame | +0.008 |
Neg logit contributions | |
�� | -0.017 |
� | -0.017 |
dra | -0.017 |
EStreamFrame | -0.016 |
srf | -0.016 |
Token | longtime |
Token ID | 15076 |
Feature activation | -7.60e-02 |
Pos logit contributions | |
sim | +0.009 |
Buchanan | +0.009 |
kitten | +0.009 |
Kap | +0.009 |
quit | +0.009 |
Neg logit contributions | |
�� | -0.015 |
� | -0.015 |
dra | -0.014 |
srf | -0.014 |
�士 | -0.014 |
Token | Guatem |
Token ID | 28171 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
Buchanan | +0.048 |
sim | +0.048 |
kitten | +0.046 |
Cain | +0.046 |
Kap | +0.045 |
Neg logit contributions | |
� | -0.078 |
�� | -0.078 |
dra | -0.075 |
srf | -0.073 |
� | -0.072 |
Token | alan |
Token ID | 25786 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
quit | +0.018 |
sim | +0.018 |
Buchanan | +0.017 |
Cain | +0.017 |
keley | +0.017 |
Neg logit contributions | |
�� | -0.051 |
� | -0.049 |
dra | -0.048 |
srf | -0.047 |
�士 | -0.047 |
Token | human |
Token ID | 1692 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
sim | +0.166 |
Buchanan | +0.163 |
kitten | +0.157 |
quit | +0.156 |
Cain | +0.155 |
Neg logit contributions | |
� | -0.277 |
�� | -0.276 |
dra | -0.272 |
srf | -0.265 |
�士 | -0.258 |
Token | rights |
Token ID | 2489 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
sim | +0.021 |
quit | +0.021 |
Buchanan | +0.021 |
keley | +0.021 |
Cain | +0.020 |
Neg logit contributions | |
� | -0.021 |
dra | -0.021 |
�� | -0.021 |
�士 | -0.018 |
srf | -0.018 |
Token | activist |
Token ID | 11276 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
sim | +0.007 |
Buchanan | +0.007 |
shame | +0.006 |
kitten | +0.006 |
spat | +0.006 |
Neg logit contributions | |
� | -0.010 |
�� | -0.010 |
dra | -0.010 |
srf | -0.010 |
EStreamFrame | -0.010 |
Token | who |
Token ID | 508 |
Feature activation | -7.06e-02 |
Pos logit contributions | |
sim | +0.006 |
Buchanan | +0.006 |
quit | +0.006 |
kitten | +0.006 |
keley | +0.006 |
Neg logit contributions | |
dra | -0.011 |
� | -0.011 |
�� | -0.011 |
srf | -0.010 |
�士 | -0.010 |
Token | has |
Token ID | 468 |
Feature activation | -6.98e-02 |
Pos logit contributions | |
sim | +0.042 |
Buchanan | +0.039 |
quit | +0.039 |
shame | +0.038 |
kitten | +0.038 |
Neg logit contributions | |
�� | -0.077 |
� | -0.076 |
dra | -0.074 |
srf | -0.073 |
� | -0.071 |
Token | eed |
Token ID | 2308 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
keley | +0.009 |
sim | +0.009 |
quit | +0.009 |
Buchanan | +0.008 |
shame | +0.008 |
Neg logit contributions | |
�� | -0.011 |
�士 | -0.010 |
� | -0.010 |
� | -0.010 |
srf | -0.010 |
Token | argues |
Token ID | 11673 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
sim | +0.016 |
Buchanan | +0.016 |
Cain | +0.015 |
quit | +0.015 |
kitten | +0.015 |
Neg logit contributions | |
�� | -0.028 |
dra | -0.028 |
� | -0.027 |
srf | -0.026 |
�士 | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +1.93e-03 |
Pos logit contributions | |
dra | +0.016 |
�� | +0.016 |
� | +0.016 |
srf | +0.015 |
�士 | +0.015 |
Neg logit contributions | |
sim | -0.009 |
Buchanan | -0.009 |
quit | -0.009 |
Cain | -0.009 |
kitten | -0.009 |
Token | persu |
Token ID | 10722 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
�� | +0.002 |
dra | +0.002 |
� | +0.002 |
�士 | +0.002 |
srf | +0.002 |
Neg logit contributions | |
sim | -0.001 |
Buchanan | -0.001 |
Cain | -0.001 |
shame | -0.001 |
kitten | -0.001 |
Token | as |
Token ID | 292 |
Feature activation | -3.95e-02 |
Pos logit contributions | |
�� | +0.086 |
� | +0.081 |
srf | +0.080 |
� | +0.080 |
� | +0.080 |
Neg logit contributions | |
sim | -0.038 |
quit | -0.035 |
Buchanan | -0.034 |
keley | -0.033 |
shame | -0.033 |
Token | ively |
Token ID | 2280 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
sim | +0.016 |
quit | +0.015 |
Cain | +0.015 |
Buchanan | +0.015 |
shame | +0.014 |
Neg logit contributions | |
�� | -0.051 |
�士 | -0.049 |
srf | -0.049 |
� | -0.049 |
dra | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
quit | +0.165 |
sim | +0.164 |
keley | +0.163 |
Buchanan | +0.162 |
kitten | +0.161 |
Neg logit contributions | |
� | -0.255 |
�� | -0.255 |
dra | -0.253 |
EStreamFrame | -0.231 |
�士 | -0.229 |
Token | that |
Token ID | 326 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
dra | +0.011 |
�� | +0.011 |
� | +0.011 |
srf | +0.010 |
�士 | +0.010 |
Neg logit contributions | |
sim | -0.006 |
Buchanan | -0.006 |
quit | -0.006 |
Cain | -0.006 |
kitten | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
Buchanan | +0.012 |
sim | +0.012 |
Cain | +0.011 |
shame | +0.011 |
quit | +0.011 |
Neg logit contributions | |
dra | -0.019 |
�� | -0.019 |
� | -0.019 |
srf | -0.018 |
�士 | -0.018 |
Token | vibrant |
Token ID | 21266 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
sim | +0.004 |
Buchanan | +0.004 |
kitten | +0.004 |
quit | +0.004 |
shame | +0.004 |
Neg logit contributions | |
�� | -0.006 |
dra | -0.006 |
� | -0.006 |
srf | -0.005 |
�士 | -0.005 |
Token | left |
Token ID | 1364 |
Feature activation | +2.66e-02 |
Pos logit contributions | |
sim | +0.011 |
Buchanan | +0.011 |
kitten | +0.010 |
Cain | +0.010 |
shame | +0.010 |
Neg logit contributions | |
�� | -0.020 |
dra | -0.020 |
� | -0.019 |
srf | -0.019 |
�士 | -0.018 |
Token | are |
Token ID | 389 |
Feature activation | +2.36e-02 |
Pos logit contributions | |
�� | +0.026 |
� | +0.025 |
dra | +0.024 |
� | +0.023 |
srf | +0.023 |
Neg logit contributions | |
sim | -0.014 |
Buchanan | -0.013 |
kitten | -0.013 |
shame | -0.013 |
quit | -0.013 |
Token | attacked |
Token ID | 7384 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
�� | +0.026 |
� | +0.025 |
dra | +0.024 |
srf | +0.023 |
�士 | +0.023 |
Neg logit contributions | |
sim | -0.014 |
Cain | -0.013 |
shame | -0.013 |
Buchanan | -0.013 |
kitten | -0.013 |
Token | by |
Token ID | 416 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
�� | +0.024 |
dra | +0.024 |
� | +0.024 |
srf | +0.022 |
�士 | +0.022 |
Neg logit contributions | |
sim | -0.010 |
Buchanan | -0.010 |
quit | -0.010 |
Cain | -0.010 |
kitten | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +2.38e-02 |
Pos logit contributions | |
�� | +0.037 |
� | +0.037 |
dra | +0.036 |
EStreamFrame | +0.035 |
srf | +0.035 |
Neg logit contributions | |
sim | -0.024 |
Cain | -0.023 |
Buchanan | -0.023 |
kitten | -0.023 |
quit | -0.023 |
Token | Wat |
Token ID | 12242 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
�� | +0.023 |
� | +0.023 |
dra | +0.022 |
srf | +0.021 |
EStreamFrame | +0.021 |
Neg logit contributions | |
sim | -0.016 |
Cain | -0.016 |
Buchanan | -0.015 |
kitten | -0.015 |
quit | -0.015 |
Token | cher |
Token ID | 2044 |
Feature activation | -2.62e-01 |
Pos logit contributions | |
�� | +0.024 |
� | +0.023 |
dra | +0.023 |
srf | +0.022 |
�士 | +0.022 |
Neg logit contributions | |
sim | -0.008 |
Cain | -0.008 |
quit | -0.007 |
Buchanan | -0.007 |
keley | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +4.55e-02 |
Pos logit contributions | |
Cain | +0.144 |
sim | +0.143 |
Buchanan | +0.138 |
quit | +0.138 |
kitten | +0.134 |
Neg logit contributions | |
�� | -0.283 |
� | -0.278 |
dra | -0.269 |
srf | -0.264 |
EStreamFrame | -0.262 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
� | +0.045 |
�� | +0.045 |
dra | +0.044 |
srf | +0.042 |
EStreamFrame | +0.041 |
Neg logit contributions | |
sim | -0.029 |
Buchanan | -0.028 |
Cain | -0.028 |
shame | -0.027 |
kitten | -0.027 |
Token | Water |
Token ID | 5638 |
Feature activation | +9.11e-02 |
Pos logit contributions | |
� | +0.024 |
�� | +0.024 |
dra | +0.023 |
srf | +0.022 |
�士 | +0.022 |
Neg logit contributions | |
sim | -0.016 |
Cain | -0.015 |
Buchanan | -0.015 |
kitten | -0.015 |
shame | -0.015 |
Token | before |
Token ID | 878 |
Feature activation | -3.98e-03 |
Pos logit contributions | |
�� | +0.096 |
� | +0.096 |
dra | +0.093 |
srf | +0.091 |
�士 | +0.090 |
Neg logit contributions | |
sim | -0.051 |
Cain | -0.049 |
Buchanan | -0.049 |
quit | -0.049 |
kitten | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
sim | +0.003 |
Cain | +0.003 |
Buchanan | +0.003 |
shame | +0.002 |
Kap | +0.002 |
Neg logit contributions | |
�� | -0.004 |
� | -0.004 |
dra | -0.004 |
� | -0.004 |
EStreamFrame | -0.004 |
Token | ins |
Token ID | 1040 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
quit | +0.046 |
sim | +0.046 |
keley | +0.045 |
Cain | +0.044 |
Buchanan | +0.044 |
Neg logit contributions | |
�� | -0.051 |
� | -0.049 |
dra | -0.048 |
srf | -0.046 |
�士 | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
�� | +0.044 |
� | +0.043 |
dra | +0.043 |
�士 | +0.041 |
srf | +0.041 |
Neg logit contributions | |
sim | -0.020 |
Buchanan | -0.019 |
quit | -0.018 |
Cain | -0.018 |
kitten | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
dra | +0.003 |
� | +0.003 |
�� | +0.003 |
srf | +0.003 |
�士 | +0.003 |
Neg logit contributions | |
sim | -0.002 |
quit | -0.002 |
Buchanan | -0.002 |
keley | -0.002 |
kitten | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
sim | +0.008 |
Buchanan | +0.007 |
quit | +0.007 |
Cain | +0.007 |
Kap | +0.007 |
Neg logit contributions | |
� | -0.031 |
� | -0.030 |
srf | -0.030 |
� | -0.030 |
�� | -0.029 |
Token | D |
Token ID | 35 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
quit | +0.016 |
sim | +0.016 |
Buchanan | +0.015 |
Cain | +0.015 |
keley | +0.015 |
Neg logit contributions | |
�� | -0.017 |
srf | -0.016 |
� | -0.016 |
� | -0.016 |
� | -0.016 |
Token | uke |
Token ID | 4649 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
sim | +0.019 |
Buchanan | +0.018 |
quit | +0.018 |
Cain | +0.018 |
keley | +0.018 |
Neg logit contributions | |
�� | -0.020 |
� | -0.020 |
dra | -0.020 |
srf | -0.019 |
�士 | -0.019 |
Token | Energy |
Token ID | 6682 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
Buchanan | +0.178 |
sim | +0.178 |
quit | +0.175 |
Cain | +0.174 |
keley | +0.170 |
Neg logit contributions | |
�� | -0.242 |
� | -0.237 |
dra | -0.235 |
srf | -0.226 |
�士 | -0.220 |
Token | � |
Token ID | 447 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
sim | +0.011 |
Buchanan | +0.010 |
quit | +0.010 |
Cain | +0.010 |
kitten | +0.010 |
Neg logit contributions | |
�� | -0.020 |
� | -0.019 |
dra | -0.019 |
srf | -0.018 |
�士 | -0.018 |
Token | � |
Token ID | 247 |
Feature activation | -2.70e-02 |
Pos logit contributions | |
Buchanan | +0.023 |
keley | +0.023 |
sim | +0.022 |
quit | +0.022 |
kitten | +0.022 |
Neg logit contributions | |
dra | -0.050 |
� | -0.050 |
� | -0.050 |
� | -0.049 |
�� | -0.049 |
Token | s |
Token ID | 82 |
Feature activation | -4.53e-02 |
Pos logit contributions | |
sim | +0.013 |
quit | +0.013 |
Buchanan | +0.013 |
Cain | +0.013 |
kitten | +0.012 |
Neg logit contributions | |
�� | -0.031 |
� | -0.030 |
dra | -0.030 |
srf | -0.028 |
�士 | -0.028 |
Token | considered |
Token ID | 3177 |
Feature activation | -9.81e-04 |
Pos logit contributions | |
sim | +0.029 |
Buchanan | +0.029 |
Cain | +0.028 |
kitten | +0.028 |
quit | +0.028 |
Neg logit contributions | |
�� | -0.045 |
� | -0.045 |
dra | -0.044 |
srf | -0.042 |
�士 | -0.042 |
Token | summer |
Token ID | 3931 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
Buchanan | +0.005 |
sim | +0.005 |
Cain | +0.005 |
quit | +0.005 |
kitten | +0.005 |
Neg logit contributions | |
�� | -0.008 |
� | -0.007 |
dra | -0.007 |
srf | -0.007 |
EStreamFrame | -0.007 |
Token | home |
Token ID | 1363 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
sim | +0.013 |
Buchanan | +0.013 |
quit | +0.013 |
kitten | +0.013 |
Kap | +0.013 |
Neg logit contributions | |
�� | -0.024 |
� | -0.024 |
dra | -0.023 |
srf | -0.022 |
EStreamFrame | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
�� | +0.001 |
� | +0.001 |
dra | +0.001 |
srf | +0.001 |
EStreamFrame | +0.001 |
Neg logit contributions | |
sim | -0.001 |
Buchanan | -0.001 |
quit | -0.001 |
Cain | -0.001 |
kitten | -0.001 |
Token | Gray |
Token ID | 12723 |
Feature activation | -6.50e-02 |
Pos logit contributions | |
sim | +0.012 |
Buchanan | +0.012 |
Cain | +0.012 |
Kap | +0.012 |
kitten | +0.011 |
Neg logit contributions | |
�� | -0.020 |
� | -0.020 |
dra | -0.020 |
srf | -0.019 |
EStreamFrame | -0.018 |
Token | cl |
Token ID | 565 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
Buchanan | +0.042 |
sim | +0.042 |
Cain | +0.042 |
keley | +0.041 |
quit | +0.041 |
Neg logit contributions | |
�� | -0.063 |
� | -0.061 |
dra | -0.060 |
srf | -0.058 |
EStreamFrame | -0.057 |
Token | iff |
Token ID | 733 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
sim | +0.016 |
keley | +0.016 |
quit | +0.015 |
Buchanan | +0.015 |
kitten | +0.015 |
Neg logit contributions | |
�� | -0.059 |
� | -0.058 |
dra | -0.057 |
srf | -0.056 |
� | -0.055 |
Token | Estate |
Token ID | 23015 |
Feature activation | +4.64e-03 |
Pos logit contributions | |
sim | +0.172 |
Buchanan | +0.172 |
Cain | +0.170 |
quit | +0.167 |
kitten | +0.165 |
Neg logit contributions | |
�� | -0.243 |
� | -0.241 |
dra | -0.238 |
srf | -0.226 |
EStreamFrame | -0.223 |
Token | , |
Token ID | 11 |
Feature activation | -8.83e-03 |
Pos logit contributions | |
�� | +0.005 |
� | +0.005 |
dra | +0.005 |
srf | +0.005 |
EStreamFrame | +0.005 |
Neg logit contributions | |
sim | -0.003 |
Buchanan | -0.002 |
Cain | -0.002 |
quit | -0.002 |
kitten | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -8.96e-03 |
Pos logit contributions | |
sim | +0.005 |
Buchanan | +0.005 |
Cain | +0.005 |
kitten | +0.005 |
Kap | +0.005 |
Neg logit contributions | |
�� | -0.009 |
� | -0.009 |
dra | -0.009 |
srf | -0.009 |
EStreamFrame | -0.008 |
Token | summer |
Token ID | 3931 |
Feature activation | -6.83e-03 |
Pos logit contributions | |
sim | +0.006 |
Buchanan | +0.006 |
Cain | +0.005 |
kitten | +0.005 |
Kap | +0.005 |
Neg logit contributions | |
�� | -0.009 |
� | -0.009 |
dra | -0.009 |
srf | -0.008 |
EStreamFrame | -0.008 |
Token | home |
Token ID | 1363 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
sim | +0.004 |
Buchanan | +0.004 |
kitten | +0.004 |
quit | +0.003 |
Cain | +0.003 |
Neg logit contributions | |
�� | -0.007 |
� | -0.007 |
dra | -0.007 |
srf | -0.007 |
EStreamFrame | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | -3.53e-02 |
Pos logit contributions | |
� | +0.010 |
dra | +0.010 |
�� | +0.010 |
srf | +0.010 |
EStreamFrame | +0.010 |
Neg logit contributions | |
sim | -0.004 |
Buchanan | -0.004 |
kitten | -0.004 |
quit | -0.004 |
Cain | -0.004 |
Token | National |
Token ID | 2351 |
Feature activation | +4.35e-03 |
Pos logit contributions | |
Buchanan | +0.023 |
sim | +0.023 |
Cain | +0.022 |
keley | +0.022 |
kitten | +0.022 |
Neg logit contributions | |
� | -0.034 |
�� | -0.034 |
dra | -0.034 |
srf | -0.032 |
�士 | -0.032 |
Token | Chairman |
Token ID | 12787 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
� | +0.004 |
�� | +0.004 |
dra | +0.004 |
srf | +0.003 |
EStreamFrame | +0.003 |
Neg logit contributions | |
Buchanan | -0.003 |
sim | -0.003 |
quit | -0.003 |
shame | -0.003 |
keley | -0.003 |
Token | Morris |
Token ID | 14433 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
�� | +0.010 |
� | +0.010 |
dra | +0.010 |
srf | +0.010 |
�士 | +0.010 |
Neg logit contributions | |
Buchanan | -0.007 |
sim | -0.006 |
Cain | -0.006 |
quit | -0.006 |
Kap | -0.006 |
Token | Hill |
Token ID | 3327 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
sim | +0.043 |
Buchanan | +0.042 |
quit | +0.042 |
Cain | +0.041 |
keley | +0.041 |
Neg logit contributions | |
dra | -0.058 |
�� | -0.058 |
� | -0.058 |
srf | -0.053 |
�士 | -0.053 |
Token | quit |
Token ID | 47391 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
quit | +0.000 |
sim | +0.000 |
Buchanan | -0.000 |
keley | -0.000 |
Cain | -0.000 |
Neg logit contributions | |
�� | -0.021 |
dra | -0.021 |
� | -0.021 |
srf | -0.020 |
�士 | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
sim | +0.132 |
Buchanan | +0.132 |
Cain | +0.125 |
quit | +0.125 |
kitten | +0.123 |
Neg logit contributions | |
� | -0.283 |
�� | -0.283 |
dra | -0.283 |
srf | -0.268 |
�士 | -0.263 |
Token | practical |
Token ID | 8472 |
Feature activation | -4.43e-02 |
Pos logit contributions | |
�� | +0.003 |
dra | +0.003 |
� | +0.003 |
EStreamFrame | +0.003 |
�士 | +0.003 |
Neg logit contributions | |
Buchanan | -0.002 |
sim | -0.002 |
Cain | -0.002 |
kitten | -0.002 |
quit | -0.002 |
Token | Social |
Token ID | 5483 |
Feature activation | -1.43e-03 |
Pos logit contributions | |
sim | +0.030 |
Buchanan | +0.029 |
kitten | +0.028 |
quit | +0.028 |
Cain | +0.028 |
Neg logit contributions | |
�� | -0.043 |
� | -0.043 |
dra | -0.043 |
srf | -0.040 |
�士 | -0.040 |
Token | ists |
Token ID | 1023 |
Feature activation | +5.27e-02 |
Pos logit contributions | |
sim | +0.001 |
Buchanan | +0.001 |
quit | +0.001 |
Cain | +0.001 |
kitten | +0.001 |
Neg logit contributions | |
� | -0.001 |
�� | -0.001 |
dra | -0.001 |
srf | -0.001 |
�士 | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
�� | +0.054 |
dra | +0.054 |
� | +0.054 |
srf | +0.051 |
�士 | +0.051 |
Neg logit contributions | |
sim | -0.032 |
Buchanan | -0.031 |
Cain | -0.030 |
kitten | -0.030 |
quit | -0.029 |
Token | f |
Token ID | 69 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
Cain | +0.006 |
sim | +0.006 |
keley | +0.006 |
Buchanan | +0.006 |
quit | +0.006 |
Neg logit contributions | |
�� | -0.011 |
� | -0.011 |
dra | -0.010 |
EStreamFrame | -0.010 |
srf | -0.010 |
Token | ner |
Token ID | 1008 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
Buchanan | +0.014 |
sim | +0.014 |
keley | +0.014 |
Cain | +0.013 |
quit | +0.013 |
Neg logit contributions | |
�� | -0.040 |
� | -0.039 |
srf | -0.038 |
dra | -0.037 |
EStreamFrame | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
sim | +0.041 |
Buchanan | +0.040 |
quit | +0.040 |
Cain | +0.040 |
keley | +0.039 |
Neg logit contributions | |
�� | -0.073 |
� | -0.072 |
dra | -0.072 |
srf | -0.067 |
�士 | -0.067 |
Token | whose |
Token ID | 3025 |
Feature activation | -4.69e-02 |
Pos logit contributions | |
sim | +0.008 |
Buchanan | +0.008 |
Cain | +0.008 |
kitten | +0.008 |
quit | +0.008 |
Neg logit contributions | |
�� | -0.015 |
� | -0.015 |
dra | -0.014 |
srf | -0.013 |
�士 | -0.013 |
Token | confid |
Token ID | 47830 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
sim | +0.029 |
Buchanan | +0.028 |
kitten | +0.027 |
Cain | +0.027 |
shame | +0.027 |
Neg logit contributions | |
�� | -0.048 |
� | -0.048 |
dra | -0.047 |
�士 | -0.045 |
srf | -0.045 |
Token | ant |
Token ID | 415 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
�� | +0.020 |
� | +0.020 |
dra | +0.020 |
srf | +0.019 |
EStreamFrame | +0.019 |
Neg logit contributions | |
sim | -0.012 |
quit | -0.012 |
Buchanan | -0.012 |
Cain | -0.012 |
kitten | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
sim | +0.151 |
Buchanan | +0.148 |
Cain | +0.147 |
quit | +0.146 |
kitten | +0.142 |
Neg logit contributions | |
�� | -0.265 |
� | -0.262 |
dra | -0.260 |
srf | -0.248 |
�士 | -0.244 |
Token | vice |
Token ID | 7927 |
Feature activation | -1.16e-03 |
Pos logit contributions | |
sim | +0.013 |
Buchanan | +0.013 |
Cain | +0.012 |
kitten | +0.012 |
shame | +0.012 |
Neg logit contributions | |
�� | -0.020 |
� | -0.020 |
dra | -0.019 |
srf | -0.018 |
�士 | -0.018 |
Token | president |
Token ID | 1893 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
sim | +0.001 |
Buchanan | +0.001 |
quit | +0.001 |
Cain | +0.001 |
kitten | +0.001 |
Neg logit contributions | |
�� | -0.001 |
dra | -0.001 |
� | -0.001 |
srf | -0.001 |
EStreamFrame | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
�� | +0.001 |
� | +0.001 |
dra | +0.001 |
srf | +0.001 |
�士 | +0.001 |
Neg logit contributions | |
sim | -0.001 |
Buchanan | -0.001 |
Cain | -0.001 |
quit | -0.001 |
kitten | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
sim | +0.010 |
Buchanan | +0.009 |
Cain | +0.009 |
quit | +0.009 |
shame | +0.009 |
Neg logit contributions | |
�� | -0.017 |
� | -0.017 |
dra | -0.017 |
srf | -0.016 |
� | -0.016 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
sim | +0.002 |
shame | +0.002 |
quit | +0.002 |
Buchanan | +0.002 |
kitten | +0.002 |
Neg logit contributions | |
�� | -0.003 |
� | -0.002 |
dra | -0.002 |
srf | -0.002 |
� | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
sim | +0.005 |
Buchanan | +0.005 |
quit | +0.005 |
kitten | +0.005 |
keley | +0.005 |
Neg logit contributions | |
�� | -0.013 |
dra | -0.013 |
� | -0.013 |
srf | -0.012 |
�士 | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e-03 |
Pos logit contributions | |
sim | +0.034 |
Buchanan | +0.033 |
quit | +0.033 |
Cain | +0.032 |
kitten | +0.032 |
Neg logit contributions | |
�� | -0.053 |
� | -0.053 |
dra | -0.053 |
srf | -0.050 |
�士 | -0.049 |
Token | CDC |
Token ID | 20434 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
Buchanan | +0.001 |
sim | +0.001 |
Cain | +0.001 |
shame | +0.001 |
Kap | +0.001 |
Neg logit contributions | |
� | -0.001 |
dra | -0.001 |
�� | -0.001 |
�士 | -0.001 |
srf | -0.001 |
Token | Guid |
Token ID | 37026 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
�� | +0.076 |
dra | +0.074 |
� | +0.074 |
srf | +0.070 |
�士 | +0.070 |
Neg logit contributions | |
sim | -0.036 |
quit | -0.035 |
Buchanan | -0.034 |
shame | -0.033 |
Cain | -0.033 |
Token | eline |
Token ID | 4470 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
�� | +0.003 |
� | +0.003 |
dra | +0.003 |
�士 | +0.003 |
srf | +0.003 |
Neg logit contributions | |
sim | -0.002 |
Buchanan | -0.002 |
Cain | -0.001 |
keley | -0.001 |
quit | -0.001 |
Token | itself |
Token ID | 2346 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
sim | +0.113 |
Buchanan | +0.107 |
quit | +0.106 |
kitten | +0.106 |
Cain | +0.105 |
Neg logit contributions | |
�� | -0.301 |
dra | -0.298 |
� | -0.296 |
�士 | -0.282 |
srf | -0.280 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
�� | +0.027 |
dra | +0.027 |
� | +0.027 |
�士 | +0.026 |
srf | +0.025 |
Neg logit contributions | |
sim | -0.013 |
quit | -0.012 |
Buchanan | -0.012 |
kitten | -0.012 |
keley | -0.012 |
Token | They |
Token ID | 1119 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
�� | +0.020 |
srf | +0.019 |
� | +0.019 |
dra | +0.018 |
ailability | +0.018 |
Neg logit contributions | |
Buchanan | -0.015 |
Cain | -0.014 |
Kap | -0.014 |
sim | -0.014 |
quit | -0.013 |
Token | see |
Token ID | 766 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
�� | +0.022 |
dra | +0.021 |
� | +0.020 |
srf | +0.019 |
� | +0.019 |
Neg logit contributions | |
sim | -0.014 |
shame | -0.013 |
quit | -0.013 |
Buchanan | -0.013 |
kitten | -0.013 |
Token | that |
Token ID | 326 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
� | +0.053 |
dra | +0.053 |
�� | +0.053 |
EStreamFrame | +0.049 |
srf | +0.049 |
Neg logit contributions | |
sim | -0.034 |
shame | -0.033 |
Buchanan | -0.033 |
Cain | -0.032 |
kitten | -0.032 |
Token | е |
Token ID | 16843 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
sim | +0.012 |
quit | +0.012 |
Buchanan | +0.012 |
Cain | +0.012 |
keley | +0.012 |
Neg logit contributions | |
� | -0.011 |
dra | -0.011 |
�� | -0.010 |
�士 | -0.009 |
EStreamFrame | -0.009 |
Token | р |
Token ID | 21169 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
Buchanan | +0.035 |
keley | +0.035 |
Cain | +0.035 |
sim | +0.035 |
quit | +0.035 |
Neg logit contributions | |
� | -0.020 |
dra | -0.019 |
�� | -0.019 |
#$ | -0.016 |
�士 | -0.016 |
Token | д |
Token ID | 43666 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
�� | +0.020 |
dra | +0.020 |
� | +0.020 |
srf | +0.018 |
�士 | +0.018 |
Neg logit contributions | |
sim | -0.024 |
quit | -0.024 |
Buchanan | -0.023 |
kitten | -0.023 |
Cain | -0.023 |
Token | и |
Token ID | 18849 |
Feature activation | -7.03e-02 |
Pos logit contributions | |
dra | +0.053 |
�� | +0.053 |
� | +0.052 |
srf | +0.049 |
�士 | +0.048 |
Neg logit contributions | |
sim | -0.039 |
quit | -0.039 |
Buchanan | -0.038 |
kitten | -0.038 |
Cain | -0.038 |
Token | т |
Token ID | 20375 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
sim | +0.054 |
quit | +0.053 |
kitten | +0.052 |
Buchanan | +0.052 |
keley | +0.052 |
Neg logit contributions | |
�� | -0.059 |
dra | -0.058 |
� | -0.056 |
srf | -0.054 |
�士 | -0.054 |
Token | ь |
Token ID | 45367 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
�� | +0.025 |
dra | +0.025 |
� | +0.024 |
srf | +0.023 |
�士 | +0.023 |
Neg logit contributions | |
sim | -0.019 |
quit | -0.019 |
kitten | -0.019 |
Buchanan | -0.018 |
Cain | -0.018 |
Token | � |
Token ID | 12466 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
sim | +0.203 |
quit | +0.197 |
Buchanan | +0.197 |
kitten | +0.196 |
Cain | +0.195 |
Neg logit contributions | |
�� | -0.202 |
dra | -0.196 |
� | -0.192 |
srf | -0.183 |
�士 | -0.182 |
Token | � |
Token ID | 111 |
Feature activation | +3.14e-02 |
Pos logit contributions | |
dra | +0.046 |
� | +0.045 |
�� | +0.044 |
srf | +0.041 |
EStreamFrame | +0.041 |
Neg logit contributions | |
sim | -0.041 |
quit | -0.041 |
Buchanan | -0.040 |
kitten | -0.040 |
keley | -0.040 |
Token | и |
Token ID | 18849 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
�� | +0.025 |
dra | +0.025 |
� | +0.024 |
srf | +0.023 |
�士 | +0.023 |
Neg logit contributions | |
sim | -0.025 |
quit | -0.025 |
kitten | -0.024 |
Buchanan | -0.024 |
keley | -0.024 |
Token | � |
Token ID | 140 |
Feature activation | +5.88e-03 |
Pos logit contributions | |
sim | +0.067 |
quit | +0.066 |
Buchanan | +0.066 |
kitten | +0.065 |
keley | +0.065 |
Neg logit contributions | |
�� | -0.057 |
dra | -0.056 |
� | -0.054 |
srf | -0.051 |
�士 | -0.050 |
Token | � |
Token ID | 109 |
Feature activation | -7.59e-02 |
Pos logit contributions | |
dra | +0.004 |
�� | +0.004 |
� | +0.004 |
srf | +0.004 |
�士 | +0.004 |
Neg logit contributions | |
sim | -0.005 |
quit | -0.005 |
Buchanan | -0.005 |
keley | -0.005 |
Cain | -0.005 |
Token | quarterbacks |
Token ID | 23643 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
sim | +0.031 |
quit | +0.031 |
Buchanan | +0.031 |
keley | +0.031 |
kitten | +0.031 |
Neg logit contributions | |
� | -0.043 |
dra | -0.043 |
�� | -0.043 |
EStreamFrame | -0.039 |
srf | -0.039 |
Token | ) |
Token ID | 8 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
quit | +0.013 |
keley | +0.013 |
Buchanan | +0.013 |
kitten | +0.012 |
sim | +0.012 |
Neg logit contributions | |
dra | -0.017 |
� | -0.017 |
�� | -0.017 |
EStreamFrame | -0.016 |
srf | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
quit | +0.020 |
keley | +0.020 |
kitten | +0.020 |
sim | +0.020 |
Buchanan | +0.020 |
Neg logit contributions | |
� | -0.029 |
dra | -0.028 |
�� | -0.028 |
EStreamFrame | -0.026 |
#$ | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
sim | +0.011 |
Buchanan | +0.010 |
quit | +0.010 |
Cain | +0.010 |
Kap | +0.010 |
Neg logit contributions | |
� | -0.041 |
� | -0.040 |
srf | -0.040 |
� | -0.040 |
�� | -0.040 |
Token | Br |
Token ID | 9414 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
quit | +0.026 |
sim | +0.025 |
Buchanan | +0.024 |
Cain | +0.024 |
Kap | +0.024 |
Neg logit contributions | |
srf | -0.028 |
�� | -0.027 |
� | -0.027 |
� | -0.027 |
dra | -0.026 |
Token | ady |
Token ID | 4597 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
sim | +0.004 |
quit | +0.004 |
keley | +0.004 |
shame | +0.004 |
spat | +0.003 |
Neg logit contributions | |
�� | -0.018 |
srf | -0.017 |
�士 | -0.017 |
� | -0.017 |
� | -0.017 |
Token | is |
Token ID | 318 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
sim | +0.152 |
quit | +0.145 |
Buchanan | +0.145 |
Cain | +0.144 |
kitten | +0.141 |
Neg logit contributions | |
�� | -0.252 |
dra | -0.251 |
� | -0.247 |
srf | -0.235 |
�士 | -0.232 |
Token | easily |
Token ID | 3538 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
sim | +0.019 |
Buchanan | +0.018 |
Cain | +0.018 |
kitten | +0.017 |
shame | +0.017 |
Neg logit contributions | |
�� | -0.034 |
dra | -0.034 |
� | -0.033 |
srf | -0.031 |
�士 | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
sim | +0.007 |
Buchanan | +0.006 |
quit | +0.006 |
Cain | +0.006 |
kitten | +0.006 |
Neg logit contributions | |
dra | -0.010 |
�� | -0.010 |
� | -0.009 |
srf | -0.009 |
�士 | -0.009 |
Token | most |
Token ID | 749 |
Feature activation | +5.49e-03 |
Pos logit contributions | |
sim | +0.012 |
kitten | +0.011 |
Buchanan | +0.011 |
Cain | +0.011 |
shame | +0.011 |
Neg logit contributions | |
�� | -0.023 |
dra | -0.022 |
� | -0.022 |
srf | -0.021 |
�士 | -0.021 |
Token | under |
Token ID | 739 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
�� | +0.005 |
dra | +0.005 |
� | +0.005 |
srf | +0.005 |
EStreamFrame | +0.005 |
Neg logit contributions | |
sim | -0.004 |
Buchanan | -0.004 |
shame | -0.004 |
Cain | -0.004 |
kitten | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | -7.03e-03 |
Pos logit contributions | |
�� | +0.016 |
dra | +0.016 |
� | +0.016 |
srf | +0.015 |
�士 | +0.015 |
Neg logit contributions | |
sim | -0.011 |
Buchanan | -0.011 |
quit | -0.011 |
Cain | -0.010 |
keley | -0.010 |
Token | headed |
Token ID | 9153 |
Feature activation | -2.52e-02 |
Pos logit contributions | |
sim | +0.004 |
Buchanan | +0.004 |
Cain | +0.004 |
quit | +0.004 |
kitten | +0.004 |
Neg logit contributions | |
�� | -0.008 |
dra | -0.008 |
� | -0.008 |
�士 | -0.007 |
srf | -0.007 |
Token | by |
Token ID | 416 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
sim | +0.015 |
kitten | +0.015 |
quit | +0.015 |
Cain | +0.014 |
keley | +0.014 |
Neg logit contributions | |
� | -0.025 |
dra | -0.025 |
�� | -0.025 |
�士 | -0.023 |
srf | -0.023 |
Token | Morris |
Token ID | 14433 |
Feature activation | -5.98e-02 |
Pos logit contributions | |
Buchanan | +0.007 |
sim | +0.007 |
Cain | +0.007 |
quit | +0.007 |
kitten | +0.007 |
Neg logit contributions | |
�� | -0.010 |
dra | -0.010 |
� | -0.010 |
srf | -0.010 |
�士 | -0.010 |
Token | Hill |
Token ID | 3327 |
Feature activation | -9.52e-04 |
Pos logit contributions | |
Buchanan | +0.038 |
sim | +0.037 |
quit | +0.037 |
Cain | +0.036 |
Kap | +0.035 |
Neg logit contributions | |
�� | -0.060 |
dra | -0.059 |
� | -0.059 |
srf | -0.056 |
�士 | -0.055 |
Token | quit |
Token ID | 47391 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
Buchanan | +0.001 |
quit | +0.001 |
sim | +0.001 |
Cain | +0.001 |
keley | +0.000 |
Neg logit contributions | |
� | -0.001 |
�� | -0.001 |
dra | -0.001 |
srf | -0.001 |
EStreamFrame | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
Buchanan | +0.133 |
quit | +0.132 |
sim | +0.131 |
keley | +0.128 |
Cain | +0.127 |
Neg logit contributions | |
�� | -0.267 |
� | -0.264 |
dra | -0.264 |
srf | -0.247 |
�士 | -0.246 |
Token | James |
Token ID | 3700 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
�� | +0.022 |
dra | +0.022 |
� | +0.021 |
EStreamFrame | +0.020 |
srf | +0.020 |
Neg logit contributions | |
Buchanan | -0.013 |
sim | -0.013 |
Cain | -0.012 |
kitten | -0.012 |
quit | -0.012 |
Token | One |
Token ID | 1881 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
�� | +0.026 |
� | +0.025 |
dra | +0.025 |
srf | +0.024 |
EStreamFrame | +0.024 |
Neg logit contributions | |
Buchanan | -0.018 |
Cain | -0.018 |
sim | -0.017 |
quit | -0.017 |
Kap | -0.017 |
Token | al |
Token ID | 282 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
quit | +0.014 |
Buchanan | +0.014 |
keley | +0.014 |
sim | +0.014 |
Cain | +0.013 |
Neg logit contributions | |
� | -0.021 |
�� | -0.021 |
dra | -0.021 |
srf | -0.020 |
EStreamFrame | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +1.62e-02 |
Pos logit contributions | |
quit | +0.008 |
Buchanan | +0.008 |
sim | +0.008 |
Cain | +0.008 |
keley | +0.008 |
Neg logit contributions | |
� | -0.014 |
�� | -0.014 |
dra | -0.014 |
srf | -0.013 |
EStreamFrame | -0.013 |
Token | 've |
Token ID | 1053 |
Feature activation | +7.90e-03 |
Pos logit contributions | |
�� | +0.014 |
� | +0.013 |
dra | +0.013 |
� | +0.013 |
�士 | +0.012 |
Neg logit contributions | |
sim | -0.008 |
kitten | -0.007 |
shame | -0.007 |
quit | -0.007 |
spat | -0.007 |
Token | spoke |
Token ID | 5158 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
�� | +0.009 |
� | +0.009 |
dra | +0.009 |
srf | +0.008 |
� | +0.008 |
Neg logit contributions | |
sim | -0.004 |
kitten | -0.004 |
shame | -0.004 |
quit | -0.004 |
Cain | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
�� | +0.024 |
dra | +0.024 |
� | +0.024 |
srf | +0.023 |
�士 | +0.023 |
Neg logit contributions | |
sim | -0.012 |
kitten | -0.011 |
Cain | -0.011 |
quit | -0.011 |
shame | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
sim | +0.012 |
kitten | +0.012 |
shame | +0.012 |
Cain | +0.012 |
Buchanan | +0.012 |
Neg logit contributions | |
�� | -0.022 |
� | -0.021 |
dra | -0.021 |
�士 | -0.020 |
srf | -0.020 |
Token | Bel |
Token ID | 12193 |
Feature activation | +6.82e-03 |
Pos logit contributions | |
quit | +0.017 |
kitten | +0.016 |
sim | +0.016 |
shame | +0.015 |
Cain | +0.015 |
Neg logit contributions | |
�� | -0.026 |
srf | -0.025 |
� | -0.025 |
� | -0.025 |
� | -0.024 |
Token | ieve |
Token ID | 12311 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
�� | +0.006 |
� | +0.006 |
dra | +0.005 |
srf | +0.005 |
�士 | +0.005 |
Neg logit contributions | |
quit | -0.005 |
sim | -0.005 |
keley | -0.005 |
Buchanan | -0.005 |
kitten | -0.005 |
Token | me |
Token ID | 502 |
Feature activation | +2.06e-03 |
Pos logit contributions | |
sim | +0.128 |
Cain | +0.125 |
Buchanan | +0.125 |
kitten | +0.125 |
quit | +0.123 |
Neg logit contributions | |
�� | -0.273 |
� | -0.270 |
dra | -0.270 |
srf | -0.255 |
EStreamFrame | -0.253 |
Token | , |
Token ID | 11 |
Feature activation | +3.91e-04 |
Pos logit contributions | |
�� | +0.002 |
� | +0.002 |
dra | +0.002 |
srf | +0.002 |
EStreamFrame | +0.002 |
Neg logit contributions | |
sim | -0.001 |
kitten | -0.001 |
Buchanan | -0.001 |
quit | -0.001 |
Cain | -0.001 |
Token | Anna |
Token ID | 11735 |
Feature activation | -2.87e-03 |
Pos logit contributions | |
�� | +0.000 |
� | +0.000 |
dra | +0.000 |
srf | +0.000 |
� | +0.000 |
Neg logit contributions | |
sim | -0.000 |
kitten | -0.000 |
Cain | -0.000 |
shame | -0.000 |
Buchanan | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
sim | +0.002 |
Buchanan | +0.002 |
kitten | +0.002 |
quit | +0.002 |
Cain | +0.002 |
Neg logit contributions | |
�� | -0.003 |
� | -0.003 |
dra | -0.003 |
srf | -0.003 |
�士 | -0.003 |
Token | If |
Token ID | 1002 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
�� | +0.016 |
srf | +0.016 |
� | +0.015 |
� | +0.015 |
� | +0.015 |
Neg logit contributions | |
Cain | -0.007 |
Buchanan | -0.007 |
sim | -0.007 |
Kap | -0.007 |
kitten | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | +4.72e-02 |
Pos logit contributions | |
�� | +0.075 |
� | +0.075 |
dra | +0.075 |
srf | +0.070 |
EStreamFrame | +0.069 |
Neg logit contributions | |
sim | -0.045 |
Buchanan | -0.044 |
quit | -0.043 |
Cain | -0.043 |
kitten | -0.042 |
Token | job |
Token ID | 1693 |
Feature activation | +3.97e-03 |
Pos logit contributions | |
�� | +0.051 |
� | +0.050 |
dra | +0.050 |
�士 | +0.048 |
srf | +0.047 |
Neg logit contributions | |
sim | -0.028 |
Buchanan | -0.026 |
kitten | -0.026 |
shame | -0.026 |
Cain | -0.026 |
Token | as |
Token ID | 355 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
�� | +0.004 |
dra | +0.004 |
� | +0.004 |
�士 | +0.004 |
srf | +0.004 |
Neg logit contributions | |
sim | -0.002 |
Buchanan | -0.002 |
quit | -0.002 |
kitten | -0.002 |
Cain | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
� | +0.038 |
dra | +0.038 |
�� | +0.038 |
srf | +0.035 |
EStreamFrame | +0.035 |
Neg logit contributions | |
sim | -0.022 |
Buchanan | -0.022 |
quit | -0.022 |
kitten | -0.021 |
Cain | -0.021 |
Token | flight |
Token ID | 5474 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
� | +0.038 |
�� | +0.038 |
dra | +0.038 |
srf | +0.035 |
�士 | +0.035 |
Neg logit contributions | |
sim | -0.023 |
Buchanan | -0.022 |
kitten | -0.022 |
quit | -0.022 |
Kap | -0.021 |
Token | attendant |
Token ID | 31277 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
�� | +0.033 |
� | +0.032 |
dra | +0.032 |
EStreamFrame | +0.030 |
srf | +0.030 |
Neg logit contributions | |
sim | -0.022 |
quit | -0.019 |
Buchanan | -0.019 |
kitten | -0.019 |
keley | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
�� | +0.144 |
� | +0.143 |
dra | +0.142 |
�士 | +0.135 |
srf | +0.134 |
Neg logit contributions | |
sim | -0.073 |
Buchanan | -0.069 |
kitten | -0.067 |
Cain | -0.067 |
quit | -0.067 |
Token | It |
Token ID | 632 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
�� | +0.042 |
srf | +0.041 |
� | +0.040 |
� | +0.040 |
dra | +0.039 |
Neg logit contributions | |
Buchanan | -0.028 |
Kap | -0.027 |
Cain | -0.027 |
sim | -0.027 |
quit | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
�� | +0.025 |
� | +0.025 |
dra | +0.025 |
srf | +0.023 |
� | +0.023 |
Neg logit contributions | |
sim | -0.015 |
Buchanan | -0.014 |
Cain | -0.014 |
kitten | -0.014 |
shame | -0.014 |
Token | glamorous |
Token ID | 46185 |
Feature activation | +6.32e-02 |
Pos logit contributions | |
�� | +0.037 |
dra | +0.036 |
� | +0.036 |
srf | +0.035 |
� | +0.034 |
Neg logit contributions | |
sim | -0.019 |
Buchanan | -0.019 |
Cain | -0.018 |
kitten | -0.018 |
shame | -0.018 |
Token | ; |
Token ID | 26 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
�� | +0.067 |
dra | +0.066 |
� | +0.066 |
�士 | +0.062 |
srf | +0.062 |
Neg logit contributions | |
sim | -0.036 |
Buchanan | -0.035 |
kitten | -0.034 |
Cain | -0.034 |
quit | -0.034 |
Token | Car |
Token ID | 1879 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
sim | +0.038 |
Cain | +0.037 |
Buchanan | +0.036 |
kitten | +0.036 |
quit | +0.036 |
Neg logit contributions | |
�� | -0.056 |
dra | -0.056 |
� | -0.055 |
EStreamFrame | -0.053 |
�士 | -0.051 |
Token | steel |
Token ID | 44822 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
�� | +0.048 |
� | +0.048 |
dra | +0.047 |
�士 | +0.045 |
-+-+ | +0.044 |
Neg logit contributions | |
sim | -0.031 |
quit | -0.031 |
keley | -0.030 |
Cain | -0.030 |
Buchanan | -0.030 |
Token | as |
Token ID | 355 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
�� | +0.048 |
dra | +0.047 |
� | +0.047 |
EStreamFrame | +0.044 |
srf | +0.044 |
Neg logit contributions | |
sim | -0.026 |
Buchanan | -0.026 |
Cain | -0.026 |
quit | -0.026 |
kitten | -0.025 |
Token | an |
Token ID | 281 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
�� | +0.004 |
� | +0.004 |
dra | +0.004 |
EStreamFrame | +0.004 |
�士 | +0.004 |
Neg logit contributions | |
sim | -0.002 |
Buchanan | -0.002 |
Cain | -0.002 |
kitten | -0.002 |
quit | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
sim | +0.007 |
Cain | +0.007 |
Buchanan | +0.007 |
kitten | +0.007 |
Kap | +0.007 |
Neg logit contributions | |
�� | -0.011 |
� | -0.010 |
dra | -0.010 |
EStreamFrame | -0.010 |
srf | -0.010 |
Token | organ |
Token ID | 9971 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
�� | +0.017 |
� | +0.017 |
dra | +0.016 |
srf | +0.016 |
-+-+ | +0.016 |
Neg logit contributions | |
quit | -0.012 |
sim | -0.012 |
keley | -0.012 |
kitten | -0.012 |
Cain | -0.011 |
Token | ization |
Token ID | 1634 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
�� | +0.192 |
� | +0.188 |
dra | +0.188 |
srf | +0.175 |
�士 | +0.174 |
Neg logit contributions | |
sim | -0.145 |
kitten | -0.141 |
quit | -0.140 |
Cain | -0.139 |
Buchanan | -0.139 |
Token | of |
Token ID | 286 |
Feature activation | +1.25e-03 |
Pos logit contributions | |
sim | +0.068 |
kitten | +0.065 |
Cain | +0.064 |
Buchanan | +0.063 |
quit | +0.062 |
Neg logit contributions | |
�� | -0.126 |
� | -0.124 |
dra | -0.123 |
srf | -0.117 |
EStreamFrame | -0.116 |
Token | distinction |
Token ID | 12941 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
�� | +0.001 |
dra | +0.001 |
� | +0.001 |
srf | +0.001 |
�士 | +0.001 |
Neg logit contributions | |
sim | -0.001 |
Cain | -0.001 |
shame | -0.001 |
Buchanan | -0.001 |
kitten | -0.001 |
Token | ." |
Token ID | 526 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
�� | +0.028 |
dra | +0.027 |
� | +0.027 |
srf | +0.025 |
EStreamFrame | +0.025 |
Neg logit contributions | |
sim | -0.017 |
Buchanan | -0.016 |
kitten | -0.016 |
quit | -0.016 |
Cain | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
�� | +0.017 |
� | +0.017 |
dra | +0.017 |
srf | +0.016 |
EStreamFrame | +0.016 |
Neg logit contributions | |
Buchanan | -0.009 |
sim | -0.009 |
Cain | -0.008 |
quit | -0.008 |
Kap | -0.008 |
Token | I |
Token ID | 314 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
sim | +0.003 |
Buchanan | +0.003 |
quit | +0.003 |
kitten | +0.003 |
Cain | +0.003 |
Neg logit contributions | |
�� | -0.006 |
� | -0.006 |
dra | -0.006 |
srf | -0.006 |
EStreamFrame | -0.006 |
Token | gave |
Token ID | 2921 |
Feature activation | -9.93e-03 |
Pos logit contributions | |
sim | +0.010 |
kitten | +0.009 |
spat | +0.009 |
Buchanan | +0.008 |
quit | +0.008 |
Neg logit contributions | |
�� | -0.017 |
� | -0.017 |
dra | -0.016 |
srf | -0.016 |
� | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | -2.37e-03 |
Pos logit contributions | |
sim | +0.006 |
Buchanan | +0.006 |
quit | +0.006 |
Cain | +0.006 |
kitten | +0.006 |
Neg logit contributions | |
�� | -0.009 |
dra | -0.009 |
� | -0.009 |
srf | -0.009 |
EStreamFrame | -0.009 |
Token | another |
Token ID | 1194 |
Feature activation | -4.42e-03 |
Pos logit contributions | |
sim | +0.001 |
Buchanan | +0.001 |
kitten | +0.001 |
Cain | +0.001 |
quit | +0.001 |
Neg logit contributions | |
�� | -0.002 |
� | -0.002 |
dra | -0.002 |
srf | -0.002 |
EStreamFrame | -0.002 |
Token | fe |
Token ID | 730 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
sim | +0.003 |
kitten | +0.002 |
Buchanan | +0.002 |
Cain | +0.002 |
shame | +0.002 |
Neg logit contributions | |
�� | -0.005 |
� | -0.005 |
dra | -0.005 |
� | -0.004 |
srf | -0.004 |
Token | int |
Token ID | 600 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
�� | +0.028 |
� | +0.027 |
dra | +0.026 |
srf | +0.026 |
�士 | +0.025 |
Neg logit contributions | |
sim | -0.019 |
quit | -0.018 |
keley | -0.018 |
kitten | -0.018 |
Buchanan | -0.018 |
Token | highlight |
Token ID | 7238 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
�� | +0.145 |
� | +0.143 |
dra | +0.143 |
srf | +0.136 |
�士 | +0.136 |
Neg logit contributions | |
sim | -0.071 |
kitten | -0.067 |
quit | -0.066 |
Buchanan | -0.066 |
Cain | -0.065 |
Token | of |
Token ID | 286 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
�� | +0.048 |
� | +0.047 |
dra | +0.047 |
�士 | +0.045 |
srf | +0.045 |
Neg logit contributions | |
sim | -0.023 |
kitten | -0.022 |
quit | -0.021 |
Buchanan | -0.021 |
Cain | -0.021 |
Token | Light |
Token ID | 4401 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
sim | +0.008 |
Buchanan | +0.008 |
Cain | +0.008 |
kitten | +0.008 |
shame | +0.008 |
Neg logit contributions | |
�� | -0.014 |
� | -0.014 |
dra | -0.013 |
srf | -0.013 |
�士 | -0.012 |
Token | Grey |
Token ID | 13980 |
Feature activation | -5.69e-02 |
Pos logit contributions | |
sim | +0.027 |
quit | +0.027 |
Buchanan | +0.026 |
keley | +0.026 |
kitten | +0.026 |
Neg logit contributions | |
dra | -0.027 |
� | -0.026 |
�� | -0.026 |
srf | -0.023 |
�士 | -0.023 |
Token | ( |
Token ID | 357 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
sim | +0.030 |
kitten | +0.029 |
Buchanan | +0.028 |
Cain | +0.028 |
quit | +0.028 |
Neg logit contributions | |
�� | -0.062 |
� | -0.062 |
dra | -0.061 |
srf | -0.058 |
�士 | -0.058 |
Token | � |
Token ID | 447 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
�� | +0.006 |
dra | +0.006 |
� | +0.006 |
srf | +0.006 |
EStreamFrame | +0.006 |
Neg logit contributions | |
Buchanan | -0.003 |
Cain | -0.003 |
sim | -0.003 |
quit | -0.003 |
kitten | -0.003 |
Token | � |
Token ID | 247 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
dra | +0.011 |
� | +0.011 |
�� | +0.010 |
srf | +0.010 |
EStreamFrame | +0.010 |
Neg logit contributions | |
sim | -0.012 |
Buchanan | -0.011 |
kitten | -0.011 |
keley | -0.011 |
Cain | -0.011 |
Token | t |
Token ID | 83 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
�� | +0.017 |
dra | +0.016 |
� | +0.016 |
srf | +0.016 |
EStreamFrame | +0.016 |
Neg logit contributions | |
sim | -0.010 |
quit | -0.010 |
Cain | -0.010 |
Buchanan | -0.010 |
kitten | -0.010 |
Token | you |
Token ID | 345 |
Feature activation | -4.31e-03 |
Pos logit contributions | |
�� | +0.024 |
dra | +0.023 |
� | +0.023 |
srf | +0.022 |
EStreamFrame | +0.022 |
Neg logit contributions | |
Cain | -0.014 |
Buchanan | -0.014 |
sim | -0.014 |
shame | -0.013 |
quit | -0.013 |
Token | ? |
Token ID | 30 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
shame | +0.002 |
sim | +0.002 |
quit | +0.002 |
kitten | +0.002 |
Buchanan | +0.002 |
Neg logit contributions | |
�� | -0.005 |
dra | -0.005 |
� | -0.005 |
� | -0.004 |
srf | -0.004 |
Token | Warning |
Token ID | 15932 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
�� | +0.024 |
srf | +0.023 |
dra | +0.023 |
� | +0.022 |
� | +0.022 |
Neg logit contributions | |
Cain | -0.014 |
Buchanan | -0.014 |
sim | -0.014 |
quit | -0.014 |
Kap | -0.013 |
Token | : |
Token ID | 25 |
Feature activation | -3.39e-03 |
Pos logit contributions | |
�� | +0.152 |
� | +0.150 |
dra | +0.149 |
�士 | +0.140 |
srf | +0.140 |
Neg logit contributions | |
sim | -0.077 |
Cain | -0.075 |
kitten | -0.074 |
quit | -0.074 |
Buchanan | -0.074 |
Token | Doing |
Token ID | 25327 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
sim | +0.002 |
Buchanan | +0.002 |
Cain | +0.002 |
kitten | +0.002 |
quit | +0.002 |
Neg logit contributions | |
� | -0.003 |
�� | -0.003 |
dra | -0.003 |
srf | -0.003 |
� | -0.003 |
Token | what |
Token ID | 644 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
�� | +0.087 |
dra | +0.085 |
� | +0.084 |
srf | +0.080 |
EStreamFrame | +0.080 |
Neg logit contributions | |
sim | -0.049 |
Buchanan | -0.048 |
Cain | -0.047 |
kitten | -0.047 |
shame | -0.047 |
Token | Cory |
Token ID | 28785 |
Feature activation | -6.52e-03 |
Pos logit contributions | |
�� | +0.076 |
dra | +0.074 |
� | +0.074 |
srf | +0.070 |
EStreamFrame | +0.070 |
Neg logit contributions | |
sim | -0.035 |
Cain | -0.035 |
Buchanan | -0.035 |
quit | -0.034 |
shame | -0.033 |
Token | Booker |
Token ID | 31004 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
Buchanan | +0.005 |
Cain | +0.005 |
sim | +0.005 |
quit | +0.005 |
shame | +0.005 |
Neg logit contributions | |
�� | -0.006 |
� | -0.005 |
dra | -0.005 |
srf | -0.005 |
� | -0.005 |
Token | going |
Token ID | 1016 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
�� | +0.046 |
dra | +0.045 |
� | +0.045 |
srf | +0.043 |
�士 | +0.042 |
Neg logit contributions | |
sim | -0.029 |
kitten | -0.028 |
Cain | -0.028 |
shame | -0.028 |
Buchanan | -0.028 |
Token | through |
Token ID | 832 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
�� | +0.033 |
� | +0.033 |
dra | +0.033 |
�士 | +0.031 |
srf | +0.031 |
Neg logit contributions | |
sim | -0.013 |
Buchanan | -0.013 |
kitten | -0.012 |
Cain | -0.012 |
shame | -0.012 |
Token | worker |
Token ID | 8383 |
Feature activation | +6.01e-02 |
Pos logit contributions | |
sim | +0.012 |
Buchanan | +0.012 |
kitten | +0.011 |
Cain | +0.011 |
shame | +0.011 |
Neg logit contributions | |
�� | -0.020 |
dra | -0.020 |
� | -0.020 |
srf | -0.018 |
�士 | -0.018 |
Token | - |
Token ID | 12 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
�� | +0.063 |
� | +0.063 |
dra | +0.063 |
�士 | +0.060 |
srf | +0.059 |
Neg logit contributions | |
sim | -0.036 |
shame | -0.033 |
Cain | -0.033 |
quit | -0.033 |
keley | -0.033 |
Token | ret |
Token ID | 1186 |
Feature activation | +3.36e-02 |
Pos logit contributions | |
�� | +0.018 |
� | +0.017 |
dra | +0.017 |
srf | +0.016 |
�士 | +0.016 |
Neg logit contributions | |
sim | -0.014 |
quit | -0.014 |
keley | -0.013 |
Cain | -0.013 |
Buchanan | -0.013 |
Token | raining |
Token ID | 24674 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
�� | +0.030 |
� | +0.029 |
dra | +0.029 |
srf | +0.028 |
�士 | +0.028 |
Neg logit contributions | |
sim | -0.025 |
quit | -0.024 |
Buchanan | -0.024 |
keley | -0.024 |
Cain | -0.023 |
Token | programs |
Token ID | 4056 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
�� | +0.152 |
� | +0.150 |
dra | +0.149 |
�士 | +0.142 |
srf | +0.141 |
Neg logit contributions | |
sim | -0.076 |
Buchanan | -0.070 |
kitten | -0.070 |
Cain | -0.070 |
keley | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
�� | +0.052 |
dra | +0.051 |
� | +0.051 |
�士 | +0.048 |
srf | +0.048 |
Neg logit contributions | |
sim | -0.026 |
Buchanan | -0.024 |
quit | -0.024 |
kitten | -0.024 |
Cain | -0.024 |
Token | in |
Token ID | 287 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
�� | +0.024 |
dra | +0.024 |
� | +0.024 |
srf | +0.022 |
�士 | +0.022 |
Neg logit contributions | |
sim | -0.014 |
kitten | -0.013 |
Buchanan | -0.013 |
Cain | -0.013 |
quit | -0.013 |
Token | an |
Token ID | 281 |
Feature activation | +7.48e-03 |
Pos logit contributions | |
�� | +0.029 |
dra | +0.029 |
� | +0.028 |
srf | +0.027 |
�士 | +0.027 |
Neg logit contributions | |
sim | -0.017 |
Buchanan | -0.016 |
Cain | -0.016 |
shame | -0.016 |
kitten | -0.015 |
Token | effort |
Token ID | 3626 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
�� | +0.008 |
dra | +0.007 |
� | +0.007 |
srf | +0.007 |
EStreamFrame | +0.007 |
Neg logit contributions | |
sim | -0.005 |
Cain | -0.005 |
kitten | -0.005 |
Buchanan | -0.005 |
Kap | -0.005 |
Token | ophobic |
Token ID | 23468 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
�� | +0.028 |
dra | +0.028 |
� | +0.028 |
�士 | +0.026 |
srf | +0.026 |
Neg logit contributions | |
sim | -0.026 |
quit | -0.025 |
Buchanan | -0.025 |
keley | -0.025 |
Cain | -0.024 |
Token | issues |
Token ID | 2428 |
Feature activation | +4.48e-02 |
Pos logit contributions | |
�� | +0.058 |
dra | +0.057 |
� | +0.057 |
�士 | +0.054 |
srf | +0.054 |
Neg logit contributions | |
sim | -0.040 |
Buchanan | -0.038 |
shame | -0.038 |
Cain | -0.037 |
kitten | -0.037 |
Token | that |
Token ID | 326 |
Feature activation | -4.88e-03 |
Pos logit contributions | |
dra | +0.048 |
�� | +0.048 |
� | +0.047 |
srf | +0.045 |
�士 | +0.045 |
Neg logit contributions | |
sim | -0.025 |
Buchanan | -0.024 |
Cain | -0.024 |
quit | -0.023 |
keley | -0.023 |
Token | dw |
Token ID | 43756 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
sim | +0.003 |
Buchanan | +0.003 |
Cain | +0.003 |
quit | +0.003 |
shame | +0.003 |
Neg logit contributions | |
�� | -0.005 |
dra | -0.005 |
� | -0.005 |
�士 | -0.005 |
EStreamFrame | -0.005 |
Token | elt |
Token ID | 2120 |
Feature activation | +7.52e-02 |
Pos logit contributions | |
keley | +0.021 |
sim | +0.021 |
quit | +0.021 |
Buchanan | +0.020 |
Cain | +0.020 |
Neg logit contributions | |
�� | -0.025 |
dra | -0.024 |
� | -0.024 |
srf | -0.023 |
�士 | -0.023 |
Token | un |
Token ID | 555 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
dra | +0.082 |
�� | +0.082 |
� | +0.081 |
srf | +0.076 |
�士 | +0.075 |
Neg logit contributions | |
sim | -0.039 |
Buchanan | -0.038 |
quit | -0.037 |
Cain | -0.037 |
keley | -0.037 |
Token | spoken |
Token ID | 19842 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
quit | +0.002 |
sim | +0.002 |
keley | +0.002 |
Buchanan | +0.002 |
Cain | +0.001 |
Neg logit contributions | |
�� | -0.003 |
dra | -0.003 |
� | -0.003 |
srf | -0.003 |
�士 | -0.003 |
Token | at |
Token ID | 379 |
Feature activation | +2.71e-02 |
Pos logit contributions | |
�� | +0.105 |
dra | +0.104 |
� | +0.103 |
�士 | +0.098 |
srf | +0.097 |
Neg logit contributions | |
sim | -0.046 |
Buchanan | -0.045 |
quit | -0.044 |
Cain | -0.044 |
keley | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e-04 |
Pos logit contributions | |
dra | +0.027 |
�� | +0.027 |
� | +0.027 |
srf | +0.025 |
�士 | +0.025 |
Neg logit contributions | |
sim | -0.017 |
Buchanan | -0.016 |
Cain | -0.016 |
keley | -0.016 |
kitten | -0.015 |
Token | heart |
Token ID | 2612 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
sim | +0.000 |
Buchanan | +0.000 |
Cain | +0.000 |
kitten | +0.000 |
shame | +0.000 |
Neg logit contributions | |
dra | -0.000 |
�� | -0.000 |
� | -0.000 |
srf | -0.000 |
�士 | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | -2.31e-03 |
Pos logit contributions | |
�� | +0.027 |
� | +0.026 |
�士 | +0.026 |
dra | +0.026 |
srf | +0.026 |
Neg logit contributions | |
sim | -0.007 |
Buchanan | -0.007 |
Cain | -0.007 |
shame | -0.007 |
quit | -0.007 |
Token | you |
Token ID | 345 |
Feature activation | +9.38e-03 |
Pos logit contributions | |
�� | +0.048 |
dra | +0.048 |
� | +0.048 |
srf | +0.045 |
�士 | +0.045 |
Neg logit contributions | |
sim | -0.021 |
Buchanan | -0.020 |
Cain | -0.020 |
quit | -0.020 |
kitten | -0.020 |
Token | flash |
Token ID | 7644 |
Feature activation | -6.39e-03 |
Pos logit contributions | |
�� | +0.010 |
� | +0.010 |
dra | +0.010 |
� | +0.010 |
srf | +0.010 |
Neg logit contributions | |
sim | -0.006 |
shame | -0.005 |
quit | -0.005 |
kitten | -0.005 |
Cain | -0.005 |
Token | them |
Token ID | 606 |
Feature activation | +3.13e-03 |
Pos logit contributions | |
sim | +0.004 |
quit | +0.004 |
shame | +0.004 |
Cain | +0.003 |
kitten | +0.003 |
Neg logit contributions | |
�� | -0.007 |
� | -0.007 |
dra | -0.007 |
�士 | -0.006 |
EStreamFrame | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
�� | +0.004 |
� | +0.004 |
dra | +0.004 |
�士 | +0.003 |
EStreamFrame | +0.003 |
Neg logit contributions | |
sim | -0.002 |
Cain | -0.002 |
shame | -0.002 |
quit | -0.001 |
kitten | -0.001 |
Token | I |
Token ID | 314 |
Feature activation | +7.46e-03 |
Pos logit contributions | |
�� | +0.017 |
srf | +0.017 |
� | +0.016 |
� | +0.016 |
dra | +0.016 |
Neg logit contributions | |
Cain | -0.010 |
Buchanan | -0.010 |
sim | -0.010 |
Kap | -0.010 |
quit | -0.009 |
Token | thought |
Token ID | 1807 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
�� | +0.008 |
� | +0.008 |
� | +0.008 |
dra | +0.008 |
srf | +0.008 |
Neg logit contributions | |
sim | -0.004 |
shame | -0.004 |
quit | -0.004 |
kitten | -0.004 |
Buchanan | -0.004 |
Token | access |
Token ID | 1895 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
�� | +0.030 |
� | +0.030 |
dra | +0.030 |
srf | +0.028 |
� | +0.028 |
Neg logit contributions | |
sim | -0.017 |
Cain | -0.017 |
Buchanan | -0.017 |
shame | -0.017 |
kitten | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
�� | +0.040 |
dra | +0.040 |
� | +0.039 |
srf | +0.037 |
EStreamFrame | +0.037 |
Neg logit contributions | |
sim | -0.019 |
Buchanan | -0.018 |
quit | -0.018 |
kitten | -0.018 |
Cain | -0.018 |
Token | information |
Token ID | 1321 |
Feature activation | +5.88e-02 |
Pos logit contributions | |
�� | +0.016 |
� | +0.015 |
dra | +0.015 |
srf | +0.014 |
� | +0.014 |
Neg logit contributions | |
sim | -0.010 |
Buchanan | -0.010 |
Cain | -0.010 |
kitten | -0.010 |
shame | -0.010 |
Token | would |
Token ID | 561 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
�� | +0.063 |
dra | +0.063 |
� | +0.062 |
EStreamFrame | +0.059 |
srf | +0.059 |
Neg logit contributions | |
sim | -0.034 |
Buchanan | -0.032 |
kitten | -0.032 |
Cain | -0.032 |
shame | -0.031 |
Token | help |
Token ID | 1037 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
�� | +0.036 |
� | +0.035 |
dra | +0.035 |
� | +0.034 |
�士 | +0.033 |
Neg logit contributions | |
sim | -0.021 |
shame | -0.020 |
kitten | -0.020 |
quit | -0.020 |
Cain | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
sim | +0.018 |
Buchanan | +0.017 |
kitten | +0.017 |
Cain | +0.017 |
quit | +0.017 |
Neg logit contributions | |
dra | -0.027 |
�� | -0.027 |
� | -0.027 |
�士 | -0.025 |
srf | -0.024 |
Token | following |
Token ID | 1708 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
� | +0.029 |
�� | +0.029 |
dra | +0.029 |
�士 | +0.027 |
� | +0.027 |
Neg logit contributions | |
sim | -0.019 |
kitten | -0.018 |
Buchanan | -0.018 |
Cain | -0.018 |
quit | -0.017 |
Token | convention |
Token ID | 9831 |
Feature activation | -2.94e-02 |
Pos logit contributions | |
sim | +0.014 |
kitten | +0.013 |
Cain | +0.013 |
Buchanan | +0.013 |
shame | +0.013 |
Neg logit contributions | |
�� | -0.020 |
� | -0.020 |
dra | -0.020 |
� | -0.019 |
�士 | -0.019 |
Token | : |
Token ID | 25 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
sim | +0.016 |
quit | +0.015 |
kitten | +0.015 |
Buchanan | +0.014 |
Cain | +0.014 |
Neg logit contributions | |
� | -0.032 |
�� | -0.032 |
dra | -0.032 |
�士 | -0.030 |
srf | -0.030 |
Token | The |
Token ID | 383 |
Feature activation | +3.29e-02 |
Pos logit contributions | |
� | +0.023 |
�� | +0.023 |
dra | +0.023 |
�士 | +0.022 |
srf | +0.021 |
Neg logit contributions | |
sim | -0.012 |
Buchanan | -0.011 |
kitten | -0.011 |
quit | -0.011 |
Cain | -0.011 |
Token | Snap |
Token ID | 16026 |
Feature activation | -7.33e-03 |
Pos logit contributions | |
� | +0.039 |
�� | +0.038 |
dra | +0.038 |
�士 | +0.036 |
� | +0.035 |
Neg logit contributions | |
sim | -0.016 |
kitten | -0.015 |
Buchanan | -0.015 |
Cain | -0.014 |
quit | -0.014 |
Token | technology |
Token ID | 3037 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
sim | +0.005 |
Buchanan | +0.005 |
kitten | +0.005 |
quit | +0.005 |
keley | +0.004 |
Neg logit contributions | |
� | -0.007 |
�� | -0.007 |
dra | -0.007 |
�士 | -0.007 |
srf | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
� | +0.021 |
�� | +0.021 |
dra | +0.020 |
�士 | +0.019 |
srf | +0.019 |
Neg logit contributions | |
sim | -0.012 |
kitten | -0.011 |
Buchanan | -0.011 |
Cain | -0.011 |
quit | -0.011 |
Token | general |
Token ID | 2276 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
�� | +0.027 |
dra | +0.027 |
� | +0.027 |
�士 | +0.025 |
srf | +0.024 |
Neg logit contributions | |
sim | -0.018 |
Buchanan | -0.018 |
kitten | -0.017 |
quit | -0.017 |
keley | -0.017 |
Token | will |
Token ID | 481 |
Feature activation | +5.80e-03 |
Pos logit contributions | |
sim | +0.007 |
kitten | +0.006 |
Buchanan | +0.006 |
quit | +0.006 |
Cain | +0.006 |
Neg logit contributions | |
�� | -0.013 |
� | -0.013 |
dra | -0.012 |
srf | -0.012 |
� | -0.012 |
Token | be |
Token ID | 307 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
�� | +0.006 |
� | +0.006 |
dra | +0.006 |
�士 | +0.006 |
� | +0.006 |
Neg logit contributions | |
sim | -0.004 |
kitten | -0.003 |
shame | -0.003 |
quit | -0.003 |
Buchanan | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
�� | +0.017 |
srf | +0.017 |
� | +0.017 |
dra | +0.016 |
� | +0.016 |
Neg logit contributions | |
Buchanan | -0.011 |
Cain | -0.011 |
Kap | -0.011 |
sim | -0.011 |
quit | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
� | +0.027 |
� | +0.026 |
� | +0.026 |
srf | +0.026 |
�� | +0.026 |
Neg logit contributions | |
sim | -0.007 |
Buchanan | -0.007 |
quit | -0.007 |
Cain | -0.006 |
Kap | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
� | +0.023 |
dra | +0.023 |
�� | +0.023 |
EF | +0.021 |
EStreamFrame | +0.021 |
Neg logit contributions | |
sim | -0.019 |
Buchanan | -0.018 |
Cain | -0.018 |
kitten | -0.018 |
quit | -0.018 |
Token | They |
Token ID | 2990 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
srf | +0.013 |
� | +0.013 |
� | +0.013 |
� | +0.013 |
�� | +0.013 |
Neg logit contributions | |
quit | -0.010 |
Buchanan | -0.009 |
Cain | -0.009 |
sim | -0.009 |
Kap | -0.009 |
Token | cannot |
Token ID | 2314 |
Feature activation | -7.61e-03 |
Pos logit contributions | |
�� | +0.017 |
� | +0.016 |
dra | +0.016 |
� | +0.015 |
srf | +0.015 |
Neg logit contributions | |
sim | -0.009 |
shame | -0.009 |
Buchanan | -0.008 |
kitten | -0.008 |
quit | -0.008 |
Token | continue |
Token ID | 2555 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
sim | +0.005 |
shame | +0.005 |
kitten | +0.005 |
Buchanan | +0.005 |
spat | +0.004 |
Neg logit contributions | |
�� | -0.008 |
� | -0.008 |
� | -0.008 |
dra | -0.008 |
� | -0.007 |
Token | ruling |
Token ID | 6922 |
Feature activation | -1.49e-02 |
Pos logit contributions | |
�� | +0.031 |
dra | +0.030 |
� | +0.030 |
�士 | +0.028 |
EStreamFrame | +0.028 |
Neg logit contributions | |
sim | -0.014 |
Buchanan | -0.014 |
Cain | -0.013 |
kitten | -0.013 |
shame | -0.013 |
Token | across |
Token ID | 1973 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
sim | +0.008 |
Buchanan | +0.008 |
Cain | +0.008 |
shame | +0.008 |
kitten | +0.008 |
Neg logit contributions | |
�� | -0.016 |
dra | -0.016 |
� | -0.016 |
srf | -0.015 |
� | -0.015 |
Token | this |
Token ID | 428 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
sim | +0.031 |
Buchanan | +0.030 |
Cain | +0.030 |
shame | +0.030 |
quit | +0.029 |
Neg logit contributions | |
dra | -0.052 |
�� | -0.052 |
� | -0.052 |
srf | -0.049 |
EStreamFrame | -0.049 |
Token | area |
Token ID | 1989 |
Feature activation | +1.25e-03 |
Pos logit contributions | |
�� | +0.031 |
dra | +0.031 |
� | +0.031 |
srf | +0.029 |
�士 | +0.029 |
Neg logit contributions | |
sim | -0.016 |
Buchanan | -0.015 |
kitten | -0.015 |
shame | -0.015 |
Cain | -0.014 |
Token | without |
Token ID | 1231 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
�� | +0.001 |
� | +0.001 |
dra | +0.001 |
�士 | +0.001 |
srf | +0.001 |
Neg logit contributions | |
sim | -0.001 |
Buchanan | -0.001 |
shame | -0.001 |
Cain | -0.001 |
kitten | -0.001 |
Token | States |
Token ID | 1829 |
Feature activation | -5.84e-02 |
Pos logit contributions | |
� | +0.015 |
�� | +0.015 |
� | +0.015 |
� | +0.015 |
srf | +0.015 |
Neg logit contributions | |
sim | -0.006 |
Buchanan | -0.006 |
Cain | -0.006 |
Kap | -0.006 |
quit | -0.005 |
Token | may |
Token ID | 743 |
Feature activation | -7.63e-03 |
Pos logit contributions | |
sim | +0.031 |
Cain | +0.029 |
Buchanan | +0.029 |
quit | +0.028 |
shame | +0.028 |
Neg logit contributions | |
�� | -0.067 |
� | -0.066 |
dra | -0.064 |
�士 | -0.064 |
� | -0.062 |
Token | sponsor |
Token ID | 17487 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
sim | +0.004 |
quit | +0.004 |
shame | +0.004 |
kitten | +0.004 |
Cain | +0.004 |
Neg logit contributions | |
�� | -0.008 |
� | -0.008 |
dra | -0.008 |
�士 | -0.008 |
� | -0.008 |
Token | family |
Token ID | 1641 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
dra | +0.046 |
�� | +0.046 |
� | +0.045 |
srf | +0.043 |
�士 | +0.043 |
Neg logit contributions | |
sim | -0.029 |
Cain | -0.027 |
kitten | -0.027 |
Buchanan | -0.026 |
quit | -0.026 |
Token | members |
Token ID | 1866 |
Feature activation | -8.27e-03 |
Pos logit contributions | |
�� | +0.013 |
dra | +0.013 |
� | +0.012 |
�士 | +0.012 |
srf | +0.012 |
Neg logit contributions | |
sim | -0.009 |
quit | -0.008 |
kitten | -0.008 |
Cain | -0.008 |
shame | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
sim | +0.004 |
Cain | +0.004 |
Buchanan | +0.004 |
kitten | +0.004 |
quit | +0.004 |
Neg logit contributions | |
�� | -0.009 |
dra | -0.009 |
� | -0.009 |
�士 | -0.009 |
srf | -0.009 |
Token | follow |
Token ID | 1061 |
Feature activation | -3.30e-03 |
Pos logit contributions | |
dra | +0.019 |
�� | +0.019 |
� | +0.019 |
EStreamFrame | +0.018 |
srf | +0.018 |
Neg logit contributions | |
sim | -0.010 |
Buchanan | -0.010 |
quit | -0.010 |
shame | -0.010 |
Cain | -0.010 |
Token | them |
Token ID | 606 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
sim | +0.002 |
Buchanan | +0.002 |
Cain | +0.002 |
quit | +0.002 |
kitten | +0.002 |
Neg logit contributions | |
dra | -0.003 |
�� | -0.003 |
� | -0.003 |
�士 | -0.003 |
srf | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +5.14e-03 |
Pos logit contributions | |
sim | +0.011 |
Buchanan | +0.011 |
kitten | +0.011 |
Cain | +0.010 |
quit | +0.010 |
Neg logit contributions | |
�� | -0.026 |
� | -0.026 |
dra | -0.025 |
�士 | -0.025 |
� | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +2.52e-03 |
Pos logit contributions | |
�� | +0.005 |
srf | +0.005 |
� | +0.005 |
� | +0.005 |
dra | +0.005 |
Neg logit contributions | |
Cain | -0.004 |
Buchanan | -0.004 |
Kap | -0.003 |
sim | -0.003 |
quit | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +2.25e-03 |
Pos logit contributions | |
� | +0.004 |
� | +0.004 |
srf | +0.004 |
� | +0.004 |
�� | +0.003 |
Neg logit contributions | |
sim | -0.001 |
Buchanan | -0.001 |
quit | -0.001 |
Cain | -0.001 |
Kap | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
� | +0.019 |
dra | +0.019 |
�� | +0.019 |
srf | +0.018 |
�士 | +0.018 |
Neg logit contributions | |
sim | -0.010 |
quit | -0.009 |
Buchanan | -0.009 |
kitten | -0.009 |
Cain | -0.009 |
Token | depicting |
Token ID | 27561 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
sim | +0.007 |
kitten | +0.007 |
Buchanan | +0.007 |
Cain | +0.007 |
shame | +0.007 |
Neg logit contributions | |
dra | -0.013 |
� | -0.013 |
�� | -0.013 |
�士 | -0.012 |
srf | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
dra | +0.020 |
� | +0.020 |
�� | +0.020 |
srf | +0.018 |
EStreamFrame | +0.018 |
Neg logit contributions | |
sim | -0.013 |
Buchanan | -0.012 |
Cain | -0.012 |
kitten | -0.012 |
quit | -0.012 |
Token | storm |
Token ID | 6388 |
Feature activation | -4.74e-02 |
Pos logit contributions | |
�� | +0.018 |
� | +0.018 |
dra | +0.018 |
�士 | +0.017 |
srf | +0.017 |
Neg logit contributions | |
sim | -0.010 |
kitten | -0.010 |
Buchanan | -0.010 |
Cain | -0.010 |
quit | -0.010 |
Token | y |
Token ID | 88 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
sim | +0.029 |
quit | +0.029 |
Buchanan | +0.028 |
kitten | +0.028 |
Cain | +0.027 |
Neg logit contributions | |
�� | -0.048 |
� | -0.047 |
dra | -0.046 |
�士 | -0.044 |
EStreamFrame | -0.044 |
Token | island |
Token ID | 7022 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
�� | +0.011 |
� | +0.011 |
dra | +0.011 |
srf | +0.011 |
�士 | +0.010 |
Neg logit contributions | |
sim | -0.006 |
Buchanan | -0.006 |
kitten | -0.006 |
Cain | -0.006 |
shame | -0.005 |
Token | scene |
Token ID | 3715 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
sim | +0.027 |
quit | +0.025 |
kitten | +0.025 |
Buchanan | +0.025 |
Cain | +0.024 |
Neg logit contributions | |
�� | -0.053 |
� | -0.052 |
dra | -0.052 |
�士 | -0.049 |
srf | -0.049 |
Token | which |
Token ID | 543 |
Feature activation | +5.81e-03 |
Pos logit contributions | |
�� | +0.027 |
dra | +0.027 |
� | +0.027 |
�士 | +0.026 |
srf | +0.025 |
Neg logit contributions | |
sim | -0.014 |
quit | -0.013 |
kitten | -0.013 |
Buchanan | -0.013 |
Cain | -0.013 |
Token | you |
Token ID | 345 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
dra | +0.006 |
�� | +0.006 |
� | +0.006 |
srf | +0.005 |
EStreamFrame | +0.005 |
Neg logit contributions | |
sim | -0.004 |
Buchanan | -0.003 |
kitten | -0.003 |
Cain | -0.003 |
quit | -0.003 |
Token | must |
Token ID | 1276 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
sim | +0.009 |
quit | +0.008 |
kitten | +0.008 |
shame | +0.008 |
Buchanan | +0.008 |
Neg logit contributions | |
�� | -0.016 |
dra | -0.015 |
� | -0.015 |
�士 | -0.014 |
srf | -0.014 |
Token | traverse |
Token ID | 38138 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
�� | +0.011 |
� | +0.010 |
dra | +0.010 |
� | +0.010 |
�士 | +0.010 |
Neg logit contributions | |
sim | -0.007 |
quit | -0.007 |
kitten | -0.007 |
shame | -0.007 |
Buchanan | -0.006 |
Token | Disease |
Token ID | 17344 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
sim | +0.002 |
Buchanan | +0.002 |
Cain | +0.002 |
kitten | +0.002 |
Kap | +0.002 |
Neg logit contributions | |
�� | -0.002 |
� | -0.002 |
dra | -0.002 |
�士 | -0.002 |
srf | -0.002 |
Token | Control |
Token ID | 6779 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
�� | +0.024 |
� | +0.023 |
dra | +0.022 |
srf | +0.022 |
� | +0.022 |
Neg logit contributions | |
Cain | -0.026 |
sim | -0.026 |
Buchanan | -0.026 |
kitten | -0.025 |
quit | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
�� | +0.087 |
dra | +0.087 |
� | +0.086 |
srf | +0.080 |
�士 | +0.079 |
Neg logit contributions | |
sim | -0.047 |
Buchanan | -0.046 |
quit | -0.046 |
keley | -0.045 |
kitten | -0.045 |
Token | Prevention |
Token ID | 18313 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
Buchanan | +0.010 |
Cain | +0.010 |
sim | +0.010 |
kitten | +0.010 |
quit | +0.010 |
Neg logit contributions | |
�� | -0.013 |
dra | -0.013 |
� | -0.013 |
srf | -0.012 |
EStreamFrame | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | +2.13e-03 |
Pos logit contributions | |
�� | +0.013 |
dra | +0.013 |
� | +0.013 |
srf | +0.012 |
�士 | +0.012 |
Neg logit contributions | |
sim | -0.007 |
quit | -0.006 |
Buchanan | -0.006 |
kitten | -0.006 |
keley | -0.006 |
Token | Atlanta |
Token ID | 9371 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
�� | +0.002 |
dra | +0.002 |
� | +0.002 |
srf | +0.002 |
EStreamFrame | +0.002 |
Neg logit contributions | |
sim | -0.001 |
Buchanan | -0.001 |
Cain | -0.001 |
Kap | -0.001 |
shame | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e-03 |
Pos logit contributions | |
sim | +0.026 |
quit | +0.025 |
Buchanan | +0.025 |
keley | +0.024 |
Cain | +0.024 |
Neg logit contributions | |
�� | -0.061 |
dra | -0.060 |
� | -0.060 |
srf | -0.056 |
�士 | -0.056 |
Token | Georgia |
Token ID | 7859 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
�� | +0.002 |
� | +0.002 |
dra | +0.002 |
EStreamFrame | +0.002 |
�士 | +0.002 |
Neg logit contributions | |
sim | -0.001 |
Buchanan | -0.001 |
Cain | -0.001 |
shame | -0.001 |
Kap | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +5.81e-03 |
Pos logit contributions | |
� | +0.018 |
dra | +0.018 |
�� | +0.017 |
srf | +0.016 |
�士 | +0.016 |
Neg logit contributions | |
sim | -0.011 |
quit | -0.011 |
Buchanan | -0.011 |
kitten | -0.011 |
Cain | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -5.67e-03 |
Pos logit contributions | |
�� | +0.007 |
dra | +0.007 |
� | +0.007 |
srf | +0.006 |
EStreamFrame | +0.006 |
Neg logit contributions | |
sim | -0.003 |
Buchanan | -0.003 |
quit | -0.003 |
kitten | -0.003 |
Cain | -0.003 |
Token | halt |
Token ID | 17369 |
Feature activation | -2.75e-02 |
Pos logit contributions | |
sim | +0.004 |
shame | +0.003 |
kitten | +0.003 |
quit | +0.003 |
Buchanan | +0.003 |
Neg logit contributions | |
�� | -0.006 |
� | -0.006 |
� | -0.006 |
dra | -0.006 |
srf | -0.006 |
Token | 5 |
Token ID | 20 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
sim | +0.062 |
Buchanan | +0.060 |
keley | +0.059 |
quit | +0.058 |
kitten | +0.058 |
Neg logit contributions | |
� | -0.100 |
�� | -0.099 |
dra | -0.098 |
srf | -0.092 |
EStreamFrame | -0.092 |
Token | X |
Token ID | 55 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
sim | +0.034 |
Buchanan | +0.030 |
kitten | +0.030 |
Cain | +0.030 |
shame | +0.030 |
Neg logit contributions | |
� | -0.055 |
�� | -0.053 |
dra | -0.053 |
srf | -0.050 |
EStreamFrame | -0.050 |
Token | memory |
Token ID | 4088 |
Feature activation | -9.08e-02 |
Pos logit contributions | |
sim | +0.066 |
Buchanan | +0.061 |
kitten | +0.059 |
shame | +0.058 |
Cain | +0.058 |
Neg logit contributions | |
� | -0.108 |
dra | -0.106 |
�� | -0.105 |
srf | -0.100 |
�士 | -0.100 |
Token | offers |
Token ID | 4394 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
sim | +0.057 |
Buchanan | +0.053 |
kitten | +0.053 |
Cain | +0.052 |
shame | +0.051 |
Neg logit contributions | |
�� | -0.094 |
� | -0.094 |
dra | -0.092 |
srf | -0.088 |
�士 | -0.088 |
Token | a |
Token ID | 257 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
sim | +0.025 |
Buchanan | +0.023 |
Cain | +0.023 |
shame | +0.022 |
kitten | +0.022 |
Neg logit contributions | |
dra | -0.041 |
� | -0.041 |
�� | -0.041 |
srf | -0.038 |
EStreamFrame | -0.038 |
Token | huge |
Token ID | 3236 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
sim | +0.025 |
Buchanan | +0.024 |
Cain | +0.023 |
kitten | +0.023 |
shame | +0.023 |
Neg logit contributions | |
dra | -0.039 |
� | -0.039 |
�� | -0.038 |
�士 | -0.037 |
� | -0.036 |
Token | step |
Token ID | 2239 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
sim | +0.047 |
Buchanan | +0.045 |
Cain | +0.044 |
kitten | +0.044 |
shame | +0.043 |
Neg logit contributions | |
� | -0.074 |
dra | -0.072 |
�� | -0.071 |
�士 | -0.068 |
srf | -0.067 |
Token | up |
Token ID | 510 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
sim | +0.056 |
Buchanan | +0.053 |
quit | +0.052 |
kitten | +0.052 |
Cain | +0.052 |
Neg logit contributions | |
�� | -0.122 |
� | -0.122 |
dra | -0.121 |
�士 | -0.115 |
EStreamFrame | -0.113 |
Token | in |
Token ID | 287 |
Feature activation | -5.04e-02 |
Pos logit contributions | |
sim | +0.033 |
Buchanan | +0.032 |
quit | +0.031 |
kitten | +0.031 |
Cain | +0.031 |
Neg logit contributions | |
dra | -0.073 |
� | -0.073 |
�� | -0.073 |
�士 | -0.068 |
srf | -0.068 |
Token | bandwidth |
Token ID | 19484 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
sim | +0.030 |
Buchanan | +0.028 |
kitten | +0.027 |
keley | +0.027 |
Cain | +0.027 |
Neg logit contributions | |
dra | -0.053 |
� | -0.053 |
�� | -0.052 |
�士 | -0.049 |
srf | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
sim | +0.058 |
kitten | +0.054 |
Buchanan | +0.053 |
Cain | +0.053 |
quit | +0.052 |
Neg logit contributions | |
� | -0.122 |
�� | -0.121 |
dra | -0.120 |
�士 | -0.115 |
srf | -0.113 |
Token | Iranian |
Token ID | 10704 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
sim | +0.013 |
Buchanan | +0.013 |
kitten | +0.012 |
quit | +0.012 |
shame | +0.012 |
Neg logit contributions | |
�� | -0.027 |
dra | -0.027 |
� | -0.026 |
srf | -0.025 |
EStreamFrame | -0.025 |
Token | missiles |
Token ID | 12798 |
Feature activation | -4.71e-02 |
Pos logit contributions | |
sim | +0.008 |
quit | +0.007 |
Buchanan | +0.007 |
kitten | +0.007 |
shame | +0.007 |
Neg logit contributions | |
�� | -0.017 |
dra | -0.017 |
� | -0.017 |
srf | -0.016 |
EStreamFrame | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
sim | +0.026 |
quit | +0.025 |
Buchanan | +0.025 |
Cain | +0.025 |
kitten | +0.024 |
Neg logit contributions | |
�� | -0.050 |
dra | -0.050 |
� | -0.050 |
�士 | -0.047 |
srf | -0.046 |
Token | Mr |
Token ID | 1770 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
�� | +0.013 |
srf | +0.013 |
dra | +0.013 |
� | +0.012 |
� | +0.012 |
Neg logit contributions | |
Buchanan | -0.008 |
Cain | -0.008 |
sim | -0.008 |
Kap | -0.008 |
quit | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
� | +0.021 |
srf | +0.020 |
�� | +0.020 |
� | +0.020 |
� | +0.020 |
Neg logit contributions | |
Buchanan | -0.007 |
Cain | -0.007 |
sim | -0.007 |
quit | -0.006 |
Kap | -0.006 |
Token | Ahmad |
Token ID | 24152 |
Feature activation | -5.73e-02 |
Pos logit contributions | |
sim | +0.006 |
Buchanan | +0.006 |
Cain | +0.006 |
quit | +0.006 |
kitten | +0.006 |
Neg logit contributions | |
dra | -0.014 |
�� | -0.014 |
� | -0.014 |
srf | -0.013 |
EStreamFrame | -0.013 |
Token | ine |
Token ID | 500 |
Feature activation | +6.13e-02 |
Pos logit contributions | |
keley | +0.030 |
sim | +0.030 |
quit | +0.029 |
Buchanan | +0.028 |
Cain | +0.028 |
Neg logit contributions | |
� | -0.067 |
�� | -0.067 |
� | -0.066 |
srf | -0.065 |
� | -0.065 |
Token | jad |
Token ID | 38442 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
� | +0.093 |
�� | +0.092 |
� | +0.092 |
� | +0.091 |
srf | +0.090 |
Neg logit contributions | |
quit | -0.012 |
keley | -0.012 |
sim | -0.011 |
Buchanan | -0.010 |
Cain | -0.009 |
Token | made |
Token ID | 925 |
Feature activation | +3.85e-02 |
Pos logit contributions | |
sim | +0.021 |
Buchanan | +0.019 |
quit | +0.019 |
Cain | +0.019 |
kitten | +0.019 |
Neg logit contributions | |
�� | -0.036 |
dra | -0.036 |
� | -0.036 |
srf | -0.034 |
� | -0.033 |
Token | no |
Token ID | 645 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
dra | +0.039 |
�� | +0.039 |
� | +0.038 |
srf | +0.036 |
EStreamFrame | +0.036 |
Neg logit contributions | |
sim | -0.024 |
Buchanan | -0.023 |
Cain | -0.023 |
kitten | -0.023 |
shame | -0.022 |
Token | mention |
Token ID | 3068 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
sim | +0.017 |
Buchanan | +0.016 |
Cain | +0.016 |
kitten | +0.016 |
quit | +0.016 |
Neg logit contributions | |
dra | -0.023 |
�� | -0.023 |
� | -0.022 |
srf | -0.022 |
EStreamFrame | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -6.16e-02 |
Pos logit contributions | |
�� | +0.007 |
dra | +0.007 |
� | +0.007 |
�士 | +0.007 |
srf | +0.007 |
Neg logit contributions | |
sim | -0.003 |
quit | -0.003 |
Buchanan | -0.003 |
kitten | -0.003 |
keley | -0.003 |
Token | Kick |
Token ID | 10279 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
sim | +0.037 |
Buchanan | +0.037 |
Cain | +0.036 |
Kap | +0.035 |
quit | +0.035 |
Neg logit contributions | |
�� | -0.066 |
srf | -0.063 |
dra | -0.062 |
� | -0.061 |
� | -0.060 |
Token | Off |
Token ID | 3242 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
�� | +0.013 |
dra | +0.013 |
� | +0.013 |
srf | +0.012 |
�士 | +0.012 |
Neg logit contributions | |
sim | -0.007 |
quit | -0.006 |
Buchanan | -0.006 |
Kap | -0.006 |
kitten | -0.006 |
Token | will |
Token ID | 481 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
sim | +0.021 |
Buchanan | +0.021 |
kitten | +0.020 |
quit | +0.020 |
Kap | +0.020 |
Neg logit contributions | |
�� | -0.041 |
dra | -0.040 |
� | -0.040 |
�士 | -0.038 |
srf | -0.038 |
Token | be |
Token ID | 307 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
sim | +0.030 |
kitten | +0.028 |
quit | +0.028 |
Buchanan | +0.028 |
shame | +0.027 |
Neg logit contributions | |
�� | -0.051 |
� | -0.050 |
dra | -0.050 |
�士 | -0.047 |
srf | -0.047 |
Token | at |
Token ID | 379 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
sim | +0.015 |
Buchanan | +0.014 |
kitten | +0.014 |
Cain | +0.014 |
quit | +0.013 |
Neg logit contributions | |
�� | -0.035 |
dra | -0.034 |
� | -0.033 |
�士 | -0.032 |
srf | -0.032 |
Token | midnight |
Token ID | 15896 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
sim | +0.024 |
Buchanan | +0.024 |
Cain | +0.023 |
Kap | +0.023 |
quit | +0.022 |
Neg logit contributions | |
�� | -0.048 |
dra | -0.047 |
� | -0.045 |
srf | -0.044 |
� | -0.044 |
Token | ! |
Token ID | 0 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
sim | +0.016 |
Buchanan | +0.015 |
quit | +0.015 |
kitten | +0.014 |
Cain | +0.014 |
Neg logit contributions | |
�� | -0.038 |
dra | -0.038 |
� | -0.037 |
�士 | -0.036 |
srf | -0.036 |
Token | ( |
Token ID | 357 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
sim | +0.047 |
Buchanan | +0.046 |
quit | +0.045 |
Cain | +0.044 |
Kap | +0.044 |
Neg logit contributions | |
�� | -0.094 |
dra | -0.091 |
� | -0.090 |
srf | -0.088 |
�士 | -0.086 |
Token | Bring |
Token ID | 31416 |
Feature activation | -3.86e-02 |
Pos logit contributions | |
quit | +0.035 |
sim | +0.035 |
kitten | +0.033 |
shame | +0.033 |
keley | +0.033 |
Neg logit contributions | |
�� | -0.044 |
� | -0.041 |
dra | -0.041 |
srf | -0.040 |
�士 | -0.039 |
Token | your |
Token ID | 534 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
sim | +0.021 |
Cain | +0.020 |
Buchanan | +0.020 |
shame | +0.020 |
kitten | +0.020 |
Neg logit contributions | |
�� | -0.042 |
dra | -0.041 |
� | -0.041 |
srf | -0.039 |
�士 | -0.039 |
Token | up |
Token ID | 510 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
sim | +0.014 |
Buchanan | +0.013 |
shame | +0.013 |
Cain | +0.013 |
spat | +0.013 |
Neg logit contributions | |
�� | -0.034 |
� | -0.033 |
dra | -0.033 |
srf | -0.032 |
�士 | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | +1.10e-03 |
Pos logit contributions | |
sim | +0.008 |
Buchanan | +0.008 |
Cain | +0.008 |
shame | +0.008 |
quit | +0.008 |
Neg logit contributions | |
�� | -0.020 |
� | -0.020 |
dra | -0.019 |
�士 | -0.019 |
srf | -0.019 |
Token | leave |
Token ID | 2666 |
Feature activation | -9.36e-03 |
Pos logit contributions | |
�� | +0.001 |
� | +0.001 |
dra | +0.001 |
� | +0.001 |
srf | +0.001 |
Neg logit contributions | |
sim | -0.001 |
quit | -0.001 |
shame | -0.001 |
kitten | -0.001 |
Buchanan | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -3.63e-02 |
Pos logit contributions | |
sim | +0.005 |
Cain | +0.005 |
Buchanan | +0.005 |
quit | +0.005 |
shame | +0.005 |
Neg logit contributions | |
�� | -0.010 |
� | -0.010 |
dra | -0.010 |
srf | -0.010 |
�士 | -0.010 |
Token | tri |
Token ID | 1333 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
Cain | +0.021 |
sim | +0.021 |
Buchanan | +0.021 |
quit | +0.021 |
shame | +0.020 |
Neg logit contributions | |
�� | -0.039 |
� | -0.038 |
dra | -0.037 |
� | -0.037 |
srf | -0.037 |
Token | pped |
Token ID | 1496 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
quit | +0.013 |
keley | +0.013 |
sim | +0.012 |
Buchanan | +0.012 |
spat | +0.012 |
Neg logit contributions | |
�� | -0.040 |
� | -0.039 |
srf | -0.038 |
dra | -0.038 |
� | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
sim | +0.119 |
Buchanan | +0.116 |
Cain | +0.115 |
shame | +0.113 |
quit | +0.112 |
Neg logit contributions | |
�� | -0.274 |
� | -0.268 |
dra | -0.267 |
srf | -0.257 |
EStreamFrame | -0.256 |
Token | falling |
Token ID | 7463 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
sim | +0.012 |
Cain | +0.012 |
Buchanan | +0.012 |
shame | +0.011 |
quit | +0.011 |
Neg logit contributions | |
�� | -0.023 |
� | -0.022 |
dra | -0.022 |
EStreamFrame | -0.021 |
srf | -0.021 |
Token | backwards |
Token ID | 16196 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
sim | +0.006 |
Buchanan | +0.006 |
shame | +0.006 |
kitten | +0.006 |
Cain | +0.006 |
Neg logit contributions | |
�� | -0.015 |
� | -0.014 |
dra | -0.014 |
srf | -0.013 |
EStreamFrame | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | -2.62e-02 |
Pos logit contributions | |
sim | +0.012 |
Buchanan | +0.012 |
shame | +0.011 |
Cain | +0.011 |
kitten | +0.011 |
Neg logit contributions | |
�� | -0.030 |
� | -0.030 |
dra | -0.029 |
srf | -0.028 |
EStreamFrame | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
sim | +0.016 |
Buchanan | +0.016 |
Cain | +0.016 |
quit | +0.015 |
kitten | +0.015 |
Neg logit contributions | |
�� | -0.026 |
� | -0.026 |
dra | -0.026 |
srf | -0.024 |
EStreamFrame | -0.024 |
Token | as |
Token ID | 355 |
Feature activation | -4.98e-02 |
Pos logit contributions | |
dra | +0.062 |
�� | +0.062 |
� | +0.062 |
srf | +0.057 |
�士 | +0.057 |
Neg logit contributions | |
sim | -0.032 |
Buchanan | -0.032 |
quit | -0.031 |
Cain | -0.031 |
keley | -0.031 |
Token | an |
Token ID | 281 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
sim | +0.028 |
Buchanan | +0.028 |
Cain | +0.028 |
kitten | +0.027 |
keley | +0.027 |
Neg logit contributions | |
dra | -0.052 |
� | -0.052 |
�� | -0.052 |
srf | -0.049 |
EStreamFrame | -0.048 |
Token | " |
Token ID | 366 |
Feature activation | -6.66e-02 |
Pos logit contributions | |
sim | +0.038 |
Cain | +0.037 |
Buchanan | +0.037 |
Kap | +0.036 |
shame | +0.036 |
Neg logit contributions | |
�� | -0.063 |
dra | -0.062 |
� | -0.061 |
srf | -0.060 |
EStreamFrame | -0.059 |
Token | ex |
Token ID | 1069 |
Feature activation | -8.72e-02 |
Pos logit contributions | |
quit | +0.043 |
keley | +0.042 |
sim | +0.042 |
Cain | +0.041 |
Buchanan | +0.040 |
Neg logit contributions | |
�� | -0.066 |
srf | -0.063 |
� | -0.063 |
dra | -0.061 |
-+-+ | -0.061 |
Token | empl |
Token ID | 18856 |
Feature activation | +3.16e-02 |
Pos logit contributions | |
sim | +0.077 |
quit | +0.076 |
Buchanan | +0.076 |
kitten | +0.075 |
keley | +0.074 |
Neg logit contributions | |
�� | -0.066 |
� | -0.063 |
dra | -0.061 |
srf | -0.059 |
�士 | -0.056 |
Token | ary |
Token ID | 560 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
� | +0.035 |
�� | +0.035 |
dra | +0.034 |
srf | +0.034 |
�士 | +0.033 |
Neg logit contributions | |
sim | -0.016 |
Buchanan | -0.015 |
quit | -0.015 |
keley | -0.015 |
kitten | -0.015 |
Token | " |
Token ID | 1 |
Feature activation | -3.78e-02 |
Pos logit contributions | |
sim | +0.134 |
Buchanan | +0.128 |
Cain | +0.125 |
Kap | +0.123 |
shame | +0.122 |
Neg logit contributions | |
� | -0.249 |
�� | -0.248 |
dra | -0.242 |
srf | -0.241 |
� | -0.238 |
Token | Defense |
Token ID | 5947 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
sim | +0.022 |
Buchanan | +0.022 |
Cain | +0.021 |
Kap | +0.021 |
kitten | +0.020 |
Neg logit contributions | |
� | -0.041 |
�� | -0.041 |
dra | -0.040 |
srf | -0.039 |
� | -0.038 |
Token | secretary |
Token ID | 7705 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
� | +0.026 |
�� | +0.025 |
dra | +0.025 |
EStreamFrame | +0.024 |
srf | +0.024 |
Neg logit contributions | |
sim | -0.021 |
Buchanan | -0.020 |
Cain | -0.020 |
kitten | -0.019 |
quit | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -5.45e-03 |
Pos logit contributions | |
sim | +0.023 |
Buchanan | +0.022 |
Cain | +0.022 |
quit | +0.022 |
kitten | +0.022 |
Neg logit contributions | |
dra | -0.042 |
� | -0.042 |
�� | -0.042 |
srf | -0.039 |
�士 | -0.039 |
Token | calling |
Token ID | 4585 |
Feature activation | -5.20e-03 |
Pos logit contributions | |
sim | +0.004 |
Buchanan | +0.003 |
Cain | +0.003 |
kitten | +0.003 |
shame | +0.003 |
Neg logit contributions | |
�� | -0.005 |
dra | -0.005 |
� | -0.005 |
srf | -0.005 |
�士 | -0.005 |
Token | ple |
Token ID | 1154 |
Feature activation | -9.34e-02 |
Pos logit contributions | |
�� | +0.015 |
dra | +0.015 |
� | +0.015 |
srf | +0.015 |
�士 | +0.014 |
Neg logit contributions | |
sim | -0.008 |
Buchanan | -0.008 |
quit | -0.008 |
Cain | -0.008 |
kitten | -0.008 |
Token | tes |
Token ID | 4879 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
sim | +0.031 |
quit | +0.029 |
Buchanan | +0.026 |
keley | +0.026 |
kitten | +0.023 |
Neg logit contributions | |
�� | -0.128 |
srf | -0.123 |
� | -0.122 |
� | -0.122 |
dra | -0.121 |
Token | glucose |
Token ID | 15701 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
sim | +0.086 |
Buchanan | +0.083 |
kitten | +0.082 |
quit | +0.081 |
Cain | +0.081 |
Neg logit contributions | |
dra | -0.131 |
�� | -0.131 |
� | -0.129 |
�士 | -0.122 |
srf | -0.122 |
Token | and |
Token ID | 290 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
sim | +0.006 |
Buchanan | +0.005 |
quit | +0.005 |
kitten | +0.005 |
shame | +0.005 |
Neg logit contributions | |
�� | -0.012 |
dra | -0.012 |
� | -0.012 |
�士 | -0.011 |
srf | -0.011 |
Token | glyc |
Token ID | 40232 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
sim | +0.019 |
kitten | +0.018 |
Buchanan | +0.018 |
shame | +0.017 |
Cain | +0.017 |
Neg logit contributions | |
�� | -0.028 |
dra | -0.028 |
� | -0.027 |
�士 | -0.026 |
srf | -0.026 |
Token | ogen |
Token ID | 6644 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
sim | +0.015 |
quit | +0.014 |
Buchanan | +0.014 |
Cain | +0.014 |
keley | +0.014 |
Neg logit contributions | |
�� | -0.027 |
dra | -0.026 |
� | -0.026 |
�士 | -0.025 |
srf | -0.025 |
Token | rapidly |
Token ID | 8902 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
sim | +0.131 |
Buchanan | +0.121 |
quit | +0.120 |
kitten | +0.120 |
shame | +0.117 |
Neg logit contributions | |
�� | -0.270 |
dra | -0.269 |
� | -0.264 |
srf | -0.252 |
�士 | -0.252 |
Token | , |
Token ID | 11 |
Feature activation | +2.35e-03 |
Pos logit contributions | |
sim | +0.023 |
quit | +0.022 |
Buchanan | +0.022 |
kitten | +0.021 |
Cain | +0.021 |
Neg logit contributions | |
�� | -0.048 |
dra | -0.048 |
� | -0.048 |
�士 | -0.046 |
srf | -0.046 |
Token | forcing |
Token ID | 10833 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
�� | +0.002 |
dra | +0.002 |
� | +0.002 |
�士 | +0.002 |
� | +0.002 |
Neg logit contributions | |
sim | -0.002 |
Buchanan | -0.001 |
kitten | -0.001 |
Cain | -0.001 |
shame | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -8.53e-03 |
Pos logit contributions | |
sim | +0.010 |
Buchanan | +0.009 |
kitten | +0.009 |
quit | +0.009 |
Cain | +0.009 |
Neg logit contributions | |
�� | -0.016 |
dra | -0.016 |
� | -0.016 |
�士 | -0.015 |
srf | -0.015 |
Token | body |
Token ID | 1767 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
sim | +0.005 |
kitten | +0.004 |
Buchanan | +0.004 |
Cain | +0.004 |
quit | +0.004 |
Neg logit contributions | |
�� | -0.009 |
dra | -0.009 |
� | -0.009 |
srf | -0.009 |
�士 | -0.009 |
Token | quarterbacks |
Token ID | 23643 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
sim | +0.031 |
quit | +0.031 |
Buchanan | +0.031 |
keley | +0.031 |
kitten | +0.031 |
Neg logit contributions | |
� | -0.043 |
dra | -0.043 |
�� | -0.043 |
EStreamFrame | -0.039 |
srf | -0.039 |
Token | ) |
Token ID | 8 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
quit | +0.013 |
keley | +0.013 |
Buchanan | +0.013 |
kitten | +0.012 |
sim | +0.012 |
Neg logit contributions | |
dra | -0.017 |
� | -0.017 |
�� | -0.017 |
EStreamFrame | -0.016 |
srf | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
quit | +0.020 |
keley | +0.020 |
kitten | +0.020 |
sim | +0.020 |
Buchanan | +0.020 |
Neg logit contributions | |
� | -0.029 |
dra | -0.028 |
�� | -0.028 |
EStreamFrame | -0.026 |
#$ | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
sim | +0.011 |
Buchanan | +0.010 |
quit | +0.010 |
Cain | +0.010 |
Kap | +0.010 |
Neg logit contributions | |
� | -0.041 |
� | -0.040 |
srf | -0.040 |
� | -0.040 |
�� | -0.040 |
Token | Br |
Token ID | 9414 |
Feature activation | -1.30e-02 |
Pos logit contributions | |
quit | +0.026 |
sim | +0.025 |
Buchanan | +0.024 |
Cain | +0.024 |
Kap | +0.024 |
Neg logit contributions | |
srf | -0.028 |
�� | -0.027 |
� | -0.027 |
� | -0.027 |
dra | -0.026 |
Token | ady |
Token ID | 4597 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
sim | +0.004 |
quit | +0.004 |
keley | +0.004 |
shame | +0.004 |
spat | +0.003 |
Neg logit contributions | |
�� | -0.018 |
srf | -0.017 |
�士 | -0.017 |
� | -0.017 |
� | -0.017 |
Token | is |
Token ID | 318 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
sim | +0.152 |
quit | +0.145 |
Buchanan | +0.145 |
Cain | +0.144 |
kitten | +0.141 |
Neg logit contributions | |
�� | -0.252 |
dra | -0.251 |
� | -0.247 |
srf | -0.235 |
�士 | -0.232 |
Token | easily |
Token ID | 3538 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
sim | +0.019 |
Buchanan | +0.018 |
Cain | +0.018 |
kitten | +0.017 |
shame | +0.017 |
Neg logit contributions | |
�� | -0.034 |
dra | -0.034 |
� | -0.033 |
srf | -0.031 |
�士 | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -2.08e-02 |
Pos logit contributions | |
sim | +0.007 |
Buchanan | +0.006 |
quit | +0.006 |
Cain | +0.006 |
kitten | +0.006 |
Neg logit contributions | |
dra | -0.010 |
�� | -0.010 |
� | -0.009 |
srf | -0.009 |
�士 | -0.009 |
Token | most |
Token ID | 749 |
Feature activation | +5.49e-03 |
Pos logit contributions | |
sim | +0.012 |
kitten | +0.011 |
Buchanan | +0.011 |
Cain | +0.011 |
shame | +0.011 |
Neg logit contributions | |
�� | -0.023 |
dra | -0.022 |
� | -0.022 |
srf | -0.021 |
�士 | -0.021 |
Token | under |
Token ID | 739 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
�� | +0.005 |
dra | +0.005 |
� | +0.005 |
srf | +0.005 |
EStreamFrame | +0.005 |
Neg logit contributions | |
sim | -0.004 |
Buchanan | -0.004 |
shame | -0.004 |
Cain | -0.004 |
kitten | -0.004 |
Token | worked |
Token ID | 3111 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
sim | +0.002 |
shame | +0.002 |
quit | +0.002 |
Buchanan | +0.002 |
kitten | +0.002 |
Neg logit contributions | |
�� | -0.003 |
� | -0.002 |
dra | -0.002 |
srf | -0.002 |
� | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | -5.34e-02 |
Pos logit contributions | |
sim | +0.005 |
Buchanan | +0.005 |
quit | +0.005 |
kitten | +0.005 |
keley | +0.005 |
Neg logit contributions | |
�� | -0.013 |
dra | -0.013 |
� | -0.013 |
srf | -0.012 |
�士 | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e-03 |
Pos logit contributions | |
sim | +0.034 |
Buchanan | +0.033 |
quit | +0.033 |
Cain | +0.032 |
kitten | +0.032 |
Neg logit contributions | |
�� | -0.053 |
� | -0.053 |
dra | -0.053 |
srf | -0.050 |
�士 | -0.049 |
Token | CDC |
Token ID | 20434 |
Feature activation | +6.75e-02 |
Pos logit contributions | |
Buchanan | +0.001 |
sim | +0.001 |
Cain | +0.001 |
shame | +0.001 |
Kap | +0.001 |
Neg logit contributions | |
� | -0.001 |
dra | -0.001 |
�� | -0.001 |
�士 | -0.001 |
srf | -0.001 |
Token | Guid |
Token ID | 37026 |
Feature activation | +2.99e-03 |
Pos logit contributions | |
�� | +0.076 |
dra | +0.074 |
� | +0.074 |
srf | +0.070 |
�士 | +0.070 |
Neg logit contributions | |
sim | -0.036 |
quit | -0.035 |
Buchanan | -0.034 |
shame | -0.033 |
Cain | -0.033 |
Token | eline |
Token ID | 4470 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
�� | +0.003 |
� | +0.003 |
dra | +0.003 |
�士 | +0.003 |
srf | +0.003 |
Neg logit contributions | |
sim | -0.002 |
Buchanan | -0.002 |
Cain | -0.001 |
keley | -0.001 |
quit | -0.001 |
Token | itself |
Token ID | 2346 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
sim | +0.113 |
Buchanan | +0.107 |
quit | +0.106 |
kitten | +0.106 |
Cain | +0.105 |
Neg logit contributions | |
�� | -0.301 |
dra | -0.298 |
� | -0.296 |
�士 | -0.282 |
srf | -0.280 |
Token | . |
Token ID | 13 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
�� | +0.027 |
dra | +0.027 |
� | +0.027 |
�士 | +0.026 |
srf | +0.025 |
Neg logit contributions | |
sim | -0.013 |
quit | -0.012 |
Buchanan | -0.012 |
kitten | -0.012 |
keley | -0.012 |
Token | They |
Token ID | 1119 |
Feature activation | +2.09e-02 |
Pos logit contributions | |
�� | +0.020 |
srf | +0.019 |
� | +0.019 |
dra | +0.018 |
ailability | +0.018 |
Neg logit contributions | |
Buchanan | -0.015 |
Cain | -0.014 |
Kap | -0.014 |
sim | -0.014 |
quit | -0.013 |
Token | see |
Token ID | 766 |
Feature activation | +5.32e-02 |
Pos logit contributions | |
�� | +0.022 |
dra | +0.021 |
� | +0.020 |
srf | +0.019 |
� | +0.019 |
Neg logit contributions | |
sim | -0.014 |
shame | -0.013 |
quit | -0.013 |
Buchanan | -0.013 |
kitten | -0.013 |
Token | that |
Token ID | 326 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
� | +0.053 |
dra | +0.053 |
�� | +0.053 |
EStreamFrame | +0.049 |
srf | +0.049 |
Neg logit contributions | |
sim | -0.034 |
shame | -0.033 |
Buchanan | -0.033 |
Cain | -0.032 |
kitten | -0.032 |