Token | !" |
Token ID | 2474 |
Feature activation | +1.44e-04 |
Pos logit contributions | |
icia | +0.028 |
icker | +0.028 |
ifying | +0.028 |
basement | +0.027 |
Jessica | +0.025 |
Neg logit contributions | |
pengu | -0.026 |
wo | -0.022 |
monkey | -0.022 |
hipp | -0.021 |
clown | -0.021 |
Token | |
Token ID | 220 |
Feature activation | -6.95e-04 |
Pos logit contributions | |
pengu | +0.000 |
monkey | +0.000 |
wo | +0.000 |
hipp | +0.000 |
clown | +0.000 |
Neg logit contributions | |
ifying | -0.000 |
icia | -0.000 |
basement | -0.000 |
icker | -0.000 |
arse | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e-03 |
Pos logit contributions | |
ifying | +0.001 |
basement | +0.001 |
icia | +0.001 |
icker | +0.001 |
diary | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
monkey | -0.001 |
hipp | -0.001 |
clown | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e-04 |
Pos logit contributions | |
ifying | +0.003 |
basement | +0.003 |
icia | +0.003 |
icker | +0.003 |
diary | +0.002 |
Neg logit contributions | |
pengu | -0.003 |
wo | -0.002 |
monkey | -0.002 |
hipp | -0.002 |
clown | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | +2.74e-03 |
Pos logit contributions | |
icia | +0.000 |
basement | +0.000 |
ifying | +0.000 |
icker | +0.000 |
diary | +0.000 |
Neg logit contributions | |
pengu | -0.000 |
wo | -0.000 |
monkey | -0.000 |
hipp | -0.000 |
clown | -0.000 |
Token | cash |
Token ID | 5003 |
Feature activation | +4.89e-02 |
Pos logit contributions | |
wo | +0.003 |
pengu | +0.003 |
haw | +0.003 |
hipp | +0.003 |
monkey | +0.003 |
Neg logit contributions | |
icia | -0.006 |
diary | -0.005 |
basement | -0.005 |
Jessica | -0.005 |
ifying | -0.005 |
Token | ier |
Token ID | 959 |
Feature activation | +1.40e-03 |
Pos logit contributions | |
pengu | +0.098 |
wo | +0.086 |
hipp | +0.086 |
monkey | +0.080 |
gir | +0.080 |
Neg logit contributions | |
icia | -0.081 |
icker | -0.080 |
ifying | -0.072 |
iper | -0.071 |
Jessica | -0.071 |
Token | smiled |
Token ID | 13541 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
pengu | +0.002 |
wo | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icia | -0.003 |
icker | -0.003 |
Jessica | -0.003 |
iper | -0.002 |
Kelly | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-03 |
Pos logit contributions | |
pengu | +0.014 |
wo | +0.012 |
hipp | +0.012 |
monkey | +0.011 |
clown | +0.011 |
Neg logit contributions | |
ifying | -0.017 |
icia | -0.017 |
icker | -0.017 |
basement | -0.017 |
Jessica | -0.016 |
Token | " |
Token ID | 366 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
icia | +0.006 |
icker | +0.006 |
basement | +0.006 |
ifying | +0.006 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.006 |
monkey | -0.005 |
hipp | -0.005 |
gir | -0.005 |
wo | -0.005 |
Token | That |
Token ID | 2504 |
Feature activation | +1.93e-02 |
Pos logit contributions | |
icia | +0.007 |
icker | +0.007 |
basement | +0.007 |
ifying | +0.007 |
Jessica | +0.007 |
Neg logit contributions | |
pengu | -0.008 |
wo | -0.007 |
hipp | -0.007 |
monkey | -0.007 |
clown | -0.006 |
Token | be |
Token ID | 307 |
Feature activation | +1.83e-02 |
Pos logit contributions | |
pengu | +0.022 |
wo | +0.019 |
hipp | +0.018 |
monkey | +0.018 |
clown | +0.018 |
Neg logit contributions | |
icia | -0.024 |
icker | -0.024 |
basement | -0.024 |
ifying | -0.023 |
Jessica | -0.022 |
Token | two |
Token ID | 734 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
pengu | +0.031 |
monkey | +0.026 |
wo | +0.026 |
hipp | +0.026 |
gir | +0.025 |
Neg logit contributions | |
icker | -0.037 |
basement | -0.037 |
ifying | -0.037 |
icia | -0.036 |
Jessica | -0.034 |
Token | dollars |
Token ID | 5054 |
Feature activation | -4.82e-03 |
Pos logit contributions | |
pengu | +0.024 |
wo | +0.021 |
hipp | +0.020 |
clown | +0.019 |
monkey | +0.019 |
Neg logit contributions | |
icia | -0.022 |
ifying | -0.021 |
icker | -0.021 |
basement | -0.021 |
.' | -0.020 |
Token | ," |
Token ID | 553 |
Feature activation | -3.93e-03 |
Pos logit contributions | |
icia | +0.008 |
ifying | +0.008 |
icker | +0.008 |
basement | +0.008 |
.' | +0.007 |
Neg logit contributions | |
pengu | -0.010 |
wo | -0.008 |
hipp | -0.008 |
monkey | -0.008 |
gir | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +8.45e-03 |
Pos logit contributions | |
icia | +0.009 |
icker | +0.009 |
basement | +0.009 |
ifying | +0.008 |
Jessica | +0.008 |
Neg logit contributions | |
pengu | -0.006 |
wo | -0.005 |
hipp | -0.005 |
monkey | -0.005 |
gir | -0.004 |
Token | cash |
Token ID | 5003 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
pengu | +0.012 |
wo | +0.012 |
haw | +0.011 |
cest | +0.010 |
ge | +0.010 |
Neg logit contributions | |
diary | -0.016 |
basement | -0.016 |
icia | -0.015 |
icker | -0.014 |
drawer | -0.014 |
Token | ier |
Token ID | 959 |
Feature activation | +2.31e-03 |
Pos logit contributions | |
pengu | +0.103 |
hipp | +0.090 |
wo | +0.087 |
clown | +0.086 |
gir | +0.086 |
Neg logit contributions | |
icker | -0.070 |
icia | -0.068 |
iper | -0.061 |
apa | -0.060 |
enna | -0.056 |
Token | said |
Token ID | 531 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
pengu | +0.004 |
wo | +0.003 |
hipp | +0.003 |
monkey | +0.003 |
clown | +0.003 |
Neg logit contributions | |
icia | -0.005 |
icker | -0.004 |
Jessica | -0.004 |
Jennifer | -0.004 |
iper | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e-03 |
Pos logit contributions | |
pengu | +0.019 |
hipp | +0.016 |
monkey | +0.016 |
wo | +0.016 |
clown | +0.016 |
Neg logit contributions | |
basement | -0.021 |
icia | -0.021 |
ifying | -0.021 |
icker | -0.020 |
Kelly | -0.019 |
Token | The |
Token ID | 383 |
Feature activation | -3.10e-03 |
Pos logit contributions | |
icia | +0.004 |
icker | +0.004 |
basement | +0.004 |
ifying | +0.004 |
Jessica | +0.003 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
clown | -0.004 |
Token | bear |
Token ID | 6842 |
Feature activation | -2.84e-03 |
Pos logit contributions | |
icia | +0.006 |
basement | +0.006 |
diary | +0.006 |
ifying | +0.006 |
icker | +0.006 |
Neg logit contributions | |
wo | -0.004 |
pengu | -0.004 |
haw | -0.004 |
hipp | -0.003 |
clown | -0.003 |
Token | back |
Token ID | 736 |
Feature activation | -6.35e-03 |
Pos logit contributions | |
icia | +0.005 |
icker | +0.005 |
basement | +0.005 |
ifying | +0.005 |
Jessica | +0.004 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
clown | -0.004 |
Token | ." |
Token ID | 526 |
Feature activation | -3.85e-04 |
Pos logit contributions | |
icia | +0.013 |
icker | +0.013 |
basement | +0.013 |
ifying | +0.012 |
Kelly | +0.012 |
Neg logit contributions | |
pengu | -0.011 |
monkey | -0.009 |
hipp | -0.009 |
wo | -0.008 |
clown | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -7.80e-04 |
Pos logit contributions | |
icia | +0.001 |
ifying | +0.001 |
basement | +0.001 |
icker | +0.001 |
arse | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
monkey | -0.001 |
hipp | -0.001 |
clown | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +7.59e-04 |
Pos logit contributions | |
icia | +0.001 |
basement | +0.001 |
icker | +0.001 |
ifying | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
clown | -0.001 |
Token | The |
Token ID | 464 |
Feature activation | -6.90e-04 |
Pos logit contributions | |
pengu | +0.001 |
hipp | +0.001 |
wo | +0.001 |
monkey | +0.001 |
gir | +0.001 |
Neg logit contributions | |
icia | -0.002 |
icker | -0.002 |
basement | -0.002 |
ifying | -0.002 |
Jessica | -0.002 |
Token | cash |
Token ID | 5003 |
Feature activation | +4.73e-02 |
Pos logit contributions | |
icia | +0.001 |
basement | +0.001 |
diary | +0.001 |
ifying | +0.001 |
icker | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
haw | -0.001 |
hipp | -0.001 |
roared | -0.001 |
Token | ier |
Token ID | 959 |
Feature activation | +2.28e-03 |
Pos logit contributions | |
pengu | +0.099 |
hipp | +0.088 |
wo | +0.086 |
gir | +0.083 |
monkey | +0.081 |
Neg logit contributions | |
icker | -0.075 |
icia | -0.073 |
basement | -0.066 |
ifying | -0.063 |
Jessica | -0.063 |
Token | looked |
Token ID | 3114 |
Feature activation | +2.82e-04 |
Pos logit contributions | |
pengu | +0.004 |
wo | +0.004 |
hipp | +0.004 |
haw | +0.004 |
monkey | +0.004 |
Neg logit contributions | |
icia | -0.004 |
icker | -0.004 |
Jessica | -0.004 |
Jennifer | -0.004 |
Jessica | -0.003 |
Token | at |
Token ID | 379 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
pengu | +0.001 |
wo | +0.000 |
hipp | +0.000 |
monkey | +0.000 |
gir | +0.000 |
Neg logit contributions | |
icia | -0.000 |
ifying | -0.000 |
icker | -0.000 |
basement | -0.000 |
Jessica | -0.000 |
Token | Sara |
Token ID | 24799 |
Feature activation | +8.70e-03 |
Pos logit contributions | |
pengu | +0.009 |
wo | +0.007 |
hipp | +0.006 |
monkey | +0.006 |
clown | +0.006 |
Neg logit contributions | |
icker | -0.016 |
ifying | -0.016 |
basement | -0.016 |
icia | -0.016 |
arse | -0.015 |
Token | 's |
Token ID | 338 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
pengu | +0.013 |
monkey | +0.011 |
wo | +0.010 |
hipp | +0.010 |
clown | +0.010 |
Neg logit contributions | |
basement | -0.019 |
ifying | -0.019 |
icia | -0.018 |
icker | -0.018 |
Kelly | -0.018 |
Token | It |
Token ID | 632 |
Feature activation | +5.72e-03 |
Pos logit contributions | |
icia | +0.000 |
icker | +0.000 |
basement | +0.000 |
ifying | +0.000 |
Jessica | +0.000 |
Neg logit contributions | |
pengu | -0.000 |
monkey | -0.000 |
wo | -0.000 |
hipp | -0.000 |
gir | -0.000 |
Token | 's |
Token ID | 338 |
Feature activation | -7.39e-03 |
Pos logit contributions | |
pengu | +0.012 |
wo | +0.011 |
hipp | +0.010 |
clown | +0.010 |
monkey | +0.010 |
Neg logit contributions | |
icia | -0.009 |
basement | -0.009 |
ifying | -0.008 |
icker | -0.008 |
Jessica | -0.008 |
Token | fun |
Token ID | 1257 |
Feature activation | -5.73e-03 |
Pos logit contributions | |
icker | +0.016 |
icia | +0.016 |
ifying | +0.016 |
basement | +0.015 |
Jessica | +0.015 |
Neg logit contributions | |
pengu | -0.012 |
monkey | -0.010 |
hipp | -0.009 |
gir | -0.009 |
wo | -0.009 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.74e-04 |
Pos logit contributions | |
icia | +0.011 |
basement | +0.011 |
ifying | +0.011 |
icker | +0.011 |
Jessica | +0.010 |
Neg logit contributions | |
pengu | -0.010 |
wo | -0.009 |
hipp | -0.008 |
monkey | -0.008 |
gir | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | -3.40e-03 |
Pos logit contributions | |
pengu | +0.001 |
monkey | +0.001 |
wo | +0.001 |
hipp | +0.001 |
clown | +0.001 |
Neg logit contributions | |
icia | -0.001 |
ifying | -0.001 |
basement | -0.001 |
icker | -0.001 |
arse | -0.001 |
Token | cash |
Token ID | 5003 |
Feature activation | +4.71e-02 |
Pos logit contributions | |
icia | +0.007 |
ifying | +0.006 |
basement | +0.006 |
slot | +0.006 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.004 |
wo | -0.004 |
haw | -0.004 |
hipp | -0.004 |
ped | -0.003 |
Token | ier |
Token ID | 959 |
Feature activation | +9.66e-04 |
Pos logit contributions | |
pengu | +0.099 |
hipp | +0.086 |
wo | +0.086 |
gir | +0.082 |
monkey | +0.080 |
Neg logit contributions | |
icker | -0.073 |
icia | -0.072 |
iper | -0.063 |
ifying | -0.063 |
basement | -0.062 |
Token | laughed |
Token ID | 13818 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
pengu | +0.002 |
wo | +0.002 |
gorilla | +0.001 |
hipp | +0.001 |
haw | +0.001 |
Neg logit contributions | |
icia | -0.002 |
icker | -0.002 |
Jessica | -0.002 |
Jenna | -0.002 |
Emily | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -3.33e-03 |
Pos logit contributions | |
pengu | +0.020 |
wo | +0.017 |
hipp | +0.017 |
monkey | +0.016 |
gir | +0.016 |
Neg logit contributions | |
icker | -0.022 |
ifying | -0.022 |
icia | -0.022 |
basement | -0.022 |
Jessica | -0.021 |
Token | said |
Token ID | 531 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
icia | +0.007 |
basement | +0.007 |
icker | +0.007 |
ifying | +0.007 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
gir | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
pengu | +0.023 |
wo | +0.021 |
hipp | +0.019 |
monkey | +0.019 |
gir | +0.019 |
Neg logit contributions | |
icker | -0.017 |
ifying | -0.016 |
icia | -0.016 |
Jessica | -0.016 |
basement | -0.016 |
Token | saw |
Token ID | 2497 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
icia | +0.029 |
icker | +0.029 |
basement | +0.029 |
ifying | +0.028 |
Jessica | +0.027 |
Neg logit contributions | |
pengu | -0.021 |
wo | -0.017 |
hipp | -0.017 |
monkey | -0.016 |
clown | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | -7.82e-03 |
Pos logit contributions | |
basement | +0.016 |
icia | +0.016 |
ifying | +0.015 |
icker | +0.015 |
Kelly | +0.014 |
Neg logit contributions | |
pengu | -0.020 |
wo | -0.017 |
hipp | -0.016 |
monkey | -0.016 |
gir | -0.016 |
Token | it |
Token ID | 340 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
icia | +0.014 |
icker | +0.014 |
ifying | +0.014 |
basement | +0.013 |
Jessica | +0.013 |
Neg logit contributions | |
pengu | -0.015 |
hipp | -0.013 |
wo | -0.013 |
monkey | -0.013 |
clown | -0.012 |
Token | had |
Token ID | 550 |
Feature activation | -1.83e-03 |
Pos logit contributions | |
pengu | +0.006 |
wo | +0.005 |
hipp | +0.005 |
monkey | +0.005 |
clown | +0.005 |
Neg logit contributions | |
icia | -0.009 |
ifying | -0.008 |
basement | -0.008 |
icker | -0.008 |
Jessica | -0.008 |
Token | been |
Token ID | 587 |
Feature activation | +7.34e-03 |
Pos logit contributions | |
ifying | +0.003 |
basement | +0.003 |
icia | +0.003 |
icker | +0.003 |
diary | +0.002 |
Neg logit contributions | |
pengu | -0.004 |
wo | -0.003 |
hipp | -0.003 |
monkey | -0.003 |
gir | -0.003 |
Token | che |
Token ID | 1125 |
Feature activation | +4.60e-02 |
Pos logit contributions | |
pengu | +0.014 |
wo | +0.012 |
hipp | +0.012 |
monkey | +0.012 |
gir | +0.012 |
Neg logit contributions | |
icia | -0.013 |
ifying | -0.013 |
basement | -0.012 |
icker | -0.012 |
Jessica | -0.011 |
Token | wed |
Token ID | 19103 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
pengu | +0.092 |
hipp | +0.079 |
monkey | +0.077 |
wo | +0.077 |
clown | +0.075 |
Neg logit contributions | |
icia | -0.081 |
icker | -0.079 |
ifying | -0.078 |
basement | -0.077 |
iper | -0.071 |
Token | up |
Token ID | 510 |
Feature activation | +9.46e-03 |
Pos logit contributions | |
pengu | +0.021 |
hipp | +0.017 |
monkey | +0.017 |
wo | +0.016 |
gir | +0.016 |
Neg logit contributions | |
basement | -0.026 |
icia | -0.026 |
icker | -0.026 |
Jessica | -0.025 |
ifying | -0.024 |
Token | by |
Token ID | 416 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
pengu | +0.016 |
hipp | +0.013 |
monkey | +0.013 |
wo | +0.013 |
clown | +0.012 |
Neg logit contributions | |
icia | -0.020 |
icker | -0.019 |
basement | -0.019 |
ifying | -0.018 |
Jessica | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +6.08e-03 |
Pos logit contributions | |
pengu | +0.020 |
hipp | +0.017 |
wo | +0.017 |
monkey | +0.016 |
clown | +0.016 |
Neg logit contributions | |
icia | -0.018 |
icker | -0.018 |
basement | -0.018 |
ifying | -0.018 |
Jessica | -0.017 |
Token | neighbor |
Token ID | 4780 |
Feature activation | +6.68e-03 |
Pos logit contributions | |
pengu | +0.011 |
monkey | +0.010 |
hipp | +0.010 |
gir | +0.009 |
wo | +0.009 |
Neg logit contributions | |
icia | -0.012 |
icker | -0.011 |
ifying | -0.011 |
basement | -0.011 |
Jessica | -0.011 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.51e-03 |
Pos logit contributions | |
pengu | +0.008 |
wo | +0.007 |
hipp | +0.007 |
monkey | +0.006 |
clown | +0.006 |
Neg logit contributions | |
icia | -0.013 |
icker | -0.013 |
basement | -0.013 |
ifying | -0.013 |
Jessica | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
pengu | +0.004 |
hipp | +0.003 |
monkey | +0.003 |
clown | +0.003 |
wo | +0.003 |
Neg logit contributions | |
ifying | -0.005 |
basement | -0.005 |
icker | -0.005 |
icia | -0.005 |
igsaw | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +2.44e-04 |
Pos logit contributions | |
ifying | +0.004 |
basement | +0.004 |
icia | +0.004 |
icker | +0.004 |
diary | +0.003 |
Neg logit contributions | |
pengu | -0.004 |
hipp | -0.003 |
monkey | -0.003 |
wo | -0.003 |
gir | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +8.50e-04 |
Pos logit contributions | |
pengu | +0.000 |
wo | +0.000 |
hipp | +0.000 |
monkey | +0.000 |
clown | +0.000 |
Neg logit contributions | |
ifying | -0.001 |
basement | -0.000 |
icia | -0.000 |
icker | -0.000 |
diary | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | -2.41e-04 |
Pos logit contributions | |
pengu | +0.002 |
hipp | +0.001 |
wo | +0.001 |
monkey | +0.001 |
clown | +0.001 |
Neg logit contributions | |
ifying | -0.002 |
basement | -0.002 |
icia | -0.002 |
icker | -0.002 |
diary | -0.002 |
Token | cash |
Token ID | 5003 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
icia | +0.001 |
basement | +0.001 |
ifying | +0.001 |
icker | +0.000 |
diary | +0.000 |
Neg logit contributions | |
pengu | -0.000 |
wo | -0.000 |
haw | -0.000 |
hipp | -0.000 |
monkey | -0.000 |
Token | ier |
Token ID | 959 |
Feature activation | -7.86e-04 |
Pos logit contributions | |
pengu | +0.087 |
wo | +0.074 |
hipp | +0.074 |
monkey | +0.071 |
gir | +0.070 |
Neg logit contributions | |
icia | -0.081 |
icker | -0.080 |
ifying | -0.075 |
basement | -0.075 |
Jessica | -0.072 |
Token | said |
Token ID | 531 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
icia | +0.002 |
icker | +0.001 |
Jessica | +0.001 |
Kelly | +0.001 |
Jennifer | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
clown | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -4.91e-04 |
Pos logit contributions | |
pengu | +0.018 |
wo | +0.016 |
hipp | +0.015 |
monkey | +0.015 |
gir | +0.015 |
Neg logit contributions | |
icia | -0.020 |
icker | -0.020 |
basement | -0.019 |
ifying | -0.019 |
Jessica | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -5.74e-03 |
Pos logit contributions | |
basement | +0.001 |
icker | +0.001 |
icia | +0.001 |
ifying | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
wo | -0.001 |
gir | -0.001 |
Token | It |
Token ID | 1026 |
Feature activation | +1.07e-02 |
Pos logit contributions | |
icia | +0.010 |
icker | +0.010 |
basement | +0.010 |
ifying | +0.010 |
Jessica | +0.009 |
Neg logit contributions | |
pengu | -0.011 |
wo | -0.010 |
hipp | -0.009 |
monkey | -0.009 |
clown | -0.009 |
Token | what |
Token ID | 644 |
Feature activation | +8.19e-03 |
Pos logit contributions | |
pengu | +0.007 |
monkey | +0.006 |
hipp | +0.005 |
gir | +0.005 |
wo | +0.005 |
Neg logit contributions | |
icker | -0.008 |
icia | -0.008 |
basement | -0.007 |
ifying | -0.007 |
Jessica | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | +2.18e-03 |
Pos logit contributions | |
pengu | +0.015 |
monkey | +0.012 |
clown | +0.012 |
hipp | +0.012 |
gir | +0.012 |
Neg logit contributions | |
icker | -0.017 |
ifying | -0.016 |
icia | -0.016 |
arse | -0.016 |
basement | -0.016 |
Token | means |
Token ID | 1724 |
Feature activation | -7.87e-03 |
Pos logit contributions | |
pengu | +0.004 |
wo | +0.003 |
monkey | +0.003 |
hipp | +0.003 |
clown | +0.003 |
Neg logit contributions | |
icker | -0.004 |
icia | -0.004 |
ifying | -0.004 |
basement | -0.004 |
Jessica | -0.004 |
Token | ." |
Token ID | 526 |
Feature activation | -1.63e-03 |
Pos logit contributions | |
icker | +0.015 |
icia | +0.015 |
ifying | +0.015 |
basement | +0.015 |
Jessica | +0.014 |
Neg logit contributions | |
pengu | -0.014 |
hipp | -0.012 |
monkey | -0.012 |
clown | -0.011 |
wo | -0.011 |
Token | The |
Token ID | 383 |
Feature activation | -4.74e-04 |
Pos logit contributions | |
ifying | +0.003 |
icia | +0.003 |
basement | +0.003 |
icker | +0.003 |
arse | +0.003 |
Neg logit contributions | |
pengu | -0.003 |
monkey | -0.002 |
hipp | -0.002 |
wo | -0.002 |
clown | -0.002 |
Token | cash |
Token ID | 5003 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
icia | +0.001 |
basement | +0.001 |
diary | +0.001 |
ifying | +0.001 |
icker | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
hipp | -0.000 |
haw | -0.000 |
monkey | -0.000 |
Token | ier |
Token ID | 959 |
Feature activation | +6.36e-04 |
Pos logit contributions | |
pengu | +0.090 |
hipp | +0.077 |
wo | +0.077 |
monkey | +0.072 |
gir | +0.072 |
Neg logit contributions | |
icia | -0.077 |
icker | -0.076 |
ifying | -0.069 |
basement | -0.068 |
iper | -0.068 |
Token | laughed |
Token ID | 13818 |
Feature activation | +1.29e-02 |
Pos logit contributions | |
pengu | +0.001 |
wo | +0.001 |
hipp | +0.001 |
monkey | +0.001 |
haw | +0.001 |
Neg logit contributions | |
icia | -0.001 |
icker | -0.001 |
Jessica | -0.001 |
iper | -0.001 |
Jennifer | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -7.93e-04 |
Pos logit contributions | |
pengu | +0.022 |
wo | +0.018 |
hipp | +0.018 |
monkey | +0.017 |
gir | +0.017 |
Neg logit contributions | |
icia | -0.026 |
icker | -0.026 |
ifying | -0.025 |
basement | -0.025 |
Jessica | -0.024 |
Token | said |
Token ID | 531 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
icia | +0.002 |
icker | +0.002 |
basement | +0.002 |
ifying | +0.002 |
Jessica | +0.002 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
clown | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.56e-03 |
Pos logit contributions | |
pengu | +0.022 |
wo | +0.020 |
hipp | +0.018 |
monkey | +0.018 |
clown | +0.018 |
Neg logit contributions | |
icker | -0.020 |
icia | -0.020 |
basement | -0.019 |
ifying | -0.019 |
Jessica | -0.018 |
Token | ier |
Token ID | 959 |
Feature activation | -9.18e-03 |
Pos logit contributions | |
pengu | +0.050 |
wo | +0.041 |
hipp | +0.041 |
monkey | +0.040 |
gir | +0.039 |
Neg logit contributions | |
icia | -0.056 |
icker | -0.055 |
basement | -0.054 |
ifying | -0.054 |
Jessica | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | -2.59e-03 |
Pos logit contributions | |
icia | +0.018 |
icker | +0.018 |
basement | +0.018 |
ifying | +0.018 |
Jessica | +0.017 |
Neg logit contributions | |
pengu | -0.015 |
wo | -0.013 |
hipp | -0.013 |
monkey | -0.012 |
clown | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e-03 |
Pos logit contributions | |
icia | +0.005 |
basement | +0.005 |
icker | +0.005 |
ifying | +0.005 |
arse | +0.004 |
Neg logit contributions | |
pengu | -0.005 |
monkey | -0.004 |
hipp | -0.004 |
wo | -0.004 |
clown | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +7.51e-04 |
Pos logit contributions | |
pengu | +0.002 |
wo | +0.002 |
monkey | +0.002 |
hipp | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icia | -0.002 |
basement | -0.002 |
ifying | -0.002 |
icker | -0.002 |
arse | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | -1.22e-03 |
Pos logit contributions | |
pengu | +0.002 |
hipp | +0.002 |
wo | +0.002 |
monkey | +0.001 |
gir | +0.001 |
Neg logit contributions | |
icia | -0.001 |
icker | -0.001 |
ifying | -0.001 |
basement | -0.001 |
Jessica | -0.001 |
Token | cash |
Token ID | 5003 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
icia | +0.003 |
basement | +0.002 |
ifying | +0.002 |
icker | +0.002 |
diary | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.001 |
haw | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
Token | ier |
Token ID | 959 |
Feature activation | -9.00e-04 |
Pos logit contributions | |
pengu | +0.092 |
wo | +0.079 |
hipp | +0.079 |
monkey | +0.075 |
gir | +0.074 |
Neg logit contributions | |
icia | -0.075 |
icker | -0.074 |
ifying | -0.067 |
basement | -0.067 |
iper | -0.066 |
Token | said |
Token ID | 531 |
Feature activation | +9.78e-03 |
Pos logit contributions | |
icia | +0.002 |
Jessica | +0.002 |
iper | +0.002 |
icker | +0.002 |
Kelly | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
clown | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
pengu | +0.018 |
wo | +0.015 |
hipp | +0.015 |
monkey | +0.015 |
gir | +0.014 |
Neg logit contributions | |
icia | -0.018 |
icker | -0.018 |
ifying | -0.018 |
basement | -0.017 |
Jessica | -0.017 |
Token | " |
Token ID | 366 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
icia | +0.004 |
icker | +0.004 |
basement | +0.004 |
ifying | +0.003 |
Jessica | +0.003 |
Neg logit contributions | |
pengu | -0.003 |
wo | -0.002 |
hipp | -0.002 |
monkey | -0.002 |
gir | -0.002 |
Token | You |
Token ID | 1639 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ifying | +0.010 |
icia | +0.010 |
icker | +0.009 |
Jessica | +0.009 |
basement | +0.009 |
Neg logit contributions | |
pengu | -0.012 |
hipp | -0.010 |
monkey | -0.010 |
wo | -0.009 |
gir | -0.009 |
Token | ier |
Token ID | 959 |
Feature activation | -7.24e-03 |
Pos logit contributions | |
pengu | +0.051 |
wo | +0.042 |
hipp | +0.041 |
monkey | +0.041 |
clown | +0.040 |
Neg logit contributions | |
icia | -0.063 |
basement | -0.062 |
icker | -0.062 |
ifying | -0.062 |
Jessica | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -5.25e-03 |
Pos logit contributions | |
icker | +0.014 |
icia | +0.014 |
basement | +0.014 |
ifying | +0.014 |
Jessica | +0.013 |
Neg logit contributions | |
pengu | -0.013 |
monkey | -0.010 |
hipp | -0.010 |
wo | -0.010 |
clown | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-04 |
Pos logit contributions | |
icia | +0.010 |
basement | +0.010 |
icker | +0.009 |
ifying | +0.009 |
arse | +0.009 |
Neg logit contributions | |
pengu | -0.010 |
monkey | -0.008 |
hipp | -0.008 |
wo | -0.008 |
clown | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +2.31e-05 |
Pos logit contributions | |
pengu | +0.000 |
wo | +0.000 |
monkey | +0.000 |
hipp | +0.000 |
clown | +0.000 |
Neg logit contributions | |
icia | -0.000 |
basement | -0.000 |
ifying | -0.000 |
icker | -0.000 |
diary | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | -7.75e-04 |
Pos logit contributions | |
pengu | +0.000 |
hipp | +0.000 |
wo | +0.000 |
monkey | +0.000 |
gir | +0.000 |
Neg logit contributions | |
icia | -0.000 |
icker | -0.000 |
ifying | -0.000 |
basement | -0.000 |
Jessica | -0.000 |
Token | cash |
Token ID | 5003 |
Feature activation | +4.51e-02 |
Pos logit contributions | |
icia | +0.002 |
basement | +0.002 |
ifying | +0.002 |
icker | +0.002 |
diary | +0.002 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
hipp | -0.001 |
haw | -0.001 |
monkey | -0.001 |
Token | ier |
Token ID | 959 |
Feature activation | -6.94e-04 |
Pos logit contributions | |
pengu | +0.090 |
wo | +0.079 |
hipp | +0.078 |
monkey | +0.073 |
gir | +0.072 |
Neg logit contributions | |
icia | -0.077 |
icker | -0.075 |
ifying | -0.069 |
basement | -0.068 |
iper | -0.067 |
Token | said |
Token ID | 531 |
Feature activation | +8.93e-03 |
Pos logit contributions | |
icia | +0.001 |
Jessica | +0.001 |
icker | +0.001 |
iper | +0.001 |
Kelly | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
clown | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -3.41e-03 |
Pos logit contributions | |
pengu | +0.016 |
wo | +0.014 |
hipp | +0.013 |
monkey | +0.013 |
gir | +0.013 |
Neg logit contributions | |
icia | -0.016 |
ifying | -0.016 |
icker | -0.016 |
basement | -0.016 |
Jessica | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
icia | +0.007 |
basement | +0.007 |
icker | +0.007 |
ifying | +0.007 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.006 |
wo | -0.005 |
hipp | -0.005 |
monkey | -0.005 |
gir | -0.005 |
Token | What |
Token ID | 2061 |
Feature activation | +1.75e-02 |
Pos logit contributions | |
ifying | +0.010 |
icia | +0.010 |
icker | +0.009 |
Jessica | +0.009 |
basement | +0.009 |
Neg logit contributions | |
pengu | -0.011 |
hipp | -0.010 |
monkey | -0.009 |
wo | -0.009 |
clown | -0.009 |
Token | own |
Token ID | 898 |
Feature activation | +9.62e-03 |
Pos logit contributions | |
pengu | +0.039 |
monkey | +0.032 |
clown | +0.032 |
hipp | +0.032 |
gir | +0.032 |
Neg logit contributions | |
basement | -0.033 |
ifying | -0.032 |
Kelly | -0.031 |
icia | -0.031 |
icker | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -6.88e-03 |
Pos logit contributions | |
pengu | +0.016 |
hipp | +0.013 |
clown | +0.013 |
monkey | +0.013 |
wo | +0.013 |
Neg logit contributions | |
icker | -0.019 |
basement | -0.019 |
icia | -0.019 |
ifying | -0.018 |
Kelly | -0.018 |
Token | From |
Token ID | 3574 |
Feature activation | -3.49e-04 |
Pos logit contributions | |
icker | +0.014 |
basement | +0.014 |
ifying | +0.014 |
icia | +0.014 |
arse | +0.014 |
Neg logit contributions | |
pengu | -0.011 |
monkey | -0.009 |
wo | -0.008 |
clown | -0.008 |
hipp | -0.008 |
Token | then |
Token ID | 788 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
icker | +0.001 |
basement | +0.001 |
ifying | +0.001 |
icia | +0.001 |
arse | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
hipp | -0.000 |
monkey | -0.000 |
clown | -0.000 |
wo | -0.000 |
Token | on |
Token ID | 319 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
icker | +0.014 |
basement | +0.014 |
icia | +0.014 |
ifying | +0.014 |
Jessica | +0.013 |
Neg logit contributions | |
pengu | -0.011 |
wo | -0.009 |
monkey | -0.009 |
gir | -0.009 |
hipp | -0.008 |
Token | out |
Token ID | 503 |
Feature activation | +4.42e-02 |
Pos logit contributions | |
pengu | +0.017 |
monkey | +0.014 |
hipp | +0.014 |
gir | +0.013 |
clown | +0.013 |
Neg logit contributions | |
icker | -0.024 |
ifying | -0.024 |
basement | -0.024 |
icia | -0.023 |
Jessica | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -6.80e-03 |
Pos logit contributions | |
pengu | +0.079 |
wo | +0.069 |
hipp | +0.066 |
monkey | +0.065 |
gir | +0.063 |
Neg logit contributions | |
icker | -0.080 |
icia | -0.080 |
ifying | -0.080 |
basement | -0.079 |
Jessica | -0.075 |
Token | they |
Token ID | 484 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
ifying | +0.012 |
icker | +0.011 |
basement | +0.011 |
icia | +0.011 |
arse | +0.010 |
Neg logit contributions | |
pengu | -0.014 |
monkey | -0.012 |
clown | -0.011 |
hipp | -0.011 |
wo | -0.011 |
Token | always |
Token ID | 1464 |
Feature activation | -4.36e-03 |
Pos logit contributions | |
basement | +0.030 |
icker | +0.030 |
ifying | +0.029 |
icia | +0.029 |
Jessica | +0.028 |
Neg logit contributions | |
pengu | -0.022 |
hipp | -0.017 |
wo | -0.017 |
monkey | -0.017 |
gir | -0.017 |
Token | chose |
Token ID | 7690 |
Feature activation | +3.29e-03 |
Pos logit contributions | |
icker | +0.010 |
basement | +0.010 |
ifying | +0.010 |
icia | +0.010 |
Jessica | +0.009 |
Neg logit contributions | |
pengu | -0.006 |
hipp | -0.005 |
wo | -0.005 |
monkey | -0.005 |
gir | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -6.09e-03 |
Pos logit contributions | |
pengu | +0.006 |
hipp | +0.005 |
monkey | +0.005 |
wo | +0.005 |
clown | +0.005 |
Neg logit contributions | |
icker | -0.006 |
icia | -0.006 |
basement | -0.006 |
ifying | -0.006 |
arse | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +1.62e-03 |
Pos logit contributions | |
pengu | +0.003 |
hipp | +0.002 |
monkey | +0.002 |
clown | +0.002 |
gir | +0.002 |
Neg logit contributions | |
ifying | -0.003 |
icker | -0.003 |
basement | -0.003 |
icia | -0.003 |
arse | -0.003 |
Token | cash |
Token ID | 5003 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
pengu | +0.003 |
wo | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
haw | +0.002 |
Neg logit contributions | |
basement | -0.003 |
icia | -0.003 |
ifying | -0.003 |
Jessica | -0.003 |
diary | -0.003 |
Token | ier |
Token ID | 959 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
pengu | +0.053 |
wo | +0.044 |
hipp | +0.043 |
monkey | +0.043 |
gir | +0.041 |
Neg logit contributions | |
icia | -0.062 |
icker | -0.062 |
basement | -0.061 |
ifying | -0.061 |
Jessica | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
icker | +0.013 |
ifying | +0.013 |
icia | +0.013 |
basement | +0.013 |
Jessica | +0.012 |
Neg logit contributions | |
pengu | -0.012 |
hipp | -0.010 |
monkey | -0.009 |
wo | -0.009 |
clown | -0.009 |
Token | The |
Token ID | 383 |
Feature activation | -2.56e-03 |
Pos logit contributions | |
icia | +0.003 |
basement | +0.003 |
icker | +0.003 |
ifying | +0.003 |
arse | +0.003 |
Neg logit contributions | |
pengu | -0.003 |
monkey | -0.002 |
hipp | -0.002 |
wo | -0.002 |
gir | -0.002 |
Token | cash |
Token ID | 5003 |
Feature activation | +4.40e-02 |
Pos logit contributions | |
icia | +0.005 |
basement | +0.005 |
ifying | +0.005 |
diary | +0.005 |
Jessica | +0.005 |
Neg logit contributions | |
pengu | -0.004 |
wo | -0.003 |
hipp | -0.003 |
haw | -0.003 |
monkey | -0.003 |
Token | ier |
Token ID | 959 |
Feature activation | -1.81e-03 |
Pos logit contributions | |
pengu | +0.091 |
wo | +0.080 |
hipp | +0.080 |
gir | +0.075 |
monkey | +0.074 |
Neg logit contributions | |
icker | -0.071 |
icia | -0.071 |
basement | -0.064 |
ifying | -0.063 |
iper | -0.063 |
Token | said |
Token ID | 531 |
Feature activation | +7.12e-03 |
Pos logit contributions | |
icia | +0.003 |
Jessica | +0.003 |
icker | +0.003 |
iper | +0.003 |
Kelly | +0.003 |
Neg logit contributions | |
pengu | -0.003 |
wo | -0.003 |
hipp | -0.003 |
monkey | -0.003 |
haw | -0.003 |
Token | they |
Token ID | 484 |
Feature activation | -3.82e-04 |
Pos logit contributions | |
pengu | +0.013 |
wo | +0.011 |
hipp | +0.011 |
monkey | +0.011 |
gir | +0.011 |
Neg logit contributions | |
icia | -0.013 |
icker | -0.013 |
basement | -0.013 |
ifying | -0.013 |
Jessica | -0.012 |
Token | could |
Token ID | 714 |
Feature activation | +1.28e-03 |
Pos logit contributions | |
icia | +0.001 |
basement | +0.001 |
icker | +0.001 |
ifying | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.000 |
hipp | -0.000 |
monkey | -0.000 |
clown | -0.000 |
Token | exchange |
Token ID | 5163 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
pengu | +0.002 |
wo | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icia | -0.002 |
basement | -0.002 |
icker | -0.002 |
ifying | -0.002 |
Jessica | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -4.09e-03 |
Pos logit contributions | |
icker | +0.001 |
icia | +0.001 |
basement | +0.001 |
ifying | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.002 |
hipp | -0.002 |
monkey | -0.002 |
clown | -0.002 |
Token | |
Token ID | 220 |
Feature activation | -2.99e-03 |
Pos logit contributions | |
icia | +0.008 |
icker | +0.008 |
basement | +0.008 |
ifying | +0.008 |
diary | +0.007 |
Neg logit contributions | |
pengu | -0.007 |
monkey | -0.006 |
wo | -0.006 |
hipp | -0.006 |
clown | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.75e-04 |
Pos logit contributions | |
ifying | +0.006 |
basement | +0.006 |
icia | +0.006 |
diary | +0.006 |
icker | +0.006 |
Neg logit contributions | |
pengu | -0.004 |
wo | -0.004 |
monkey | -0.004 |
hipp | -0.003 |
clown | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-04 |
Pos logit contributions | |
ifying | +0.000 |
basement | +0.000 |
icia | +0.000 |
icker | +0.000 |
diary | +0.000 |
Neg logit contributions | |
pengu | -0.000 |
wo | -0.000 |
monkey | -0.000 |
clown | -0.000 |
hipp | -0.000 |
Token | The |
Token ID | 464 |
Feature activation | -1.48e-03 |
Pos logit contributions | |
pengu | +0.000 |
monkey | +0.000 |
wo | +0.000 |
gir | +0.000 |
clown | +0.000 |
Neg logit contributions | |
icker | -0.000 |
basement | -0.000 |
icia | -0.000 |
ifying | -0.000 |
igsaw | -0.000 |
Token | cash |
Token ID | 5003 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
icia | +0.003 |
basement | +0.003 |
ifying | +0.002 |
icker | +0.002 |
diary | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.002 |
haw | -0.002 |
hipp | -0.002 |
clown | -0.002 |
Token | ier |
Token ID | 959 |
Feature activation | -1.06e-03 |
Pos logit contributions | |
pengu | +0.092 |
wo | +0.081 |
hipp | +0.080 |
gir | +0.075 |
monkey | +0.074 |
Neg logit contributions | |
icia | -0.070 |
icker | -0.067 |
basement | -0.061 |
ifying | -0.060 |
iper | -0.059 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.30e-03 |
Pos logit contributions | |
icia | +0.002 |
icker | +0.002 |
Jessica | +0.002 |
Kelly | +0.002 |
Jessica | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
hipp | -0.002 |
wo | -0.002 |
gorilla | -0.002 |
monkey | -0.002 |
Token | Max |
Token ID | 5436 |
Feature activation | +1.52e-03 |
Pos logit contributions | |
icia | +0.004 |
basement | +0.004 |
ifying | +0.004 |
icker | +0.004 |
Jessica | +0.003 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
gir | -0.004 |
Token | spinning |
Token ID | 19493 |
Feature activation | +3.29e-04 |
Pos logit contributions | |
pengu | +0.003 |
wo | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icia | -0.003 |
icker | -0.003 |
basement | -0.003 |
ifying | -0.003 |
Jessica | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +5.38e-03 |
Pos logit contributions | |
pengu | +0.001 |
wo | +0.001 |
hipp | +0.001 |
monkey | +0.001 |
gir | +0.001 |
Neg logit contributions | |
icia | -0.001 |
basement | -0.001 |
ifying | -0.001 |
icker | -0.001 |
Jessica | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +5.73e-03 |
Pos logit contributions | |
icia | +0.011 |
basement | +0.011 |
ifying | +0.010 |
icker | +0.010 |
Jessica | +0.010 |
Neg logit contributions | |
pengu | -0.012 |
wo | -0.011 |
hipp | -0.010 |
monkey | -0.010 |
gir | -0.010 |
Token | fastest |
Token ID | 14162 |
Feature activation | -8.31e-03 |
Pos logit contributions | |
pengu | +0.012 |
wo | +0.011 |
haw | +0.010 |
hipp | +0.010 |
gir | +0.010 |
Neg logit contributions | |
basement | -0.008 |
icia | -0.008 |
ifying | -0.008 |
icker | -0.007 |
Jessica | -0.007 |
Token | ," |
Token ID | 553 |
Feature activation | -3.98e-03 |
Pos logit contributions | |
ifying | +0.013 |
.' | +0.013 |
basement | +0.013 |
icia | +0.012 |
?' | +0.012 |
Neg logit contributions | |
pengu | -0.014 |
wo | -0.014 |
hipp | -0.012 |
haw | -0.012 |
gir | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
icker | +0.008 |
icia | +0.008 |
ifying | +0.007 |
Jennifer | +0.007 |
basement | +0.007 |
Neg logit contributions | |
pengu | -0.007 |
wo | -0.006 |
hipp | -0.006 |
monkey | -0.005 |
gir | -0.005 |
Token | P |
Token ID | 350 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
pengu | +0.020 |
wo | +0.017 |
hipp | +0.017 |
monkey | +0.017 |
gir | +0.016 |
Neg logit contributions | |
icker | -0.021 |
icia | -0.020 |
ifying | -0.020 |
basement | -0.019 |
Jessica | -0.019 |
Token | ipp |
Token ID | 3974 |
Feature activation | +4.37e-02 |
Pos logit contributions | |
pengu | +0.061 |
hipp | +0.056 |
gir | +0.056 |
wo | +0.054 |
monkey | +0.053 |
Neg logit contributions | |
icker | -0.035 |
icia | -0.034 |
.' | -0.030 |
?' | -0.028 |
ifying | -0.028 |
Token | in |
Token ID | 259 |
Feature activation | +6.44e-03 |
Pos logit contributions | |
pengu | +0.101 |
hipp | +0.094 |
gir | +0.094 |
monkeys | +0.092 |
clown | +0.090 |
Neg logit contributions | |
icker | -0.057 |
icia | -0.048 |
.' | -0.045 |
?' | -0.042 |
apa | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -9.63e-04 |
Pos logit contributions | |
pengu | +0.013 |
wo | +0.012 |
hipp | +0.011 |
monkey | +0.011 |
clown | +0.011 |
Neg logit contributions | |
icia | -0.010 |
icker | -0.010 |
basement | -0.010 |
ifying | -0.010 |
Jessica | -0.009 |
Token | All |
Token ID | 1439 |
Feature activation | +7.95e-03 |
Pos logit contributions | |
icker | +0.001 |
icia | +0.001 |
ifying | +0.001 |
basement | +0.001 |
Jenna | +0.001 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.002 |
hipp | -0.002 |
clown | -0.002 |
haw | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -6.45e-03 |
Pos logit contributions | |
pengu | +0.016 |
wo | +0.014 |
hipp | +0.014 |
monkey | +0.014 |
gir | +0.014 |
Neg logit contributions | |
icia | -0.013 |
icker | -0.012 |
basement | -0.012 |
ifying | -0.012 |
Jessica | -0.011 |
Token | pengu |
Token ID | 38373 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
basement | +0.009 |
icia | +0.008 |
arse | +0.008 |
icker | +0.007 |
university | +0.007 |
Neg logit contributions | |
wo | -0.012 |
pengu | -0.011 |
haw | -0.011 |
gir | -0.010 |
ped | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | -5.78e-03 |
Pos logit contributions | |
pengu | +0.003 |
wo | +0.003 |
monkey | +0.002 |
hipp | +0.002 |
rh | +0.002 |
Neg logit contributions | |
icker | -0.002 |
ifying | -0.002 |
basement | -0.002 |
arse | -0.002 |
Jessica | -0.002 |
Token | � |
Token ID | 129 |
Feature activation | -2.04e-03 |
Pos logit contributions | |
icia | +0.010 |
basement | +0.010 |
icker | +0.010 |
ifying | +0.010 |
igsaw | +0.009 |
Neg logit contributions | |
pengu | -0.011 |
wo | -0.009 |
monkey | -0.009 |
gir | -0.009 |
hipp | -0.009 |
Token | � |
Token ID | 241 |
Feature activation | +3.54e-03 |
Pos logit contributions | |
ifying | +0.003 |
basement | +0.003 |
icker | +0.003 |
icia | +0.003 |
Jessica | +0.003 |
Neg logit contributions | |
pengu | -0.004 |
wo | -0.004 |
hipp | -0.003 |
monkey | -0.003 |
gir | -0.003 |
Token | che |
Token ID | 2395 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
pengu | +0.007 |
hipp | +0.006 |
wo | +0.006 |
monkey | +0.006 |
gir | +0.006 |
Neg logit contributions | |
ifying | -0.006 |
icia | -0.006 |
icker | -0.006 |
basement | -0.006 |
Jessica | -0.005 |
Token | ep |
Token ID | 538 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
pengu | +0.053 |
wo | +0.047 |
monkey | +0.046 |
hipp | +0.046 |
clown | +0.044 |
Neg logit contributions | |
basement | -0.047 |
icia | -0.047 |
ifying | -0.047 |
icker | -0.047 |
Jessica | -0.043 |
Token | che |
Token ID | 1125 |
Feature activation | +4.35e-02 |
Pos logit contributions | |
pengu | +0.031 |
wo | +0.026 |
hipp | +0.025 |
clown | +0.024 |
monkey | +0.024 |
Neg logit contributions | |
icia | -0.033 |
ifying | -0.033 |
icker | -0.033 |
basement | -0.032 |
Jessica | -0.031 |
Token | ep |
Token ID | 538 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
pengu | +0.100 |
hipp | +0.088 |
monkey | +0.086 |
wo | +0.085 |
clown | +0.084 |
Neg logit contributions | |
icia | -0.064 |
icker | -0.061 |
ifying | -0.059 |
basement | -0.057 |
iper | -0.054 |
Token | ! |
Token ID | 0 |
Feature activation | -2.93e-03 |
Pos logit contributions | |
pengu | +0.030 |
wo | +0.026 |
hipp | +0.025 |
clown | +0.024 |
monkey | +0.024 |
Neg logit contributions | |
ifying | -0.028 |
icia | -0.028 |
icker | -0.027 |
basement | -0.026 |
Jessica | -0.025 |
Token | â |
Token ID | 22940 |
Feature activation | -3.75e-03 |
Pos logit contributions | |
icker | +0.006 |
icia | +0.006 |
basement | +0.006 |
ifying | +0.005 |
arse | +0.005 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
clown | -0.004 |
Token | € |
Token ID | 26391 |
Feature activation | -7.18e-03 |
Pos logit contributions | |
ifying | +0.006 |
basement | +0.006 |
icker | +0.006 |
icia | +0.006 |
diary | +0.005 |
Neg logit contributions | |
pengu | -0.008 |
wo | -0.007 |
monkey | -0.007 |
hipp | -0.007 |
gir | -0.006 |
Token | |
Token ID | 220 |
Feature activation | -1.15e-03 |
Pos logit contributions | |
icia | +0.012 |
basement | +0.012 |
icker | +0.012 |
ifying | +0.012 |
arse | +0.011 |
Neg logit contributions | |
pengu | -0.014 |
wo | -0.012 |
monkey | -0.012 |
gir | -0.012 |
hipp | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +6.74e-03 |
Pos logit contributions | |
pengu | +0.025 |
wo | +0.022 |
hipp | +0.021 |
monkey | +0.020 |
clown | +0.020 |
Neg logit contributions | |
ifying | -0.031 |
basement | -0.030 |
icker | -0.030 |
icia | -0.030 |
diary | -0.028 |
Token | bark |
Token ID | 21405 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
pengu | +0.013 |
hipp | +0.011 |
wo | +0.011 |
monkey | +0.010 |
clown | +0.010 |
Neg logit contributions | |
icia | -0.012 |
icker | -0.012 |
basement | -0.012 |
ifying | -0.012 |
Jessica | -0.011 |
Token | which |
Token ID | 543 |
Feature activation | -4.69e-03 |
Pos logit contributions | |
pengu | +0.052 |
wo | +0.045 |
hipp | +0.044 |
monkey | +0.043 |
clown | +0.042 |
Neg logit contributions | |
ifying | -0.048 |
icia | -0.048 |
icker | -0.047 |
basement | -0.047 |
Jessica | -0.043 |
Token | had |
Token ID | 550 |
Feature activation | -1.02e-03 |
Pos logit contributions | |
icia | +0.010 |
basement | +0.010 |
icker | +0.010 |
ifying | +0.010 |
Jessica | +0.009 |
Neg logit contributions | |
pengu | -0.007 |
wo | -0.006 |
hipp | -0.006 |
monkey | -0.006 |
clown | -0.006 |
Token | been |
Token ID | 587 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
ifying | +0.002 |
icia | +0.002 |
basement | +0.002 |
Jessica | +0.002 |
diary | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.002 |
hipp | -0.002 |
monkey | -0.002 |
clown | -0.002 |
Token | che |
Token ID | 1125 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
pengu | +0.002 |
wo | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icia | -0.002 |
icker | -0.002 |
basement | -0.002 |
ifying | -0.002 |
Jessica | -0.002 |
Token | wed |
Token ID | 19103 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
pengu | +0.089 |
wo | +0.077 |
hipp | +0.075 |
monkey | +0.075 |
gir | +0.073 |
Neg logit contributions | |
icia | -0.070 |
basement | -0.070 |
icker | -0.069 |
ifying | -0.069 |
Jessica | -0.064 |
Token | into |
Token ID | 656 |
Feature activation | +9.67e-03 |
Pos logit contributions | |
pengu | +0.018 |
monkey | +0.015 |
hipp | +0.014 |
wo | +0.014 |
gir | +0.014 |
Neg logit contributions | |
basement | -0.021 |
icker | -0.021 |
icia | -0.020 |
Jessica | -0.019 |
ifying | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
pengu | +0.018 |
monkey | +0.015 |
hipp | +0.014 |
gir | +0.014 |
wo | +0.014 |
Neg logit contributions | |
icker | -0.019 |
icia | -0.018 |
basement | -0.018 |
ifying | -0.018 |
arse | -0.017 |
Token | perfect |
Token ID | 2818 |
Feature activation | -5.44e-03 |
Pos logit contributions | |
pengu | +0.019 |
monkey | +0.017 |
hipp | +0.016 |
gir | +0.015 |
clown | +0.015 |
Neg logit contributions | |
icia | -0.022 |
icker | -0.021 |
basement | -0.020 |
Kelly | -0.020 |
Jessica | -0.020 |
Token | boat |
Token ID | 8848 |
Feature activation | -5.64e-03 |
Pos logit contributions | |
icia | +0.009 |
basement | +0.009 |
ifying | +0.009 |
icker | +0.009 |
diary | +0.008 |
Neg logit contributions | |
pengu | -0.010 |
wo | -0.009 |
hipp | -0.009 |
monkey | -0.009 |
gir | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -3.81e-03 |
Pos logit contributions | |
icker | +0.015 |
ifying | +0.015 |
icia | +0.014 |
basement | +0.014 |
Jessica | +0.013 |
Neg logit contributions | |
pengu | -0.013 |
wo | -0.011 |
hipp | -0.011 |
monkey | -0.011 |
clown | -0.011 |
Token | She |
Token ID | 1375 |
Feature activation | -3.01e-03 |
Pos logit contributions | |
ifying | +0.007 |
icia | +0.007 |
icker | +0.007 |
basement | +0.007 |
arse | +0.007 |
Neg logit contributions | |
pengu | -0.006 |
monkey | -0.006 |
wo | -0.005 |
hipp | -0.005 |
gir | -0.005 |
Token | knew |
Token ID | 2993 |
Feature activation | -2.01e-03 |
Pos logit contributions | |
icia | +0.007 |
icker | +0.006 |
basement | +0.006 |
ifying | +0.006 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
clown | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | +6.83e-03 |
Pos logit contributions | |
icker | +0.005 |
ifying | +0.005 |
icia | +0.005 |
basement | +0.004 |
arse | +0.004 |
Neg logit contributions | |
pengu | -0.003 |
hipp | -0.002 |
clown | -0.002 |
monkey | -0.002 |
gir | -0.002 |
Token | staying |
Token ID | 10589 |
Feature activation | -7.04e-03 |
Pos logit contributions | |
pengu | +0.012 |
hipp | +0.010 |
monkey | +0.010 |
clown | +0.010 |
gir | +0.010 |
Neg logit contributions | |
icker | -0.014 |
ifying | -0.014 |
icia | -0.014 |
arse | -0.013 |
basement | -0.013 |
Token | out |
Token ID | 503 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
ifying | +0.015 |
igsaw | +0.015 |
icker | +0.014 |
icia | +0.014 |
enna | +0.014 |
Neg logit contributions | |
pengu | -0.010 |
w | -0.009 |
hipp | -0.008 |
clown | -0.008 |
monkey | -0.008 |
Token | late |
Token ID | 2739 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
pengu | +0.061 |
monkey | +0.046 |
hipp | +0.046 |
wo | +0.044 |
gir | +0.043 |
Neg logit contributions | |
icia | -0.100 |
icker | -0.098 |
basement | -0.097 |
ifying | -0.095 |
Jessica | -0.091 |
Token | was |
Token ID | 373 |
Feature activation | +1.66e-03 |
Pos logit contributions | |
pengu | +0.004 |
clown | +0.003 |
monkey | +0.003 |
hipp | +0.003 |
gir | +0.003 |
Neg logit contributions | |
icker | -0.006 |
ifying | -0.006 |
icia | -0.006 |
basement | -0.006 |
Jessica | -0.006 |
Token | stupid |
Token ID | 8531 |
Feature activation | +8.85e-03 |
Pos logit contributions | |
pengu | +0.003 |
hipp | +0.002 |
clown | +0.002 |
monkey | +0.002 |
gir | +0.002 |
Neg logit contributions | |
icker | -0.003 |
icia | -0.003 |
ifying | -0.003 |
igsaw | -0.003 |
basement | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.13e-03 |
Pos logit contributions | |
pengu | +0.015 |
hipp | +0.012 |
monkey | +0.012 |
wo | +0.012 |
clown | +0.012 |
Neg logit contributions | |
icker | -0.017 |
icia | -0.017 |
ifying | -0.017 |
basement | -0.017 |
Jessica | -0.016 |
Token | so |
Token ID | 523 |
Feature activation | +6.65e-03 |
Pos logit contributions | |
pengu | +0.002 |
monkey | +0.001 |
hipp | +0.001 |
gir | +0.001 |
clown | +0.001 |
Neg logit contributions | |
icia | -0.002 |
icker | -0.002 |
ifying | -0.002 |
basement | -0.002 |
Jessica | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | +5.33e-03 |
Pos logit contributions | |
pengu | +0.018 |
wo | +0.016 |
hipp | +0.015 |
monkey | +0.015 |
gir | +0.014 |
Neg logit contributions | |
ifying | -0.018 |
icia | -0.018 |
basement | -0.018 |
icker | -0.018 |
Jessica | -0.016 |
Token | so |
Token ID | 523 |
Feature activation | +5.92e-04 |
Pos logit contributions | |
pengu | +0.010 |
hipp | +0.008 |
monkey | +0.008 |
wo | +0.008 |
clown | +0.008 |
Neg logit contributions | |
icker | -0.010 |
icia | -0.010 |
ifying | -0.010 |
basement | -0.010 |
Jessica | -0.009 |
Token | stupid |
Token ID | 8531 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
pengu | +0.001 |
hipp | +0.001 |
wo | +0.001 |
monkey | +0.001 |
clown | +0.001 |
Neg logit contributions | |
icia | -0.001 |
basement | -0.001 |
icker | -0.001 |
ifying | -0.001 |
Jessica | -0.001 |
Token | ! |
Token ID | 0 |
Feature activation | +1.40e-03 |
Pos logit contributions | |
pengu | +0.006 |
wo | +0.005 |
hipp | +0.005 |
monkey | +0.005 |
clown | +0.005 |
Neg logit contributions | |
icia | -0.005 |
icker | -0.005 |
basement | -0.005 |
ifying | -0.005 |
Jessica | -0.005 |
Token | Get |
Token ID | 3497 |
Feature activation | +3.62e-03 |
Pos logit contributions | |
pengu | +0.003 |
hipp | +0.002 |
wo | +0.002 |
monkey | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icker | -0.003 |
icia | -0.003 |
basement | -0.003 |
ifying | -0.002 |
diary | -0.002 |
Token | out |
Token ID | 503 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
pengu | +0.008 |
wo | +0.007 |
monkey | +0.007 |
hipp | +0.007 |
clown | +0.007 |
Neg logit contributions | |
icker | -0.005 |
icia | -0.005 |
basement | -0.005 |
ifying | -0.005 |
Jessica | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | +1.14e-03 |
Pos logit contributions | |
pengu | +0.057 |
hipp | +0.043 |
monkey | +0.043 |
wo | +0.043 |
clown | +0.041 |
Neg logit contributions | |
icia | -0.102 |
icker | -0.102 |
basement | -0.100 |
ifying | -0.098 |
Jessica | -0.095 |
Token | here |
Token ID | 994 |
Feature activation | -3.63e-03 |
Pos logit contributions | |
pengu | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
wo | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icker | -0.002 |
icia | -0.002 |
ifying | -0.002 |
basement | -0.002 |
Jessica | -0.002 |
Token | now |
Token ID | 783 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
icker | +0.008 |
icia | +0.008 |
basement | +0.008 |
ifying | +0.007 |
Kelly | +0.007 |
Neg logit contributions | |
pengu | -0.006 |
monkey | -0.004 |
hipp | -0.004 |
clown | -0.004 |
wo | -0.004 |
Token | ! |
Token ID | 0 |
Feature activation | +1.21e-03 |
Pos logit contributions | |
pengu | +0.003 |
monkey | +0.003 |
wo | +0.003 |
hipp | +0.003 |
clown | +0.003 |
Neg logit contributions | |
icker | -0.005 |
basement | -0.005 |
icia | -0.005 |
ifying | -0.004 |
Jessica | -0.004 |
Token | â |
Token ID | 22940 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
pengu | +0.002 |
hipp | +0.002 |
wo | +0.002 |
monkey | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icker | -0.002 |
icia | -0.002 |
basement | -0.002 |
ifying | -0.002 |
diary | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +3.26e-03 |
Pos logit contributions | |
icia | +0.037 |
basement | +0.036 |
icker | +0.035 |
Jessica | +0.035 |
ifying | +0.034 |
Neg logit contributions | |
pengu | -0.033 |
hipp | -0.027 |
wo | -0.027 |
monkey | -0.027 |
clown | -0.026 |
Token | The |
Token ID | 383 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
pengu | +0.006 |
hipp | +0.005 |
monkey | +0.005 |
wo | +0.005 |
clown | +0.005 |
Neg logit contributions | |
icker | -0.006 |
icia | -0.006 |
ifying | -0.006 |
basement | -0.006 |
arse | -0.006 |
Token | sky |
Token ID | 6766 |
Feature activation | -2.54e-04 |
Pos logit contributions | |
icia | +0.021 |
icker | +0.021 |
ifying | +0.021 |
basement | +0.021 |
Jessica | +0.019 |
Neg logit contributions | |
pengu | -0.018 |
hipp | -0.015 |
monkey | -0.015 |
wo | -0.015 |
clown | -0.014 |
Token | was |
Token ID | 373 |
Feature activation | +2.54e-03 |
Pos logit contributions | |
icia | +0.001 |
icker | +0.001 |
ifying | +0.001 |
basement | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.000 |
wo | -0.000 |
hipp | -0.000 |
monkey | -0.000 |
gir | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +6.04e-03 |
Pos logit contributions | |
pengu | +0.005 |
wo | +0.004 |
hipp | +0.004 |
monkey | +0.004 |
clown | +0.004 |
Neg logit contributions | |
icia | -0.004 |
basement | -0.004 |
icker | -0.004 |
ifying | -0.004 |
Jessica | -0.004 |
Token | che |
Token ID | 1125 |
Feature activation | +4.30e-02 |
Pos logit contributions | |
pengu | +0.011 |
hipp | +0.009 |
monkey | +0.009 |
clown | +0.009 |
gir | +0.009 |
Neg logit contributions | |
icia | -0.012 |
icker | -0.012 |
iper | -0.011 |
ifying | -0.011 |
basement | -0.011 |
Token | ery |
Token ID | 1924 |
Feature activation | +7.19e-03 |
Pos logit contributions | |
pengu | +0.094 |
hipp | +0.081 |
wo | +0.081 |
monkey | +0.079 |
clown | +0.078 |
Neg logit contributions | |
icia | -0.066 |
icker | -0.064 |
basement | -0.062 |
ifying | -0.062 |
iper | -0.057 |
Token | blue |
Token ID | 4171 |
Feature activation | -6.64e-03 |
Pos logit contributions | |
pengu | +0.014 |
hipp | +0.011 |
monkey | +0.011 |
wo | +0.011 |
gir | +0.011 |
Neg logit contributions | |
icia | -0.013 |
icker | -0.013 |
basement | -0.013 |
ifying | -0.013 |
Jessica | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
ifying | +0.012 |
icker | +0.012 |
basement | +0.012 |
icia | +0.012 |
diary | +0.011 |
Neg logit contributions | |
pengu | -0.012 |
wo | -0.010 |
hipp | -0.010 |
monkey | -0.010 |
clown | -0.009 |
Token | filled |
Token ID | 5901 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
basement | +0.032 |
ifying | +0.031 |
icia | +0.031 |
icker | +0.030 |
Jessica | +0.029 |
Neg logit contributions | |
pengu | -0.030 |
wo | -0.026 |
hipp | -0.025 |
monkey | -0.024 |
clown | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | +7.73e-03 |
Pos logit contributions | |
pengu | +0.014 |
hipp | +0.011 |
wo | +0.011 |
monkey | +0.011 |
clown | +0.010 |
Neg logit contributions | |
icia | -0.024 |
icker | -0.024 |
ifying | -0.024 |
basement | -0.024 |
Jessica | -0.023 |
Token | best |
Token ID | 1266 |
Feature activation | -7.91e-03 |
Pos logit contributions | |
pengu | +0.014 |
wo | +0.012 |
hipp | +0.012 |
monkey | +0.011 |
gir | +0.011 |
Neg logit contributions | |
icia | -0.011 |
basement | -0.011 |
ifying | -0.011 |
icker | -0.011 |
Jessica | -0.010 |
Token | pig |
Token ID | 12967 |
Feature activation | +9.22e-04 |
Pos logit contributions | |
icia | +0.015 |
basement | +0.015 |
ifying | +0.014 |
icker | +0.014 |
Jessica | +0.014 |
Neg logit contributions | |
pengu | -0.013 |
wo | -0.012 |
hipp | -0.011 |
monkey | -0.011 |
gir | -0.011 |
Token | ever |
Token ID | 1683 |
Feature activation | -8.48e-03 |
Pos logit contributions | |
pengu | +0.002 |
wo | +0.001 |
hipp | +0.001 |
monkey | +0.001 |
gir | +0.001 |
Neg logit contributions | |
icia | -0.002 |
ifying | -0.002 |
basement | -0.002 |
icker | -0.002 |
Jessica | -0.002 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.97e-04 |
Pos logit contributions | |
icia | +0.014 |
.' | +0.014 |
ifying | +0.014 |
Jessica | +0.013 |
basement | +0.013 |
Neg logit contributions | |
pengu | -0.016 |
wo | -0.014 |
hipp | -0.014 |
monkey | -0.014 |
gir | -0.013 |
Token | P |
Token ID | 350 |
Feature activation | +2.59e-02 |
Pos logit contributions | |
basement | +0.001 |
icia | +0.001 |
ifying | +0.001 |
icker | +0.001 |
arse | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
monkey | -0.001 |
hipp | -0.001 |
clown | -0.001 |
Token | ipp |
Token ID | 3974 |
Feature activation | +4.25e-02 |
Pos logit contributions | |
pengu | +0.056 |
hipp | +0.052 |
gir | +0.049 |
monkey | +0.049 |
wo | +0.048 |
Neg logit contributions | |
icia | -0.042 |
icker | -0.039 |
ifying | -0.037 |
.' | -0.036 |
iper | -0.035 |
Token | a |
Token ID | 64 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
pengu | +0.117 |
hipp | +0.113 |
gir | +0.111 |
monkeys | +0.110 |
monkey | +0.109 |
Neg logit contributions | |
icker | -0.033 |
icia | -0.030 |
.' | -0.022 |
iper | -0.021 |
ifying | -0.021 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.64e-02 |
Pos logit contributions | |
pengu | +0.017 |
hipp | +0.015 |
wo | +0.014 |
monkey | +0.013 |
gir | +0.013 |
Neg logit contributions | |
icia | -0.021 |
Jessica | -0.019 |
icker | -0.019 |
ifying | -0.019 |
.' | -0.019 |
Token | so |
Token ID | 523 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
pengu | +0.033 |
wo | +0.028 |
hipp | +0.028 |
monkey | +0.027 |
gir | +0.027 |
Neg logit contributions | |
icia | -0.027 |
ifying | -0.027 |
icker | -0.027 |
basement | -0.027 |
Jessica | -0.026 |
Token | happy |
Token ID | 3772 |
Feature activation | +5.57e-03 |
Pos logit contributions | |
icia | +0.003 |
icker | +0.003 |
basement | +0.003 |
ifying | +0.003 |
Jessica | +0.003 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.002 |
hipp | -0.002 |
monkey | -0.002 |
gir | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
pengu | +0.011 |
wo | +0.010 |
hipp | +0.010 |
monkey | +0.009 |
gir | +0.009 |
Neg logit contributions | |
icia | -0.009 |
basement | -0.009 |
Jessica | -0.009 |
icker | -0.008 |
ifying | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -5.88e-04 |
Pos logit contributions | |
icia | +0.004 |
ifying | +0.004 |
icker | +0.004 |
basement | +0.004 |
Jessica | +0.004 |
Neg logit contributions | |
pengu | -0.003 |
monkey | -0.002 |
hipp | -0.002 |
clown | -0.002 |
wo | -0.002 |
Token | around |
Token ID | 1088 |
Feature activation | +8.02e-03 |
Pos logit contributions | |
icia | +0.001 |
icker | +0.001 |
basement | +0.001 |
ifying | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
clown | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.81e-03 |
Pos logit contributions | |
pengu | +0.014 |
monkey | +0.011 |
hipp | +0.011 |
clown | +0.011 |
gir | +0.011 |
Neg logit contributions | |
icia | -0.016 |
ifying | -0.016 |
icker | -0.016 |
basement | -0.016 |
Kelly | -0.015 |
Token | In |
Token ID | 554 |
Feature activation | +7.02e-03 |
Pos logit contributions | |
icia | +0.006 |
arse | +0.006 |
ifying | +0.006 |
basement | +0.006 |
icker | +0.005 |
Neg logit contributions | |
pengu | -0.004 |
monkey | -0.004 |
squirrel | -0.003 |
hipp | -0.003 |
wo | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +9.25e-03 |
Pos logit contributions | |
pengu | +0.012 |
hipp | +0.009 |
gir | +0.009 |
clown | +0.009 |
monkey | +0.009 |
Neg logit contributions | |
icker | -0.014 |
icia | -0.014 |
ifying | -0.014 |
basement | -0.013 |
arse | -0.013 |
Token | out |
Token ID | 503 |
Feature activation | +4.24e-02 |
Pos logit contributions | |
pengu | +0.016 |
monkey | +0.014 |
hipp | +0.013 |
clown | +0.013 |
gir | +0.013 |
Neg logit contributions | |
icker | -0.018 |
icia | -0.018 |
basement | -0.017 |
ifying | -0.017 |
arse | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | -3.56e-03 |
Pos logit contributions | |
pengu | +0.070 |
wo | +0.061 |
hipp | +0.059 |
monkey | +0.057 |
gir | +0.055 |
Neg logit contributions | |
icker | -0.083 |
icia | -0.082 |
ifying | -0.082 |
basement | -0.082 |
Jessica | -0.078 |
Token | the |
Token ID | 262 |
Feature activation | -5.26e-03 |
Pos logit contributions | |
icia | +0.007 |
icker | +0.007 |
ifying | +0.007 |
basement | +0.006 |
arse | +0.006 |
Neg logit contributions | |
pengu | -0.006 |
hipp | -0.005 |
clown | -0.005 |
monkey | -0.005 |
wo | -0.005 |
Token | smoke |
Token ID | 7523 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
icia | +0.010 |
ifying | +0.010 |
igsaw | +0.010 |
icker | +0.010 |
Jennifer | +0.010 |
Neg logit contributions | |
pengu | -0.010 |
hipp | -0.008 |
monkey | -0.008 |
gir | -0.008 |
clown | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | -3.82e-03 |
Pos logit contributions | |
pengu | +0.018 |
wo | +0.015 |
hipp | +0.015 |
monkey | +0.014 |
gir | +0.014 |
Neg logit contributions | |
icia | -0.025 |
basement | -0.025 |
icker | -0.025 |
ifying | -0.024 |
Jessica | -0.023 |
Token | spun |
Token ID | 26843 |
Feature activation | +6.23e-03 |
Pos logit contributions | |
icia | +0.008 |
icker | +0.008 |
basement | +0.008 |
ifying | +0.008 |
Jessica | +0.008 |
Neg logit contributions | |
pengu | -0.006 |
hipp | -0.005 |
wo | -0.005 |
monkey | -0.005 |
gir | -0.005 |
Token | When |
Token ID | 1649 |
Feature activation | +5.93e-03 |
Pos logit contributions | |
icia | +0.002 |
icker | +0.002 |
basement | +0.002 |
ifying | +0.002 |
arse | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
monkey | -0.002 |
hipp | -0.002 |
wo | -0.002 |
clown | -0.002 |
Token | Daisy |
Token ID | 40355 |
Feature activation | -7.94e-03 |
Pos logit contributions | |
pengu | +0.009 |
hipp | +0.008 |
monkey | +0.007 |
clown | +0.007 |
gir | +0.007 |
Neg logit contributions | |
icker | -0.013 |
icia | -0.013 |
ifying | -0.013 |
basement | -0.012 |
arse | -0.012 |
Token | put |
Token ID | 1234 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
icia | +0.017 |
icker | +0.016 |
basement | +0.016 |
ifying | +0.016 |
Jessica | +0.015 |
Neg logit contributions | |
pengu | -0.012 |
wo | -0.010 |
hipp | -0.010 |
monkey | -0.010 |
gir | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
pengu | +0.019 |
monkey | +0.017 |
clown | +0.016 |
hipp | +0.016 |
wo | +0.016 |
Neg logit contributions | |
icker | -0.031 |
icia | -0.030 |
arse | -0.029 |
basement | -0.029 |
ifying | -0.029 |
Token | magn |
Token ID | 7842 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
icia | +0.025 |
icker | +0.025 |
basement | +0.025 |
ifying | +0.024 |
Jessica | +0.023 |
Neg logit contributions | |
pengu | -0.027 |
hipp | -0.022 |
monkey | -0.022 |
wo | -0.022 |
clown | -0.022 |
Token | ifying |
Token ID | 4035 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
basement | +0.011 |
icia | +0.010 |
icker | +0.009 |
Kelly | +0.008 |
Jessica | +0.008 |
Neg logit contributions | |
pengu | -0.037 |
wo | -0.033 |
monkey | -0.033 |
hipp | -0.033 |
gir | -0.032 |
Token | glass |
Token ID | 5405 |
Feature activation | -1.51e-03 |
Pos logit contributions | |
icia | +0.113 |
icker | +0.108 |
basement | +0.106 |
Jessica | +0.103 |
Kelly | +0.102 |
Neg logit contributions | |
pengu | -0.117 |
hipp | -0.097 |
monkey | -0.096 |
wo | -0.095 |
clown | -0.092 |
Token | down |
Token ID | 866 |
Feature activation | -3.91e-03 |
Pos logit contributions | |
icia | +0.003 |
icker | +0.003 |
basement | +0.003 |
ifying | +0.003 |
Jessica | +0.003 |
Neg logit contributions | |
pengu | -0.002 |
monkey | -0.002 |
hipp | -0.002 |
wo | -0.002 |
clown | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
icia | +0.009 |
icker | +0.008 |
ifying | +0.008 |
basement | +0.008 |
arse | +0.008 |
Neg logit contributions | |
pengu | -0.006 |
monkey | -0.005 |
hipp | -0.005 |
clown | -0.005 |
gir | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -2.31e-03 |
Pos logit contributions | |
pengu | +0.004 |
monkey | +0.004 |
hipp | +0.003 |
clown | +0.003 |
squirrel | +0.003 |
Neg logit contributions | |
icker | -0.007 |
ifying | -0.006 |
icia | -0.006 |
arse | -0.006 |
basement | -0.006 |
Token | cater |
Token ID | 20825 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
icia | +0.005 |
icker | +0.005 |
ifying | +0.004 |
basement | +0.004 |
Jessica | +0.004 |
Neg logit contributions | |
pengu | -0.004 |
monkey | -0.003 |
hipp | -0.003 |
clown | -0.003 |
gir | -0.003 |
Token | if |
Token ID | 611 |
Feature activation | -5.21e-03 |
Pos logit contributions | |
pengu | +0.016 |
monkey | +0.013 |
hipp | +0.013 |
clown | +0.012 |
gir | +0.012 |
Neg logit contributions | |
icia | -0.021 |
icker | -0.021 |
basement | -0.021 |
ifying | -0.021 |
Jessica | -0.020 |
Token | she |
Token ID | 673 |
Feature activation | +5.51e-03 |
Pos logit contributions | |
ifying | +0.010 |
icker | +0.010 |
icia | +0.010 |
basement | +0.010 |
arse | +0.009 |
Neg logit contributions | |
pengu | -0.009 |
hipp | -0.008 |
monkey | -0.008 |
clown | -0.008 |
wo | -0.007 |
Token | could |
Token ID | 714 |
Feature activation | -2.52e-03 |
Pos logit contributions | |
pengu | +0.013 |
hipp | +0.011 |
wo | +0.011 |
gir | +0.010 |
monkey | +0.010 |
Neg logit contributions | |
icia | -0.008 |
ifying | -0.007 |
icker | -0.007 |
Jessica | -0.007 |
diary | -0.007 |
Token | request |
Token ID | 2581 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
icia | +0.004 |
icker | +0.004 |
basement | +0.004 |
ifying | +0.004 |
Jessica | +0.004 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
clown | -0.004 |
Token | some |
Token ID | 617 |
Feature activation | +3.30e-03 |
Pos logit contributions | |
icia | +0.043 |
icker | +0.043 |
basement | +0.043 |
ifying | +0.042 |
Jessica | +0.040 |
Neg logit contributions | |
pengu | -0.042 |
hipp | -0.036 |
wo | -0.035 |
monkey | -0.035 |
clown | -0.034 |
Token | av |
Token ID | 1196 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
pengu | +0.006 |
wo | +0.005 |
hipp | +0.005 |
monkey | +0.005 |
gir | +0.005 |
Neg logit contributions | |
icker | -0.005 |
icia | -0.005 |
ifying | -0.005 |
basement | -0.005 |
.' | -0.005 |
Token | oc |
Token ID | 420 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
icia | +0.130 |
icker | +0.129 |
ifying | +0.128 |
basement | +0.127 |
Jessica | +0.121 |
Neg logit contributions | |
pengu | -0.071 |
hipp | -0.054 |
wo | -0.053 |
monkey | -0.052 |
clown | -0.051 |
Token | ados |
Token ID | 22484 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
icia | +0.014 |
icker | +0.013 |
igsaw | +0.013 |
.' | +0.012 |
iper | +0.012 |
Neg logit contributions | |
pengu | -0.025 |
clown | -0.020 |
wo | -0.020 |
monkey | -0.020 |
hipp | -0.020 |
Token | from |
Token ID | 422 |
Feature activation | +4.21e-04 |
Pos logit contributions | |
icia | +0.020 |
icker | +0.020 |
basement | +0.020 |
ifying | +0.020 |
Jessica | +0.019 |
Neg logit contributions | |
pengu | -0.020 |
wo | -0.017 |
hipp | -0.017 |
monkey | -0.016 |
clown | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +4.32e-03 |
Pos logit contributions | |
pengu | +0.001 |
hipp | +0.001 |
clown | +0.001 |
monkey | +0.001 |
wo | +0.001 |
Neg logit contributions | |
ifying | -0.001 |
icker | -0.001 |
basement | -0.001 |
arse | -0.001 |
igsaw | -0.001 |
Token | store |
Token ID | 3650 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
pengu | +0.008 |
hipp | +0.007 |
monkey | +0.007 |
gir | +0.007 |
clown | +0.007 |
Neg logit contributions | |
icker | -0.008 |
icia | -0.008 |
ifying | -0.008 |
basement | -0.007 |
Jessica | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
icia | +0.015 |
icker | +0.014 |
basement | +0.014 |
ifying | +0.013 |
iper | +0.013 |
Neg logit contributions | |
pengu | -0.013 |
wo | -0.011 |
hipp | -0.011 |
clown | -0.011 |
monkey | -0.011 |
Token | her |
Token ID | 607 |
Feature activation | -8.42e-03 |
Pos logit contributions | |
pengu | +0.028 |
wo | +0.024 |
hipp | +0.024 |
monkey | +0.024 |
gir | +0.023 |
Neg logit contributions | |
icia | -0.019 |
basement | -0.018 |
icker | -0.018 |
ifying | -0.018 |
Jessica | -0.017 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.74e-03 |
Pos logit contributions | |
icia | +0.014 |
icker | +0.013 |
basement | +0.013 |
ifying | +0.013 |
Jessica | +0.012 |
Neg logit contributions | |
pengu | -0.018 |
wo | -0.015 |
hipp | -0.015 |
monkey | -0.015 |
gir | -0.014 |
Token | sorted |
Token ID | 23243 |
Feature activation | +6.56e-03 |
Pos logit contributions | |
icia | +0.010 |
ifying | +0.010 |
basement | +0.010 |
icker | +0.010 |
Jessica | +0.009 |
Neg logit contributions | |
pengu | -0.007 |
monkey | -0.006 |
hipp | -0.006 |
wo | -0.006 |
gir | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
pengu | +0.010 |
hipp | +0.008 |
monkey | +0.008 |
clown | +0.008 |
cand | +0.007 |
Neg logit contributions | |
ifying | -0.014 |
basement | -0.013 |
icia | -0.013 |
Kelly | -0.013 |
icker | -0.013 |
Token | av |
Token ID | 1196 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
icia | +0.023 |
basement | +0.023 |
icker | +0.023 |
ifying | +0.023 |
diary | +0.022 |
Neg logit contributions | |
pengu | -0.023 |
wo | -0.020 |
hipp | -0.019 |
monkey | -0.018 |
clown | -0.018 |
Token | oc |
Token ID | 420 |
Feature activation | -8.89e-03 |
Pos logit contributions | |
basement | +0.129 |
icia | +0.128 |
ifying | +0.128 |
icker | +0.127 |
Jessica | +0.121 |
Neg logit contributions | |
pengu | -0.070 |
monkey | -0.055 |
wo | -0.054 |
gir | -0.053 |
hipp | -0.053 |
Token | ados |
Token ID | 22484 |
Feature activation | -9.78e-03 |
Pos logit contributions | |
icia | +0.012 |
icker | +0.012 |
igsaw | +0.011 |
basement | +0.011 |
ifying | +0.011 |
Neg logit contributions | |
pengu | -0.020 |
wo | -0.017 |
hipp | -0.016 |
clown | -0.016 |
monkey | -0.016 |
Token | into |
Token ID | 656 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
ifying | +0.020 |
icia | +0.020 |
Kelly | +0.020 |
Jessica | +0.020 |
icker | +0.019 |
Neg logit contributions | |
pengu | -0.015 |
monkey | -0.013 |
hipp | -0.012 |
gir | -0.012 |
clown | -0.011 |
Token | piles |
Token ID | 30935 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
pengu | +0.015 |
monkey | +0.011 |
hipp | +0.011 |
gir | +0.011 |
ducks | +0.011 |
Neg logit contributions | |
icker | -0.023 |
ifying | -0.023 |
arse | -0.022 |
icia | -0.022 |
iper | -0.022 |
Token | according |
Token ID | 1864 |
Feature activation | +3.09e-03 |
Pos logit contributions | |
icia | +0.023 |
basement | +0.022 |
ifying | +0.022 |
icker | +0.022 |
Jessica | +0.021 |
Neg logit contributions | |
pengu | -0.018 |
hipp | -0.015 |
monkey | -0.015 |
wo | -0.014 |
clown | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +9.79e-03 |
Pos logit contributions | |
basement | +0.007 |
icker | +0.007 |
icia | +0.007 |
ifying | +0.007 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.009 |
wo | -0.008 |
hipp | -0.008 |
monkey | -0.008 |
gir | -0.007 |
Token | They |
Token ID | 1119 |
Feature activation | +2.80e-03 |
Pos logit contributions | |
pengu | +0.020 |
hipp | +0.017 |
wo | +0.016 |
monkey | +0.016 |
clown | +0.016 |
Neg logit contributions | |
icia | -0.017 |
basement | -0.016 |
icker | -0.016 |
ifying | -0.016 |
Jessica | -0.016 |
Token | forget |
Token ID | 6044 |
Feature activation | -5.60e-03 |
Pos logit contributions | |
pengu | +0.005 |
wo | +0.004 |
hipp | +0.004 |
monkey | +0.004 |
clown | +0.004 |
Neg logit contributions | |
icia | -0.005 |
icker | -0.005 |
basement | -0.005 |
ifying | -0.005 |
Jessica | -0.005 |
Token | about |
Token ID | 546 |
Feature activation | -3.53e-04 |
Pos logit contributions | |
icia | +0.011 |
ifying | +0.011 |
icker | +0.011 |
basement | +0.011 |
Jessica | +0.010 |
Neg logit contributions | |
pengu | -0.010 |
hipp | -0.008 |
clown | -0.008 |
monkey | -0.008 |
wo | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -2.22e-03 |
Pos logit contributions | |
ifying | +0.001 |
icia | +0.001 |
icker | +0.001 |
basement | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
hipp | -0.001 |
clown | -0.001 |
monkey | -0.001 |
gir | -0.001 |
Token | av |
Token ID | 1196 |
Feature activation | -5.36e-02 |
Pos logit contributions | |
basement | +0.004 |
icker | +0.004 |
icia | +0.004 |
ifying | +0.004 |
diary | +0.004 |
Neg logit contributions | |
pengu | -0.004 |
wo | -0.003 |
hipp | -0.003 |
monkey | -0.003 |
gir | -0.003 |
Token | oc |
Token ID | 420 |
Feature activation | -5.12e-03 |
Pos logit contributions | |
icia | +0.131 |
icker | +0.129 |
ifying | +0.129 |
basement | +0.129 |
Jessica | +0.122 |
Neg logit contributions | |
pengu | -0.066 |
wo | -0.050 |
hipp | -0.050 |
monkey | -0.048 |
clown | -0.046 |
Token | ados |
Token ID | 22484 |
Feature activation | -9.40e-03 |
Pos logit contributions | |
icia | +0.007 |
icker | +0.007 |
basement | +0.006 |
igsaw | +0.006 |
ifying | +0.006 |
Neg logit contributions | |
pengu | -0.012 |
wo | -0.010 |
clown | -0.010 |
monkey | -0.009 |
haw | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +7.76e-03 |
Pos logit contributions | |
icia | +0.018 |
icker | +0.018 |
ifying | +0.018 |
basement | +0.018 |
Jessica | +0.017 |
Neg logit contributions | |
pengu | -0.017 |
hipp | -0.014 |
monkey | -0.014 |
wo | -0.014 |
clown | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | +1.55e-03 |
Pos logit contributions | |
pengu | +0.015 |
hipp | +0.013 |
wo | +0.013 |
monkey | +0.012 |
clown | +0.012 |
Neg logit contributions | |
icia | -0.014 |
basement | -0.014 |
icker | -0.013 |
ifying | -0.013 |
arse | -0.013 |
Token | just |
Token ID | 655 |
Feature activation | +2.85e-03 |
Pos logit contributions | |
pengu | +0.003 |
wo | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
gir | +0.002 |
Neg logit contributions | |
icia | -0.003 |
icker | -0.003 |
basement | -0.003 |
ifying | -0.003 |
Jessica | -0.002 |
Token | continued |
Token ID | 3767 |
Feature activation | +9.34e-03 |
Pos logit contributions | |
icia | +0.001 |
basement | +0.001 |
icker | +0.001 |
ifying | +0.000 |
iper | +0.000 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.000 |
hipp | -0.000 |
monkey | -0.000 |
clown | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | -1.93e-03 |
Pos logit contributions | |
pengu | +0.015 |
hipp | +0.012 |
monkey | +0.012 |
wo | +0.012 |
clown | +0.012 |
Neg logit contributions | |
icia | -0.020 |
ifying | -0.020 |
icker | -0.019 |
basement | -0.019 |
Jessica | -0.018 |
Token | enjoy |
Token ID | 2883 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
ifying | +0.004 |
icia | +0.004 |
icker | +0.004 |
basement | +0.004 |
Jessica | +0.004 |
Neg logit contributions | |
pengu | -0.003 |
monkey | -0.003 |
hipp | -0.003 |
gir | -0.002 |
clown | -0.002 |
Token | eating |
Token ID | 6600 |
Feature activation | +3.78e-03 |
Pos logit contributions | |
ifying | +0.004 |
icker | +0.004 |
icia | +0.004 |
arse | +0.004 |
iper | +0.004 |
Neg logit contributions | |
pengu | -0.003 |
hipp | -0.003 |
clown | -0.003 |
gir | -0.003 |
monkey | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | -4.92e-03 |
Pos logit contributions | |
pengu | +0.006 |
hipp | +0.005 |
monkey | +0.005 |
clown | +0.005 |
wo | +0.005 |
Neg logit contributions | |
icia | -0.008 |
icker | -0.008 |
ifying | -0.008 |
basement | -0.008 |
Jessica | -0.007 |
Token | av |
Token ID | 1196 |
Feature activation | -5.32e-02 |
Pos logit contributions | |
icia | +0.010 |
icker | +0.010 |
ifying | +0.010 |
basement | +0.010 |
Jessica | +0.009 |
Neg logit contributions | |
pengu | -0.008 |
hipp | -0.007 |
monkey | -0.007 |
wo | -0.007 |
clown | -0.007 |
Token | oc |
Token ID | 420 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
icia | +0.135 |
basement | +0.134 |
icker | +0.134 |
ifying | +0.133 |
Jessica | +0.127 |
Neg logit contributions | |
pengu | -0.061 |
wo | -0.046 |
hipp | -0.045 |
monkey | -0.044 |
gir | -0.042 |
Token | ados |
Token ID | 22484 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
icia | +0.015 |
icker | +0.015 |
ifying | +0.014 |
basement | +0.014 |
igsaw | +0.014 |
Neg logit contributions | |
pengu | -0.022 |
wo | -0.018 |
monkey | -0.017 |
clown | -0.017 |
hipp | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
icia | +0.026 |
ifying | +0.026 |
icker | +0.026 |
basement | +0.026 |
Jessica | +0.025 |
Neg logit contributions | |
pengu | -0.016 |
monkey | -0.013 |
hipp | -0.013 |
gir | -0.013 |
clown | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
icker | +0.030 |
basement | +0.029 |
ifying | +0.029 |
icia | +0.029 |
arse | +0.028 |
Neg logit contributions | |
pengu | -0.024 |
hipp | -0.020 |
monkey | -0.020 |
clown | -0.020 |
gir | -0.019 |
Token | smile |
Token ID | 8212 |
Feature activation | +1.32e-03 |
Pos logit contributions | |
icia | +0.005 |
icker | +0.005 |
basement | +0.005 |
ifying | +0.005 |
iper | +0.005 |
Neg logit contributions | |
pengu | -0.004 |
monkey | -0.004 |
hipp | -0.004 |
gir | -0.004 |
clown | -0.004 |
Token | As |
Token ID | 1081 |
Feature activation | -3.91e-03 |
Pos logit contributions | |
pengu | +0.005 |
monkey | +0.004 |
hipp | +0.004 |
wo | +0.004 |
clown | +0.004 |
Neg logit contributions | |
icia | -0.005 |
basement | -0.005 |
icker | -0.005 |
arse | -0.005 |
ifying | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -9.11e-03 |
Pos logit contributions | |
icker | +0.010 |
icia | +0.010 |
ifying | +0.010 |
basement | +0.010 |
arse | +0.009 |
Neg logit contributions | |
pengu | -0.005 |
hipp | -0.004 |
monkey | -0.004 |
clown | -0.004 |
gir | -0.004 |
Token | farmer |
Token ID | 18739 |
Feature activation | -4.27e-03 |
Pos logit contributions | |
icia | +0.018 |
icker | +0.018 |
basement | +0.018 |
ifying | +0.018 |
Jessica | +0.017 |
Neg logit contributions | |
pengu | -0.015 |
hipp | -0.013 |
wo | -0.013 |
monkey | -0.012 |
gir | -0.012 |
Token | scattered |
Token ID | 16830 |
Feature activation | +9.13e-03 |
Pos logit contributions | |
icia | +0.009 |
basement | +0.009 |
ifying | +0.009 |
icker | +0.009 |
Jessica | +0.008 |
Neg logit contributions | |
pengu | -0.007 |
wo | -0.005 |
hipp | -0.005 |
monkey | -0.005 |
clown | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
pengu | +0.017 |
hipp | +0.015 |
wo | +0.015 |
monkey | +0.014 |
clown | +0.014 |
Neg logit contributions | |
icia | -0.016 |
icker | -0.016 |
basement | -0.016 |
ifying | -0.016 |
Jessica | -0.015 |
Token | av |
Token ID | 1196 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
icia | +0.028 |
icker | +0.027 |
basement | +0.027 |
ifying | +0.027 |
Jessica | +0.025 |
Neg logit contributions | |
pengu | -0.026 |
hipp | -0.022 |
monkey | -0.022 |
wo | -0.021 |
gir | -0.021 |
Token | oc |
Token ID | 420 |
Feature activation | -6.11e-03 |
Pos logit contributions | |
basement | +0.141 |
icia | +0.140 |
icker | +0.139 |
ifying | +0.138 |
Jessica | +0.133 |
Neg logit contributions | |
pengu | -0.055 |
wo | -0.041 |
monkey | -0.040 |
hipp | -0.039 |
gir | -0.038 |
Token | ados |
Token ID | 22484 |
Feature activation | -1.56e-02 |
Pos logit contributions | |
icia | +0.010 |
icker | +0.010 |
ifying | +0.010 |
basement | +0.010 |
igsaw | +0.009 |
Neg logit contributions | |
pengu | -0.012 |
wo | -0.010 |
monkey | -0.010 |
clown | -0.010 |
hipp | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -6.04e-04 |
Pos logit contributions | |
icia | +0.033 |
icker | +0.032 |
basement | +0.032 |
ifying | +0.032 |
Jessica | +0.031 |
Neg logit contributions | |
pengu | -0.025 |
hipp | -0.020 |
monkey | -0.020 |
wo | -0.020 |
gir | -0.019 |
Token | he |
Token ID | 339 |
Feature activation | -7.64e-03 |
Pos logit contributions | |
icker | +0.001 |
icia | +0.001 |
basement | +0.001 |
ifying | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
wo | -0.001 |
gir | -0.001 |
Token | noticed |
Token ID | 6810 |
Feature activation | -4.20e-03 |
Pos logit contributions | |
icia | +0.015 |
ifying | +0.014 |
icker | +0.014 |
basement | +0.014 |
Jessica | +0.013 |
Neg logit contributions | |
pengu | -0.013 |
wo | -0.012 |
hipp | -0.011 |
monkey | -0.011 |
clown | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | -8.60e-04 |
Pos logit contributions | |
pengu | +0.003 |
monkey | +0.003 |
wo | +0.003 |
gir | +0.003 |
hipp | +0.003 |
Neg logit contributions | |
ifying | -0.005 |
icia | -0.005 |
icker | -0.005 |
basement | -0.005 |
igsaw | -0.005 |
Token | takes |
Token ID | 2753 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
icia | +0.002 |
basement | +0.002 |
icker | +0.001 |
ifying | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.002 |
hipp | -0.001 |
wo | -0.001 |
monkey | -0.001 |
clown | -0.001 |
Token | out |
Token ID | 503 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
pengu | +0.004 |
monkey | +0.003 |
wo | +0.003 |
clown | +0.003 |
hipp | +0.003 |
Neg logit contributions | |
ifying | -0.004 |
basement | -0.003 |
icker | -0.003 |
icia | -0.003 |
arse | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -2.23e-03 |
Pos logit contributions | |
pengu | +0.020 |
monkey | +0.017 |
hipp | +0.016 |
gir | +0.016 |
clown | +0.016 |
Neg logit contributions | |
icia | -0.023 |
ifying | -0.023 |
icker | -0.022 |
basement | -0.022 |
arse | -0.021 |
Token | magn |
Token ID | 7842 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
icia | +0.005 |
icker | +0.004 |
ifying | +0.004 |
Kelly | +0.004 |
iper | +0.004 |
Neg logit contributions | |
pengu | -0.004 |
monkey | -0.004 |
gir | -0.003 |
hipp | -0.003 |
clown | -0.003 |
Token | ifying |
Token ID | 4035 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
basement | +0.009 |
icia | +0.008 |
icker | +0.007 |
Kelly | +0.006 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.044 |
wo | -0.040 |
monkey | -0.039 |
gir | -0.039 |
hipp | -0.038 |
Token | glass |
Token ID | 5405 |
Feature activation | -3.48e-03 |
Pos logit contributions | |
icia | +0.096 |
icker | +0.093 |
basement | +0.091 |
ifying | +0.090 |
Jessica | +0.087 |
Neg logit contributions | |
pengu | -0.101 |
hipp | -0.084 |
monkey | -0.084 |
wo | -0.083 |
clown | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +1.87e-03 |
Pos logit contributions | |
icia | +0.007 |
basement | +0.006 |
icker | +0.006 |
ifying | +0.006 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.006 |
wo | -0.005 |
hipp | -0.005 |
monkey | -0.005 |
clown | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | -3.39e-03 |
Pos logit contributions | |
pengu | +0.003 |
monkey | +0.002 |
wo | +0.002 |
hipp | +0.002 |
gir | +0.002 |
Neg logit contributions | |
icia | -0.004 |
ifying | -0.004 |
arse | -0.004 |
basement | -0.004 |
icker | -0.004 |
Token | looks |
Token ID | 3073 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
icia | +0.006 |
basement | +0.006 |
icker | +0.006 |
ifying | +0.006 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.006 |
hipp | -0.006 |
wo | -0.005 |
monkey | -0.005 |
clown | -0.005 |
Token | at |
Token ID | 379 |
Feature activation | -5.93e-03 |
Pos logit contributions | |
icia | +0.023 |
basement | +0.023 |
icker | +0.023 |
ifying | +0.023 |
Jessica | +0.021 |
Neg logit contributions | |
pengu | -0.023 |
hipp | -0.019 |
monkey | -0.019 |
wo | -0.019 |
clown | -0.018 |
Token | flashlight |
Token ID | 38371 |
Feature activation | -8.47e-03 |
Pos logit contributions | |
icia | +0.001 |
icker | +0.001 |
basement | +0.001 |
ifying | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
monkey | -0.001 |
hipp | -0.001 |
clown | -0.001 |
gir | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
icia | +0.015 |
basement | +0.015 |
ifying | +0.015 |
icker | +0.015 |
Jessica | +0.014 |
Neg logit contributions | |
pengu | -0.016 |
wo | -0.013 |
hipp | -0.013 |
monkey | -0.013 |
clown | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +9.93e-04 |
Pos logit contributions | |
icia | +0.029 |
basement | +0.029 |
ifying | +0.029 |
icker | +0.029 |
Jessica | +0.027 |
Neg logit contributions | |
pengu | -0.025 |
wo | -0.021 |
hipp | -0.020 |
monkey | -0.020 |
clown | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -1.80e-03 |
Pos logit contributions | |
pengu | +0.002 |
wo | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
gir | +0.001 |
Neg logit contributions | |
icia | -0.002 |
icker | -0.002 |
basement | -0.002 |
ifying | -0.002 |
Jessica | -0.002 |
Token | magn |
Token ID | 7842 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
icia | +0.003 |
icker | +0.003 |
basement | +0.003 |
ifying | +0.003 |
Jessica | +0.003 |
Neg logit contributions | |
pengu | -0.003 |
monkey | -0.003 |
hipp | -0.003 |
clown | -0.003 |
gir | -0.003 |
Token | ifying |
Token ID | 4035 |
Feature activation | -5.23e-02 |
Pos logit contributions | |
basement | +0.012 |
icia | +0.011 |
icker | +0.010 |
Kelly | +0.009 |
Jessica | +0.009 |
Neg logit contributions | |
pengu | -0.047 |
wo | -0.042 |
monkey | -0.042 |
hipp | -0.042 |
gir | -0.041 |
Token | glass |
Token ID | 5405 |
Feature activation | -5.31e-03 |
Pos logit contributions | |
icia | +0.091 |
icker | +0.089 |
basement | +0.087 |
ifying | +0.086 |
Jessica | +0.082 |
Neg logit contributions | |
pengu | -0.104 |
hipp | -0.087 |
wo | -0.087 |
monkey | -0.086 |
clown | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
icia | +0.010 |
icker | +0.009 |
basement | +0.009 |
ifying | +0.009 |
Jessica | +0.009 |
Neg logit contributions | |
pengu | -0.010 |
hipp | -0.009 |
monkey | -0.008 |
wo | -0.008 |
clown | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e-03 |
Pos logit contributions | |
icia | +0.002 |
icker | +0.002 |
basement | +0.002 |
arse | +0.002 |
ifying | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
monkey | -0.002 |
hipp | -0.002 |
wo | -0.002 |
gir | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.69e-03 |
Pos logit contributions | |
ifying | +0.003 |
icia | +0.003 |
basement | +0.002 |
arse | +0.002 |
icker | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.001 |
monkey | -0.001 |
hipp | -0.001 |
clown | -0.001 |
Token | As |
Token ID | 1722 |
Feature activation | +2.44e-04 |
Pos logit contributions | |
icia | +0.003 |
ifying | +0.003 |
basement | +0.003 |
icker | +0.003 |
arse | +0.003 |
Neg logit contributions | |
pengu | -0.003 |
monkey | -0.002 |
wo | -0.002 |
hipp | -0.002 |
clown | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +9.61e-03 |
Pos logit contributions | |
icia | +0.036 |
basement | +0.035 |
icker | +0.035 |
ifying | +0.035 |
Jessica | +0.033 |
Neg logit contributions | |
pengu | -0.022 |
wo | -0.017 |
hipp | -0.017 |
monkey | -0.017 |
gir | -0.016 |
Token | try |
Token ID | 1949 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
pengu | +0.017 |
wo | +0.014 |
monkey | +0.014 |
hipp | +0.013 |
gir | +0.013 |
Neg logit contributions | |
icia | -0.019 |
icker | -0.019 |
basement | -0.019 |
ifying | -0.019 |
Jessica | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -4.47e-03 |
Pos logit contributions | |
icia | +0.022 |
ifying | +0.022 |
icker | +0.022 |
basement | +0.022 |
Jessica | +0.021 |
Neg logit contributions | |
pengu | -0.019 |
hipp | -0.016 |
monkey | -0.016 |
wo | -0.016 |
clown | -0.015 |
Token | grab |
Token ID | 5552 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
ifying | +0.009 |
basement | +0.009 |
icia | +0.009 |
icker | +0.009 |
Jessica | +0.008 |
Neg logit contributions | |
pengu | -0.008 |
wo | -0.007 |
monkey | -0.007 |
hipp | -0.007 |
clown | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -4.28e-03 |
Pos logit contributions | |
basement | +0.013 |
icia | +0.013 |
icker | +0.013 |
Jessica | +0.013 |
Kelly | +0.013 |
Neg logit contributions | |
pengu | -0.012 |
hipp | -0.010 |
monkey | -0.010 |
wo | -0.010 |
clown | -0.010 |
Token | av |
Token ID | 1196 |
Feature activation | -5.20e-02 |
Pos logit contributions | |
ifying | +0.008 |
basement | +0.008 |
icia | +0.008 |
icker | +0.008 |
diary | +0.007 |
Neg logit contributions | |
pengu | -0.007 |
wo | -0.006 |
monkey | -0.006 |
hipp | -0.006 |
clown | -0.006 |
Token | oc |
Token ID | 420 |
Feature activation | -6.84e-03 |
Pos logit contributions | |
icia | +0.131 |
basement | +0.130 |
icker | +0.130 |
ifying | +0.129 |
Jessica | +0.123 |
Neg logit contributions | |
pengu | -0.060 |
wo | -0.045 |
hipp | -0.044 |
monkey | -0.044 |
gir | -0.041 |
Token | ados |
Token ID | 22484 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
icia | +0.010 |
icker | +0.010 |
ifying | +0.010 |
basement | +0.010 |
igsaw | +0.010 |
Neg logit contributions | |
pengu | -0.014 |
wo | -0.012 |
clown | -0.012 |
monkey | -0.012 |
hipp | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +7.01e-03 |
Pos logit contributions | |
icker | +0.021 |
icia | +0.021 |
basement | +0.021 |
ifying | +0.021 |
Jessica | +0.021 |
Neg logit contributions | |
pengu | -0.016 |
hipp | -0.013 |
monkey | -0.013 |
gir | -0.012 |
wo | -0.012 |
Token | But |
Token ID | 887 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
pengu | +0.013 |
monkey | +0.010 |
hipp | +0.010 |
wo | +0.010 |
clown | +0.010 |
Neg logit contributions | |
icia | -0.014 |
basement | -0.014 |
arse | -0.013 |
ifying | -0.013 |
diary | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -9.80e-04 |
Pos logit contributions | |
pengu | +0.023 |
hipp | +0.019 |
monkey | +0.019 |
wo | +0.019 |
clown | +0.019 |
Neg logit contributions | |
icia | -0.021 |
icker | -0.020 |
basement | -0.020 |
ifying | -0.020 |
Jessica | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +5.46e-03 |
Pos logit contributions | |
pengu | +0.007 |
wo | +0.006 |
hipp | +0.006 |
monkey | +0.006 |
clown | +0.006 |
Neg logit contributions | |
icia | -0.006 |
icker | -0.006 |
basement | -0.006 |
ifying | -0.006 |
Jessica | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | -9.13e-04 |
Pos logit contributions | |
pengu | +0.010 |
monkey | +0.009 |
hipp | +0.009 |
wo | +0.009 |
gir | +0.008 |
Neg logit contributions | |
icia | -0.010 |
icker | -0.010 |
ifying | -0.009 |
basement | -0.009 |
iper | -0.009 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.85e-03 |
Pos logit contributions | |
icia | +0.002 |
basement | +0.002 |
icker | +0.002 |
Jessica | +0.002 |
Jessica | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
clown | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +1.99e-03 |
Pos logit contributions | |
pengu | +0.012 |
wo | +0.010 |
hipp | +0.010 |
monkey | +0.010 |
gir | +0.009 |
Neg logit contributions | |
basement | -0.009 |
icia | -0.009 |
icker | -0.009 |
ifying | -0.009 |
diary | -0.008 |
Token | eat |
Token ID | 4483 |
Feature activation | +3.78e-03 |
Pos logit contributions | |
pengu | +0.004 |
wo | +0.003 |
hipp | +0.003 |
monkey | +0.003 |
gir | +0.003 |
Neg logit contributions | |
icia | -0.004 |
ifying | -0.004 |
icker | -0.004 |
basement | -0.004 |
Jessica | -0.003 |
Token | av |
Token ID | 1196 |
Feature activation | -5.11e-02 |
Pos logit contributions | |
pengu | +0.006 |
wo | +0.006 |
hipp | +0.005 |
monkey | +0.005 |
haw | +0.005 |
Neg logit contributions | |
icia | -0.007 |
basement | -0.007 |
icker | -0.007 |
ifying | -0.007 |
diary | -0.006 |
Token | oc |
Token ID | 420 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
icia | +0.116 |
icker | +0.114 |
ifying | +0.114 |
basement | +0.113 |
Jessica | +0.108 |
Neg logit contributions | |
pengu | -0.071 |
hipp | -0.056 |
wo | -0.054 |
monkey | -0.052 |
clown | -0.052 |
Token | ados |
Token ID | 22484 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
icia | +0.014 |
icker | +0.014 |
igsaw | +0.014 |
iper | +0.013 |
.' | +0.013 |
Neg logit contributions | |
pengu | -0.026 |
hipp | -0.021 |
wo | -0.021 |
monkey | -0.021 |
clown | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
icia | +0.031 |
icker | +0.030 |
basement | +0.030 |
ifying | +0.030 |
Jessica | +0.028 |
Neg logit contributions | |
pengu | -0.026 |
hipp | -0.021 |
monkey | -0.021 |
wo | -0.021 |
gir | -0.021 |
Token | One |
Token ID | 1881 |
Feature activation | -4.73e-03 |
Pos logit contributions | |
pengu | +0.002 |
monkey | +0.002 |
hipp | +0.002 |
gir | +0.002 |
clown | +0.002 |
Neg logit contributions | |
ifying | -0.003 |
icker | -0.003 |
icia | -0.003 |
basement | -0.002 |
arse | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
icia | +0.007 |
icker | +0.007 |
basement | +0.007 |
ifying | +0.007 |
diary | +0.006 |
Neg logit contributions | |
pengu | -0.010 |
wo | -0.009 |
hipp | -0.009 |
monkey | -0.009 |
clown | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | -2.43e-03 |
Pos logit contributions | |
icia | +0.001 |
basement | +0.001 |
icker | +0.001 |
ifying | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.000 |
hipp | -0.000 |
monkey | -0.000 |
clown | -0.000 |
Token | I |
Token ID | 40 |
Feature activation | +1.68e-03 |
Pos logit contributions | |
icia | +0.005 |
icker | +0.005 |
basement | +0.005 |
ifying | +0.005 |
Jessica | +0.004 |
Neg logit contributions | |
pengu | -0.004 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
clown | -0.003 |
Token | will |
Token ID | 481 |
Feature activation | -1.20e-02 |
Pos logit contributions | |
pengu | +0.003 |
hipp | +0.003 |
wo | +0.003 |
monkey | +0.003 |
gir | +0.003 |
Neg logit contributions | |
icia | -0.003 |
icker | -0.003 |
ifying | -0.003 |
basement | -0.003 |
Jessica | -0.003 |
Token | buy |
Token ID | 2822 |
Feature activation | -1.38e-03 |
Pos logit contributions | |
icia | +0.021 |
icker | +0.020 |
ifying | +0.020 |
basement | +0.020 |
Jessica | +0.019 |
Neg logit contributions | |
pengu | -0.024 |
wo | -0.020 |
hipp | -0.020 |
monkey | -0.020 |
gir | -0.019 |
Token | more |
Token ID | 517 |
Feature activation | -5.76e-03 |
Pos logit contributions | |
icia | +0.002 |
icker | +0.002 |
basement | +0.002 |
ifying | +0.002 |
Jessica | +0.002 |
Neg logit contributions | |
pengu | -0.003 |
wo | -0.002 |
hipp | -0.002 |
monkey | -0.002 |
clown | -0.002 |
Token | av |
Token ID | 1196 |
Feature activation | -5.10e-02 |
Pos logit contributions | |
basement | +0.011 |
icia | +0.011 |
icker | +0.011 |
ifying | +0.011 |
Jessica | +0.010 |
Neg logit contributions | |
pengu | -0.010 |
wo | -0.008 |
hipp | -0.008 |
monkey | -0.008 |
gir | -0.008 |
Token | oc |
Token ID | 420 |
Feature activation | -6.18e-03 |
Pos logit contributions | |
icia | +0.121 |
icker | +0.120 |
ifying | +0.120 |
basement | +0.118 |
Jessica | +0.113 |
Neg logit contributions | |
pengu | -0.066 |
hipp | -0.050 |
wo | -0.049 |
monkey | -0.047 |
clown | -0.047 |
Token | ados |
Token ID | 22484 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
icia | +0.008 |
icker | +0.008 |
igsaw | +0.008 |
iper | +0.007 |
.' | +0.007 |
Neg logit contributions | |
pengu | -0.014 |
clown | -0.012 |
hipp | -0.012 |
wo | -0.011 |
monkey | -0.011 |
Token | tomorrow |
Token ID | 9439 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
icia | +0.019 |
basement | +0.018 |
ifying | +0.018 |
icker | +0.018 |
Jessica | +0.017 |
Neg logit contributions | |
pengu | -0.020 |
wo | -0.017 |
hipp | -0.016 |
monkey | -0.016 |
clown | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +5.75e-03 |
Pos logit contributions | |
icker | +0.045 |
ifying | +0.044 |
icia | +0.043 |
basement | +0.043 |
arse | +0.042 |
Neg logit contributions | |
pengu | -0.033 |
monkey | -0.027 |
hipp | -0.026 |
gir | -0.026 |
clown | -0.026 |
Token | You |
Token ID | 921 |
Feature activation | +9.95e-03 |
Pos logit contributions | |
pengu | +0.010 |
monkey | +0.009 |
hipp | +0.009 |
wo | +0.009 |
gir | +0.008 |
Neg logit contributions | |
icker | -0.011 |
icia | -0.011 |
basement | -0.011 |
arse | -0.010 |
ifying | -0.010 |
Token | recommendation |
Token ID | 15602 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
ifying | +0.008 |
icia | +0.008 |
icker | +0.008 |
basement | +0.007 |
Jessica | +0.007 |
Neg logit contributions | |
pengu | -0.007 |
monkey | -0.006 |
hipp | -0.006 |
gir | -0.006 |
wo | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +4.41e-03 |
Pos logit contributions | |
icker | +0.031 |
ifying | +0.030 |
icia | +0.030 |
basement | +0.030 |
arse | +0.028 |
Neg logit contributions | |
pengu | -0.023 |
monkey | -0.019 |
hipp | -0.019 |
wo | -0.018 |
clown | -0.018 |
Token | picked |
Token ID | 6497 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
pengu | +0.007 |
wo | +0.006 |
hipp | +0.006 |
monkey | +0.006 |
clown | +0.006 |
Neg logit contributions | |
icia | -0.009 |
icker | -0.009 |
basement | -0.009 |
ifying | -0.009 |
Jessica | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -7.65e-03 |
Pos logit contributions | |
pengu | +0.026 |
monkey | +0.023 |
hipp | +0.022 |
wo | +0.022 |
clown | +0.021 |
Neg logit contributions | |
icker | -0.026 |
basement | -0.026 |
ifying | -0.025 |
icia | -0.025 |
Jessica | -0.024 |
Token | right |
Token ID | 826 |
Feature activation | -2.54e-03 |
Pos logit contributions | |
icia | +0.014 |
basement | +0.014 |
ifying | +0.013 |
icker | +0.013 |
diary | +0.013 |
Neg logit contributions | |
pengu | -0.014 |
wo | -0.012 |
hipp | -0.012 |
monkey | -0.011 |
clown | -0.011 |
Token | av |
Token ID | 1196 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
icia | +0.005 |
icker | +0.005 |
basement | +0.005 |
ifying | +0.005 |
Jessica | +0.004 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
clown | -0.004 |
Token | oc |
Token ID | 420 |
Feature activation | -8.33e-03 |
Pos logit contributions | |
basement | +0.137 |
icia | +0.136 |
icker | +0.135 |
ifying | +0.134 |
Jessica | +0.129 |
Neg logit contributions | |
pengu | -0.051 |
wo | -0.038 |
monkey | -0.037 |
hipp | -0.035 |
gir | -0.035 |
Token | ados |
Token ID | 22484 |
Feature activation | -5.54e-03 |
Pos logit contributions | |
icia | +0.012 |
icker | +0.012 |
ifying | +0.012 |
basement | +0.012 |
igsaw | +0.012 |
Neg logit contributions | |
pengu | -0.018 |
wo | -0.015 |
clown | -0.014 |
hipp | -0.014 |
monkey | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -6.75e-03 |
Pos logit contributions | |
icker | +0.012 |
icia | +0.011 |
basement | +0.011 |
ifying | +0.011 |
Jessica | +0.011 |
Neg logit contributions | |
pengu | -0.009 |
hipp | -0.007 |
monkey | -0.007 |
wo | -0.007 |
gir | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -9.52e-04 |
Pos logit contributions | |
ifying | +0.013 |
icia | +0.013 |
icker | +0.013 |
basement | +0.013 |
arse | +0.012 |
Neg logit contributions | |
pengu | -0.012 |
monkey | -0.011 |
wo | -0.010 |
hipp | -0.010 |
gir | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -5.32e-04 |
Pos logit contributions | |
ifying | +0.002 |
icia | +0.002 |
basement | +0.002 |
icker | +0.002 |
arse | +0.001 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.002 |
monkey | -0.002 |
hipp | -0.002 |
clown | -0.002 |
Token | It |
Token ID | 632 |
Feature activation | +3.96e-03 |
Pos logit contributions | |
icker | +0.010 |
icia | +0.010 |
basement | +0.009 |
ifying | +0.009 |
arse | +0.009 |
Neg logit contributions | |
pengu | -0.009 |
monkey | -0.008 |
hipp | -0.008 |
wo | -0.008 |
clown | -0.007 |
Token | turned |
Token ID | 2900 |
Feature activation | -3.84e-03 |
Pos logit contributions | |
pengu | +0.007 |
wo | +0.006 |
hipp | +0.006 |
clown | +0.006 |
monkey | +0.006 |
Neg logit contributions | |
icia | -0.007 |
basement | -0.007 |
ifying | -0.007 |
icker | -0.007 |
diary | -0.007 |
Token | out |
Token ID | 503 |
Feature activation | +5.05e-03 |
Pos logit contributions | |
icia | +0.006 |
icker | +0.006 |
basement | +0.006 |
ifying | +0.005 |
Jessica | +0.005 |
Neg logit contributions | |
pengu | -0.008 |
hipp | -0.007 |
wo | -0.007 |
monkey | -0.007 |
gir | -0.007 |
Token | that |
Token ID | 326 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
pengu | +0.007 |
monkey | +0.005 |
hipp | +0.005 |
gir | +0.005 |
wo | +0.005 |
Neg logit contributions | |
icia | -0.012 |
icker | -0.012 |
basement | -0.012 |
ifying | -0.011 |
Jessica | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -9.11e-03 |
Pos logit contributions | |
icker | +0.027 |
ifying | +0.027 |
icia | +0.026 |
basement | +0.025 |
arse | +0.024 |
Neg logit contributions | |
pengu | -0.027 |
hipp | -0.023 |
monkey | -0.022 |
clown | -0.022 |
gir | -0.021 |
Token | av |
Token ID | 1196 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
icia | +0.021 |
icker | +0.021 |
ifying | +0.020 |
basement | +0.020 |
Jessica | +0.019 |
Neg logit contributions | |
pengu | -0.013 |
hipp | -0.011 |
monkey | -0.011 |
wo | -0.010 |
gir | -0.010 |
Token | oc |
Token ID | 420 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
icia | +0.132 |
basement | +0.132 |
icker | +0.131 |
ifying | +0.130 |
Jessica | +0.125 |
Neg logit contributions | |
pengu | -0.055 |
wo | -0.041 |
monkey | -0.040 |
hipp | -0.039 |
gir | -0.038 |
Token | ados |
Token ID | 22484 |
Feature activation | -8.93e-03 |
Pos logit contributions | |
icia | +0.015 |
icker | +0.015 |
ifying | +0.015 |
basement | +0.015 |
igsaw | +0.014 |
Neg logit contributions | |
pengu | -0.021 |
wo | -0.018 |
clown | -0.017 |
monkey | -0.017 |
hipp | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
icia | +0.019 |
basement | +0.019 |
icker | +0.019 |
ifying | +0.019 |
Jessica | +0.017 |
Neg logit contributions | |
pengu | -0.014 |
wo | -0.011 |
hipp | -0.011 |
monkey | -0.011 |
gir | -0.011 |
Token | bad |
Token ID | 2089 |
Feature activation | +7.18e-03 |
Pos logit contributions | |
pengu | +0.030 |
wo | +0.026 |
hipp | +0.025 |
monkey | +0.025 |
clown | +0.024 |
Neg logit contributions | |
icia | -0.028 |
ifying | -0.028 |
basement | -0.028 |
icker | -0.027 |
Jessica | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +4.53e-04 |
Pos logit contributions | |
pengu | +0.014 |
wo | +0.012 |
hipp | +0.012 |
monkey | +0.011 |
gir | +0.011 |
Neg logit contributions | |
icia | -0.012 |
basement | -0.012 |
icker | -0.012 |
ifying | -0.012 |
Jessica | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +5.76e-03 |
Pos logit contributions | |
pengu | +0.004 |
monkey | +0.003 |
wo | +0.003 |
hipp | +0.003 |
gir | +0.003 |
Neg logit contributions | |
icia | -0.004 |
icker | -0.004 |
basement | -0.004 |
ifying | -0.004 |
igsaw | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | -2.67e-04 |
Pos logit contributions | |
pengu | +0.011 |
monkey | +0.010 |
hipp | +0.009 |
wo | +0.009 |
gir | +0.009 |
Neg logit contributions | |
icia | -0.011 |
icker | -0.010 |
basement | -0.010 |
ifying | -0.010 |
arse | -0.009 |
Token | loved |
Token ID | 6151 |
Feature activation | +5.07e-03 |
Pos logit contributions | |
icia | +0.001 |
icker | +0.001 |
basement | +0.001 |
Jessica | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.000 |
wo | -0.000 |
hipp | -0.000 |
monkey | -0.000 |
gir | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +1.15e-03 |
Pos logit contributions | |
pengu | +0.010 |
wo | +0.009 |
hipp | +0.008 |
monkey | +0.008 |
gir | +0.008 |
Neg logit contributions | |
basement | -0.008 |
icia | -0.008 |
icker | -0.008 |
ifying | -0.008 |
Jessica | -0.007 |
Token | eat |
Token ID | 4483 |
Feature activation | +3.05e-03 |
Pos logit contributions | |
pengu | +0.002 |
wo | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icia | -0.002 |
ifying | -0.002 |
icker | -0.002 |
basement | -0.002 |
Jessica | -0.002 |
Token | av |
Token ID | 1196 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
pengu | +0.005 |
wo | +0.005 |
hipp | +0.004 |
monkey | +0.004 |
haw | +0.004 |
Neg logit contributions | |
icia | -0.006 |
basement | -0.006 |
icker | -0.005 |
ifying | -0.005 |
diary | -0.005 |
Token | oc |
Token ID | 420 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
icia | +0.115 |
icker | +0.113 |
ifying | +0.112 |
basement | +0.111 |
Jessica | +0.107 |
Neg logit contributions | |
pengu | -0.070 |
hipp | -0.055 |
wo | -0.053 |
monkey | -0.052 |
clown | -0.052 |
Token | ados |
Token ID | 22484 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
icia | +0.013 |
igsaw | +0.013 |
icker | +0.013 |
iper | +0.012 |
.' | +0.012 |
Neg logit contributions | |
pengu | -0.026 |
wo | -0.021 |
hipp | -0.021 |
monkey | -0.021 |
clown | -0.021 |
Token | because |
Token ID | 780 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
icia | +0.031 |
icker | +0.030 |
ifying | +0.030 |
basement | +0.030 |
Jessica | +0.029 |
Neg logit contributions | |
pengu | -0.026 |
hipp | -0.021 |
monkey | -0.021 |
wo | -0.021 |
gir | -0.020 |
Token | they |
Token ID | 484 |
Feature activation | -5.66e-03 |
Pos logit contributions | |
pengu | +0.024 |
hipp | +0.021 |
monkey | +0.021 |
wo | +0.020 |
gir | +0.020 |
Neg logit contributions | |
icia | -0.025 |
icker | -0.025 |
basement | -0.024 |
ifying | -0.024 |
arse | -0.023 |
Token | were |
Token ID | 547 |
Feature activation | +8.84e-04 |
Pos logit contributions | |
icia | +0.011 |
icker | +0.010 |
basement | +0.010 |
ifying | +0.010 |
?' | +0.009 |
Neg logit contributions | |
pengu | -0.010 |
wo | -0.009 |
monkey | -0.008 |
hipp | -0.008 |
haw | -0.008 |
Token | every |
Token ID | 790 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
icia | +0.004 |
icker | +0.004 |
ifying | +0.004 |
basement | +0.004 |
Jessica | +0.004 |
Neg logit contributions | |
pengu | -0.003 |
monkey | -0.003 |
hipp | -0.003 |
gir | -0.003 |
wo | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
icia | +0.038 |
icker | +0.038 |
ifying | +0.037 |
basement | +0.036 |
Jessica | +0.035 |
Neg logit contributions | |
pengu | -0.035 |
hipp | -0.030 |
monkey | -0.030 |
wo | -0.028 |
gir | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +2.62e-03 |
Pos logit contributions | |
basement | +0.052 |
icia | +0.051 |
icker | +0.051 |
ifying | +0.049 |
Jessica | +0.048 |
Neg logit contributions | |
pengu | -0.040 |
monkey | -0.032 |
hipp | -0.032 |
gir | -0.032 |
clown | -0.031 |
Token | supply |
Token ID | 5127 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
pengu | +0.005 |
hipp | +0.004 |
monkey | +0.004 |
gir | +0.004 |
wo | +0.004 |
Neg logit contributions | |
icker | -0.005 |
ifying | -0.005 |
icia | -0.005 |
basement | -0.005 |
Jessica | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -5.10e-03 |
Pos logit contributions | |
icia | +0.025 |
basement | +0.024 |
ifying | +0.024 |
icker | +0.024 |
Jessica | +0.023 |
Neg logit contributions | |
pengu | -0.024 |
hipp | -0.020 |
wo | -0.020 |
monkey | -0.020 |
clown | -0.019 |
Token | av |
Token ID | 1196 |
Feature activation | -4.96e-02 |
Pos logit contributions | |
icia | +0.009 |
basement | +0.009 |
icker | +0.009 |
ifying | +0.009 |
Jessica | +0.008 |
Neg logit contributions | |
pengu | -0.010 |
wo | -0.008 |
hipp | -0.008 |
monkey | -0.008 |
clown | -0.008 |
Token | oc |
Token ID | 420 |
Feature activation | -5.77e-03 |
Pos logit contributions | |
basement | +0.129 |
icia | +0.129 |
icker | +0.128 |
ifying | +0.127 |
Jessica | +0.121 |
Neg logit contributions | |
pengu | -0.054 |
wo | -0.040 |
monkey | -0.039 |
hipp | -0.039 |
gir | -0.037 |
Token | ados |
Token ID | 22484 |
Feature activation | -2.72e-03 |
Pos logit contributions | |
icia | +0.009 |
icker | +0.009 |
ifying | +0.008 |
basement | +0.008 |
igsaw | +0.008 |
Neg logit contributions | |
pengu | -0.012 |
wo | -0.010 |
clown | -0.010 |
hipp | -0.010 |
monkey | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -9.58e-04 |
Pos logit contributions | |
icia | +0.006 |
icker | +0.005 |
basement | +0.005 |
ifying | +0.005 |
Jessica | +0.005 |
Neg logit contributions | |
pengu | -0.005 |
hipp | -0.004 |
monkey | -0.004 |
wo | -0.004 |
gir | -0.003 |
Token | And |
Token ID | 843 |
Feature activation | +7.23e-03 |
Pos logit contributions | |
icia | +0.002 |
basement | +0.002 |
icker | +0.002 |
ifying | +0.002 |
arse | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
monkey | -0.002 |
hipp | -0.002 |
wo | -0.001 |
gir | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
pengu | +0.013 |
hipp | +0.011 |
monkey | +0.010 |
wo | +0.010 |
gir | +0.010 |
Neg logit contributions | |
icia | -0.014 |
icker | -0.014 |
basement | -0.014 |
ifying | -0.014 |
Jessica | -0.013 |
Token | who |
Token ID | 508 |
Feature activation | -7.51e-03 |
Pos logit contributions | |
icia | +0.011 |
ifying | +0.011 |
basement | +0.011 |
icker | +0.011 |
Jessica | +0.010 |
Neg logit contributions | |
pengu | -0.007 |
hipp | -0.005 |
monkey | -0.005 |
wo | -0.005 |
gir | -0.005 |
Token | liked |
Token ID | 8288 |
Feature activation | +7.50e-03 |
Pos logit contributions | |
icia | +0.018 |
icker | +0.018 |
basement | +0.018 |
ifying | +0.017 |
Jessica | +0.016 |
Neg logit contributions | |
pengu | -0.010 |
wo | -0.008 |
hipp | -0.008 |
monkey | -0.008 |
gir | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +7.28e-03 |
Pos logit contributions | |
pengu | +0.015 |
wo | +0.013 |
hipp | +0.012 |
monkey | +0.012 |
gir | +0.012 |
Neg logit contributions | |
basement | -0.012 |
icker | -0.012 |
icia | -0.012 |
ifying | -0.012 |
diary | -0.011 |
Token | collect |
Token ID | 2824 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
pengu | +0.014 |
wo | +0.012 |
hipp | +0.012 |
monkey | +0.012 |
gir | +0.011 |
Neg logit contributions | |
icia | -0.013 |
icker | -0.013 |
basement | -0.013 |
ifying | -0.012 |
Jessica | -0.012 |
Token | or |
Token ID | 393 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
pengu | +0.026 |
wo | +0.023 |
hipp | +0.022 |
monkey | +0.021 |
clown | +0.021 |
Neg logit contributions | |
basement | -0.024 |
icia | -0.024 |
icker | -0.024 |
ifying | -0.024 |
diary | -0.023 |
Token | nam |
Token ID | 7402 |
Feature activation | -4.91e-02 |
Pos logit contributions | |
icia | +0.015 |
icker | +0.014 |
ifying | +0.014 |
basement | +0.014 |
Jessica | +0.013 |
Neg logit contributions | |
pengu | -0.027 |
hipp | -0.023 |
monkey | -0.023 |
wo | -0.023 |
clown | -0.023 |
Token | ents |
Token ID | 658 |
Feature activation | +3.66e-04 |
Pos logit contributions | |
icker | +0.085 |
icia | +0.085 |
ifying | +0.084 |
basement | +0.082 |
Jessica | +0.078 |
Neg logit contributions | |
pengu | -0.095 |
hipp | -0.081 |
wo | -0.081 |
monkey | -0.080 |
clown | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-03 |
Pos logit contributions | |
pengu | +0.001 |
wo | +0.001 |
hipp | +0.001 |
monkey | +0.001 |
gir | +0.001 |
Neg logit contributions | |
icia | -0.001 |
icker | -0.001 |
basement | -0.001 |
ifying | -0.001 |
Jessica | -0.001 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
pengu | +0.006 |
monkey | +0.005 |
hipp | +0.005 |
gir | +0.005 |
wo | +0.005 |
Neg logit contributions | |
icia | -0.005 |
ifying | -0.005 |
icker | -0.005 |
arse | -0.005 |
basement | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | -9.55e-03 |
Pos logit contributions | |
icker | +0.034 |
icia | +0.034 |
ifying | +0.033 |
basement | +0.033 |
arse | +0.031 |
Neg logit contributions | |
pengu | -0.035 |
hipp | -0.029 |
monkey | -0.029 |
wo | -0.029 |
clown | -0.029 |
Token | went |
Token ID | 1816 |
Feature activation | -1.07e-03 |
Pos logit contributions | |
icia | +0.019 |
basement | +0.018 |
icker | +0.018 |
ifying | +0.017 |
diary | +0.017 |
Neg logit contributions | |
pengu | -0.016 |
wo | -0.014 |
hipp | -0.014 |
monkey | -0.013 |
clown | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -9.83e-03 |
Pos logit contributions | |
icia | +0.022 |
icker | +0.021 |
basement | +0.021 |
ifying | +0.021 |
Jessica | +0.020 |
Neg logit contributions | |
pengu | -0.019 |
monkey | -0.016 |
hipp | -0.016 |
gir | -0.015 |
wo | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +4.15e-03 |
Pos logit contributions | |
icia | +0.019 |
basement | +0.019 |
ifying | +0.019 |
icker | +0.018 |
Jessica | +0.018 |
Neg logit contributions | |
pengu | -0.017 |
wo | -0.014 |
hipp | -0.014 |
monkey | -0.013 |
clown | -0.013 |
Token | all |
Token ID | 477 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
pengu | +0.008 |
wo | +0.007 |
hipp | +0.006 |
monkey | +0.006 |
clown | +0.006 |
Neg logit contributions | |
icia | -0.007 |
basement | -0.007 |
ifying | -0.007 |
icker | -0.007 |
Jessica | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -8.41e-03 |
Pos logit contributions | |
pengu | +0.033 |
hipp | +0.027 |
wo | +0.026 |
monkey | +0.026 |
clown | +0.025 |
Neg logit contributions | |
icia | -0.037 |
icker | -0.037 |
basement | -0.036 |
ifying | -0.036 |
Jessica | -0.034 |
Token | other |
Token ID | 584 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
icia | +0.018 |
basement | +0.018 |
icker | +0.017 |
ifying | +0.017 |
Jessica | +0.017 |
Neg logit contributions | |
pengu | -0.012 |
wo | -0.011 |
hipp | -0.010 |
monkey | -0.010 |
gir | -0.009 |
Token | av |
Token ID | 1196 |
Feature activation | -4.90e-02 |
Pos logit contributions | |
pengu | +0.023 |
wo | +0.021 |
hipp | +0.019 |
monkey | +0.018 |
gir | +0.018 |
Neg logit contributions | |
icia | -0.031 |
basement | -0.030 |
icker | -0.030 |
ifying | -0.029 |
diary | -0.029 |
Token | oc |
Token ID | 420 |
Feature activation | -6.82e-03 |
Pos logit contributions | |
icia | +0.109 |
ifying | +0.108 |
icker | +0.108 |
basement | +0.105 |
iper | +0.104 |
Neg logit contributions | |
pengu | -0.069 |
hipp | -0.054 |
clown | -0.052 |
wo | -0.052 |
monkey | -0.050 |
Token | ados |
Token ID | 22484 |
Feature activation | -1.22e-02 |
Pos logit contributions | |
icker | +0.009 |
icia | +0.009 |
igsaw | +0.008 |
.' | +0.008 |
ifying | +0.008 |
Neg logit contributions | |
pengu | -0.016 |
wo | -0.013 |
clown | -0.013 |
hipp | -0.012 |
monkey | -0.012 |
Token | were |
Token ID | 547 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
icia | +0.024 |
basement | +0.024 |
icker | +0.023 |
ifying | +0.023 |
Jessica | +0.022 |
Neg logit contributions | |
pengu | -0.020 |
wo | -0.017 |
hipp | -0.017 |
monkey | -0.016 |
gir | -0.016 |
Token | very |
Token ID | 845 |
Feature activation | +1.71e-03 |
Pos logit contributions | |
pengu | +0.028 |
wo | +0.025 |
hipp | +0.023 |
monkey | +0.023 |
clown | +0.023 |
Neg logit contributions | |
icia | -0.024 |
ifying | -0.023 |
basement | -0.023 |
icker | -0.023 |
Jennifer | -0.022 |
Token | happy |
Token ID | 3772 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
pengu | +0.004 |
wo | +0.003 |
monkey | +0.003 |
hipp | +0.003 |
clown | +0.003 |
Neg logit contributions | |
icker | -0.003 |
icia | -0.002 |
ifying | -0.002 |
basement | -0.002 |
.' | -0.002 |
Token | still |
Token ID | 991 |
Feature activation | -3.97e-03 |
Pos logit contributions | |
pengu | +0.010 |
monkey | +0.008 |
hipp | +0.008 |
clown | +0.008 |
gir | +0.008 |
Neg logit contributions | |
icker | -0.014 |
ifying | -0.013 |
icia | -0.013 |
basement | -0.013 |
igsaw | -0.013 |
Token | couldn |
Token ID | 3521 |
Feature activation | +2.77e-03 |
Pos logit contributions | |
icker | +0.008 |
icia | +0.008 |
basement | +0.008 |
ifying | +0.008 |
igsaw | +0.008 |
Neg logit contributions | |
pengu | -0.006 |
monkey | -0.005 |
hipp | -0.005 |
clown | -0.005 |
gir | -0.005 |
Token | 't |
Token ID | 470 |
Feature activation | +2.61e-03 |
Pos logit contributions | |
pengu | +0.003 |
monkey | +0.003 |
hipp | +0.003 |
wo | +0.003 |
clown | +0.003 |
Neg logit contributions | |
icker | -0.007 |
icia | -0.006 |
basement | -0.006 |
ifying | -0.006 |
Jessica | -0.006 |
Token | find |
Token ID | 1064 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
pengu | +0.005 |
monkey | +0.004 |
hipp | +0.004 |
wo | +0.004 |
clown | +0.004 |
Neg logit contributions | |
ifying | -0.004 |
icia | -0.004 |
icker | -0.004 |
basement | -0.004 |
Jessica | -0.004 |
Token | any |
Token ID | 597 |
Feature activation | +4.14e-03 |
Pos logit contributions | |
pengu | +0.007 |
monkey | +0.006 |
hipp | +0.006 |
clown | +0.006 |
wo | +0.006 |
Neg logit contributions | |
icker | -0.008 |
icia | -0.007 |
ifying | -0.007 |
basement | -0.007 |
arse | -0.007 |
Token | av |
Token ID | 1196 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
pengu | +0.008 |
wo | +0.007 |
hipp | +0.006 |
monkey | +0.006 |
gir | +0.006 |
Neg logit contributions | |
basement | -0.007 |
icia | -0.007 |
ifying | -0.007 |
icker | -0.007 |
Jessica | -0.007 |
Token | oc |
Token ID | 420 |
Feature activation | -6.35e-03 |
Pos logit contributions | |
icia | +0.125 |
basement | +0.124 |
icker | +0.124 |
ifying | +0.122 |
Jessica | +0.117 |
Neg logit contributions | |
pengu | -0.055 |
wo | -0.042 |
monkey | -0.040 |
hipp | -0.040 |
gir | -0.038 |
Token | ados |
Token ID | 22484 |
Feature activation | -1.13e-02 |
Pos logit contributions | |
icia | +0.010 |
icker | +0.010 |
ifying | +0.010 |
basement | +0.009 |
igsaw | +0.009 |
Neg logit contributions | |
pengu | -0.013 |
wo | -0.011 |
hipp | -0.011 |
clown | -0.011 |
monkey | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -4.39e-03 |
Pos logit contributions | |
icker | +0.021 |
icia | +0.021 |
basement | +0.021 |
ifying | +0.020 |
Jessica | +0.019 |
Neg logit contributions | |
pengu | -0.021 |
hipp | -0.017 |
monkey | -0.017 |
wo | -0.017 |
gir | -0.016 |
Token | Finally |
Token ID | 9461 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
icia | +0.008 |
icker | +0.008 |
basement | +0.008 |
ifying | +0.008 |
arse | +0.008 |
Neg logit contributions | |
pengu | -0.008 |
monkey | -0.007 |
hipp | -0.006 |
wo | -0.006 |
clown | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.78e-03 |
Pos logit contributions | |
pengu | +0.029 |
hipp | +0.023 |
monkey | +0.023 |
clown | +0.022 |
wo | +0.022 |
Neg logit contributions | |
icker | -0.044 |
icia | -0.044 |
ifying | -0.043 |
basement | -0.043 |
Jessica | -0.041 |
Token | store |
Token ID | 3650 |
Feature activation | -9.91e-03 |
Pos logit contributions | |
icker | +0.004 |
icia | +0.004 |
ifying | +0.004 |
basement | +0.004 |
arse | +0.004 |
Neg logit contributions | |
pengu | -0.005 |
hipp | -0.004 |
monkey | -0.004 |
clown | -0.004 |
wo | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +9.86e-03 |
Pos logit contributions | |
icia | +0.021 |
icker | +0.021 |
ifying | +0.021 |
basement | +0.021 |
Jessica | +0.019 |
Neg logit contributions | |
pengu | -0.016 |
wo | -0.013 |
hipp | -0.013 |
monkey | -0.013 |
clown | -0.012 |
Token | forgot |
Token ID | 16453 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
pengu | +0.016 |
wo | +0.013 |
hipp | +0.013 |
monkey | +0.012 |
gir | +0.012 |
Neg logit contributions | |
icia | -0.021 |
basement | -0.021 |
icker | -0.021 |
ifying | -0.020 |
Jessica | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +4.92e-03 |
Pos logit contributions | |
pengu | +0.033 |
hipp | +0.027 |
monkey | +0.027 |
clown | +0.027 |
wo | +0.025 |
Neg logit contributions | |
icker | -0.043 |
icia | -0.043 |
ifying | -0.042 |
basement | -0.041 |
arse | -0.039 |
Token | buy |
Token ID | 2822 |
Feature activation | +2.03e-04 |
Pos logit contributions | |
pengu | +0.008 |
hipp | +0.007 |
wo | +0.007 |
monkey | +0.007 |
clown | +0.007 |
Neg logit contributions | |
ifying | -0.010 |
icker | -0.010 |
basement | -0.010 |
icia | -0.010 |
Jessica | -0.009 |
Token | av |
Token ID | 1196 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
pengu | +0.000 |
hipp | +0.000 |
wo | +0.000 |
monkey | +0.000 |
clown | +0.000 |
Neg logit contributions | |
icia | -0.000 |
icker | -0.000 |
basement | -0.000 |
ifying | -0.000 |
Jessica | -0.000 |
Token | oc |
Token ID | 420 |
Feature activation | -6.90e-03 |
Pos logit contributions | |
icia | +0.114 |
icker | +0.112 |
ifying | +0.112 |
basement | +0.110 |
Jessica | +0.106 |
Neg logit contributions | |
pengu | -0.065 |
hipp | -0.049 |
wo | -0.049 |
monkey | -0.047 |
clown | -0.047 |
Token | ados |
Token ID | 22484 |
Feature activation | -6.78e-03 |
Pos logit contributions | |
icia | +0.009 |
icker | +0.008 |
igsaw | +0.008 |
iper | +0.008 |
.' | +0.008 |
Neg logit contributions | |
pengu | -0.016 |
wo | -0.013 |
clown | -0.013 |
hipp | -0.013 |
monkey | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -4.45e-04 |
Pos logit contributions | |
icker | +0.014 |
icia | +0.014 |
basement | +0.014 |
ifying | +0.013 |
Jessica | +0.013 |
Neg logit contributions | |
pengu | -0.011 |
hipp | -0.009 |
monkey | -0.009 |
wo | -0.009 |
clown | -0.009 |
Token | Lily |
Token ID | 20037 |
Feature activation | -5.68e-03 |
Pos logit contributions | |
icia | +0.001 |
icker | +0.001 |
ifying | +0.001 |
basement | +0.001 |
arse | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
monkey | -0.001 |
wo | -0.001 |
hipp | -0.001 |
clown | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -1.00e-02 |
Pos logit contributions | |
icia | +0.012 |
basement | +0.011 |
icker | +0.010 |
Jessica | +0.010 |
Jessica | +0.010 |
Neg logit contributions | |
pengu | -0.010 |
wo | -0.009 |
hipp | -0.008 |
haw | -0.008 |
clown | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -3.09e-03 |
Pos logit contributions | |
pengu | +0.035 |
wo | +0.028 |
hipp | +0.028 |
monkey | +0.028 |
clown | +0.027 |
Neg logit contributions | |
icia | -0.048 |
icker | -0.048 |
ifying | -0.048 |
basement | -0.048 |
Jessica | -0.045 |
Token | shared |
Token ID | 4888 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
icia | +0.007 |
icker | +0.006 |
basement | +0.006 |
ifying | +0.006 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
gir | -0.004 |
Token | everything |
Token ID | 2279 |
Feature activation | +9.77e-03 |
Pos logit contributions | |
pengu | +0.025 |
monkey | +0.022 |
clown | +0.022 |
hipp | +0.021 |
wo | +0.021 |
Neg logit contributions | |
basement | -0.027 |
icia | -0.027 |
ifying | -0.027 |
icker | -0.027 |
arse | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
pengu | +0.018 |
wo | +0.015 |
hipp | +0.015 |
monkey | +0.015 |
clown | +0.015 |
Neg logit contributions | |
icia | -0.018 |
icker | -0.017 |
basement | -0.017 |
ifying | -0.017 |
Jessica | -0.016 |
Token | including |
Token ID | 1390 |
Feature activation | -8.40e-03 |
Pos logit contributions | |
icia | +0.025 |
basement | +0.025 |
icker | +0.024 |
Jessica | +0.024 |
Jennifer | +0.024 |
Neg logit contributions | |
pengu | -0.025 |
wo | -0.023 |
hipp | -0.021 |
monkey | -0.021 |
haw | -0.020 |
Token | av |
Token ID | 1196 |
Feature activation | -4.83e-02 |
Pos logit contributions | |
icia | +0.015 |
icker | +0.015 |
ifying | +0.015 |
basement | +0.015 |
Jessica | +0.014 |
Neg logit contributions | |
pengu | -0.016 |
hipp | -0.013 |
monkey | -0.013 |
wo | -0.013 |
clown | -0.013 |
Token | oc |
Token ID | 420 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
icia | +0.111 |
icker | +0.109 |
ifying | +0.109 |
basement | +0.106 |
iper | +0.103 |
Neg logit contributions | |
pengu | -0.065 |
hipp | -0.051 |
wo | -0.050 |
clown | -0.048 |
monkey | -0.047 |
Token | ados |
Token ID | 22484 |
Feature activation | -8.13e-03 |
Pos logit contributions | |
icia | +0.012 |
icker | +0.012 |
igsaw | +0.011 |
iper | +0.011 |
Jennifer | +0.011 |
Neg logit contributions | |
pengu | -0.022 |
wo | -0.018 |
monkey | -0.018 |
clown | -0.018 |
hipp | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -2.68e-03 |
Pos logit contributions | |
icia | +0.013 |
basement | +0.013 |
icker | +0.013 |
ifying | +0.013 |
diary | +0.012 |
Neg logit contributions | |
pengu | -0.016 |
wo | -0.014 |
hipp | -0.014 |
monkey | -0.014 |
clown | -0.013 |
Token | They |
Token ID | 1119 |
Feature activation | -8.25e-03 |
Pos logit contributions | |
ifying | +0.005 |
icker | +0.005 |
icia | +0.005 |
basement | +0.005 |
arse | +0.005 |
Neg logit contributions | |
pengu | -0.004 |
monkey | -0.004 |
hipp | -0.004 |
gir | -0.003 |
clown | -0.003 |
Token | were |
Token ID | 547 |
Feature activation | -2.23e-03 |
Pos logit contributions | |
icia | +0.016 |
icker | +0.016 |
basement | +0.015 |
ifying | +0.015 |
Jessica | +0.014 |
Neg logit contributions | |
pengu | -0.014 |
wo | -0.012 |
hipp | -0.012 |
monkey | -0.012 |
clown | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
icia | +0.024 |
ifying | +0.024 |
icker | +0.024 |
basement | +0.024 |
igsaw | +0.022 |
Neg logit contributions | |
pengu | -0.026 |
wo | -0.022 |
monkey | -0.022 |
hipp | -0.022 |
clown | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -6.93e-04 |
Pos logit contributions | |
pengu | +0.015 |
hipp | +0.011 |
monkey | +0.011 |
wo | +0.010 |
clown | +0.010 |
Neg logit contributions | |
icia | -0.033 |
icker | -0.032 |
ifying | -0.032 |
basement | -0.032 |
arse | -0.030 |
Token | said |
Token ID | 531 |
Feature activation | +3.69e-03 |
Pos logit contributions | |
icia | +0.001 |
icker | +0.001 |
basement | +0.001 |
Jessica | +0.001 |
ifying | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
gir | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -4.99e-03 |
Pos logit contributions | |
pengu | +0.007 |
wo | +0.006 |
hipp | +0.006 |
monkey | +0.006 |
gir | +0.005 |
Neg logit contributions | |
icker | -0.007 |
icia | -0.007 |
basement | -0.007 |
ifying | -0.007 |
Jessica | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | -2.44e-03 |
Pos logit contributions | |
icia | +0.011 |
basement | +0.011 |
icker | +0.011 |
ifying | +0.011 |
Jessica | +0.010 |
Neg logit contributions | |
pengu | -0.007 |
hipp | -0.006 |
wo | -0.006 |
monkey | -0.006 |
gir | -0.006 |
Token | That |
Token ID | 2504 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
icker | +0.005 |
icia | +0.005 |
basement | +0.005 |
ifying | +0.005 |
igsaw | +0.004 |
Neg logit contributions | |
pengu | -0.004 |
wo | -0.004 |
monkey | -0.003 |
hipp | -0.003 |
clown | -0.003 |
Token | 's |
Token ID | 338 |
Feature activation | +7.79e-03 |
Pos logit contributions | |
pengu | +0.047 |
monkey | +0.039 |
hipp | +0.038 |
wo | +0.038 |
clown | +0.038 |
Neg logit contributions | |
icker | -0.043 |
ifying | -0.043 |
icia | -0.042 |
basement | -0.041 |
Jessica | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
pengu | +0.011 |
monkey | +0.010 |
hipp | +0.009 |
clown | +0.009 |
gir | +0.009 |
Neg logit contributions | |
icker | -0.017 |
ifying | -0.017 |
basement | -0.016 |
icia | -0.016 |
arse | -0.016 |
Token | nice |
Token ID | 3621 |
Feature activation | -9.37e-04 |
Pos logit contributions | |
pengu | +0.022 |
monkey | +0.019 |
hipp | +0.018 |
wo | +0.018 |
clown | +0.018 |
Neg logit contributions | |
icia | -0.021 |
ifying | -0.021 |
icker | -0.021 |
basement | -0.021 |
Jessica | -0.020 |
Token | line |
Token ID | 1627 |
Feature activation | +3.30e-03 |
Pos logit contributions | |
ifying | +0.002 |
icia | +0.002 |
icker | +0.002 |
basement | +0.002 |
arse | +0.001 |
Neg logit contributions | |
pengu | -0.002 |
monkey | -0.002 |
hipp | -0.002 |
wo | -0.002 |
clown | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
pengu | +0.006 |
wo | +0.005 |
hipp | +0.005 |
monkey | +0.005 |
gir | +0.005 |
Neg logit contributions | |
icia | -0.006 |
basement | -0.006 |
ifying | -0.006 |
icker | -0.006 |
Jessica | -0.006 |
Token | others |
Token ID | 1854 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ifying | +0.029 |
icker | +0.029 |
icia | +0.028 |
basement | +0.028 |
Jessica | +0.026 |
Neg logit contributions | |
pengu | -0.029 |
hipp | -0.024 |
monkey | -0.024 |
wo | -0.024 |
clown | -0.023 |
Token | is |
Token ID | 318 |
Feature activation | +5.03e-04 |
Pos logit contributions | |
pengu | +0.020 |
wo | +0.017 |
hipp | +0.017 |
monkey | +0.017 |
clown | +0.016 |
Neg logit contributions | |
icia | -0.018 |
icker | -0.018 |
basement | -0.018 |
ifying | -0.017 |
Jessica | -0.016 |
Token | always |
Token ID | 1464 |
Feature activation | -6.14e-03 |
Pos logit contributions | |
pengu | +0.001 |
hipp | +0.001 |
monkey | +0.001 |
wo | +0.001 |
gir | +0.001 |
Neg logit contributions | |
ifying | -0.001 |
icker | -0.001 |
icia | -0.001 |
basement | -0.001 |
Jessica | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
icker | +0.013 |
icia | +0.013 |
ifying | +0.013 |
basement | +0.013 |
Jessica | +0.012 |
Neg logit contributions | |
pengu | -0.009 |
monkey | -0.008 |
hipp | -0.008 |
gir | -0.007 |
clown | -0.007 |
Token | right |
Token ID | 826 |
Feature activation | +1.88e-03 |
Pos logit contributions | |
pengu | +0.008 |
monkey | +0.007 |
hipp | +0.007 |
gir | +0.007 |
clown | +0.006 |
Neg logit contributions | |
icker | -0.010 |
ifying | -0.010 |
icia | -0.009 |
igsaw | -0.009 |
Jessica | -0.009 |
Token | thing |
Token ID | 1517 |
Feature activation | +2.53e-02 |
Pos logit contributions | |
pengu | +0.003 |
hipp | +0.002 |
monkey | +0.002 |
wo | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icker | -0.004 |
icia | -0.004 |
ifying | -0.004 |
basement | -0.004 |
Jessica | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +6.47e-03 |
Pos logit contributions | |
pengu | +0.044 |
hipp | +0.037 |
monkey | +0.036 |
wo | +0.036 |
clown | +0.035 |
Neg logit contributions | |
icia | -0.049 |
icker | -0.049 |
basement | -0.048 |
ifying | -0.048 |
Jessica | -0.045 |
Token | do |
Token ID | 466 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
pengu | +0.010 |
hipp | +0.009 |
monkey | +0.009 |
wo | +0.008 |
clown | +0.008 |
Neg logit contributions | |
ifying | -0.014 |
icia | -0.013 |
icker | -0.013 |
basement | -0.013 |
Jessica | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -5.13e-03 |
Pos logit contributions | |
ifying | +0.028 |
icker | +0.028 |
icia | +0.027 |
basement | +0.027 |
Kelly | +0.026 |
Neg logit contributions | |
pengu | -0.021 |
hipp | -0.017 |
monkey | -0.017 |
clown | -0.017 |
wo | -0.016 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.32e-03 |
Pos logit contributions | |
ifying | +0.010 |
icia | +0.010 |
basement | +0.010 |
icker | +0.009 |
arse | +0.009 |
Neg logit contributions | |
pengu | -0.009 |
monkey | -0.008 |
wo | -0.008 |
hipp | -0.008 |
gir | -0.007 |
Token | Once |
Token ID | 7454 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
icia | +0.005 |
icker | +0.005 |
ifying | +0.005 |
iper | +0.005 |
arse | +0.005 |
Neg logit contributions | |
pengu | -0.004 |
monkey | -0.003 |
wo | -0.003 |
hipp | -0.003 |
clown | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
icker | +0.000 |
icia | +0.000 |
Jessica | +0.000 |
ifying | +0.000 |
Kelly | +0.000 |
Neg logit contributions | |
pengu | -0.000 |
monkey | -0.000 |
hipp | -0.000 |
gir | -0.000 |
clown | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -4.62e-03 |
Pos logit contributions | |
basement | +0.028 |
icia | +0.028 |
ifying | +0.027 |
icker | +0.027 |
Jessica | +0.026 |
Neg logit contributions | |
pengu | -0.023 |
wo | -0.019 |
hipp | -0.019 |
monkey | -0.018 |
clown | -0.018 |
Token | there |
Token ID | 612 |
Feature activation | +5.60e-03 |
Pos logit contributions | |
icia | +0.008 |
icker | +0.008 |
basement | +0.008 |
ifying | +0.008 |
Jessica | +0.007 |
Neg logit contributions | |
pengu | -0.009 |
hipp | -0.008 |
wo | -0.008 |
monkey | -0.008 |
gir | -0.007 |
Token | were |
Token ID | 547 |
Feature activation | +1.74e-02 |
Pos logit contributions | |
pengu | +0.007 |
wo | +0.006 |
hipp | +0.005 |
monkey | +0.005 |
gir | +0.005 |
Neg logit contributions | |
icia | -0.013 |
basement | -0.013 |
icker | -0.013 |
ifying | -0.013 |
Jessica | -0.012 |
Token | no |
Token ID | 645 |
Feature activation | -3.01e-04 |
Pos logit contributions | |
pengu | +0.034 |
wo | +0.033 |
hipp | +0.029 |
monkey | +0.029 |
clown | +0.029 |
Neg logit contributions | |
basement | -0.028 |
ifying | -0.028 |
icia | -0.025 |
icker | -0.025 |
diary | -0.024 |
Token | other |
Token ID | 584 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
basement | +0.001 |
icker | +0.001 |
icia | +0.001 |
ifying | +0.001 |
diary | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.000 |
hipp | -0.000 |
monkey | -0.000 |
clown | -0.000 |
Token | animals |
Token ID | 4695 |
Feature activation | +8.82e-03 |
Pos logit contributions | |
pengu | +0.038 |
wo | +0.036 |
hipp | +0.030 |
haw | +0.030 |
clown | +0.029 |
Neg logit contributions | |
basement | -0.058 |
diary | -0.054 |
ifying | -0.054 |
icia | -0.054 |
icker | -0.053 |
Token | around |
Token ID | 1088 |
Feature activation | +7.07e-03 |
Pos logit contributions | |
pengu | +0.016 |
hipp | +0.013 |
monkey | +0.013 |
wo | +0.013 |
clown | +0.013 |
Neg logit contributions | |
icia | -0.017 |
icker | -0.017 |
basement | -0.016 |
ifying | -0.016 |
Jessica | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.33e-03 |
Pos logit contributions | |
pengu | +0.013 |
hipp | +0.011 |
monkey | +0.010 |
clown | +0.010 |
wo | +0.010 |
Neg logit contributions | |
icker | -0.014 |
icia | -0.014 |
ifying | -0.013 |
iper | -0.013 |
basement | -0.013 |
Token | The |
Token ID | 383 |
Feature activation | -4.86e-03 |
Pos logit contributions | |
icia | +0.003 |
ifying | +0.003 |
icker | +0.002 |
basement | +0.002 |
Jessica | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
monkey | -0.002 |
hipp | -0.002 |
wo | -0.002 |
gir | -0.002 |
Token | bird |
Token ID | 6512 |
Feature activation | +3.16e-04 |
Pos logit contributions | |
basement | +0.010 |
icia | +0.010 |
icker | +0.010 |
ifying | +0.010 |
diary | +0.010 |
Neg logit contributions | |
pengu | -0.007 |
wo | -0.006 |
hipp | -0.006 |
clown | -0.005 |
haw | -0.005 |
Token | his |
Token ID | 465 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
pengu | +0.018 |
hipp | +0.015 |
monkey | +0.014 |
clown | +0.014 |
wo | +0.014 |
Neg logit contributions | |
icker | -0.020 |
icia | -0.020 |
ifying | -0.020 |
basement | -0.019 |
Kelly | -0.018 |
Token | wife |
Token ID | 3656 |
Feature activation | +2.82e-03 |
Pos logit contributions | |
pengu | +0.010 |
monkey | +0.008 |
hipp | +0.008 |
clown | +0.008 |
gir | +0.008 |
Neg logit contributions | |
icia | -0.010 |
ifying | -0.010 |
icker | -0.010 |
basement | -0.010 |
Kelly | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +2.08e-03 |
Pos logit contributions | |
pengu | +0.005 |
monkey | +0.004 |
hipp | +0.004 |
gir | +0.004 |
clown | +0.004 |
Neg logit contributions | |
icker | -0.006 |
basement | -0.006 |
ifying | -0.006 |
icia | -0.006 |
igsaw | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | -4.49e-03 |
Pos logit contributions | |
pengu | +0.003 |
wo | +0.003 |
hipp | +0.003 |
monkey | +0.003 |
gir | +0.003 |
Neg logit contributions | |
icia | -0.004 |
basement | -0.004 |
icker | -0.004 |
ifying | -0.004 |
Jessica | -0.004 |
Token | found |
Token ID | 1043 |
Feature activation | -4.26e-03 |
Pos logit contributions | |
icia | +0.009 |
basement | +0.009 |
ifying | +0.009 |
icker | +0.009 |
Jessica | +0.008 |
Neg logit contributions | |
pengu | -0.007 |
wo | -0.006 |
hipp | -0.006 |
monkey | -0.006 |
gir | -0.006 |
Token | out |
Token ID | 503 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
icker | +0.008 |
icia | +0.008 |
ifying | +0.007 |
basement | +0.007 |
arse | +0.007 |
Neg logit contributions | |
pengu | -0.008 |
hipp | -0.007 |
monkey | -0.007 |
wo | -0.007 |
clown | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
pengu | +0.037 |
monkey | +0.030 |
clown | +0.030 |
hipp | +0.030 |
wo | +0.029 |
Neg logit contributions | |
icia | -0.045 |
icker | -0.045 |
basement | -0.044 |
ifying | -0.042 |
arse | -0.041 |
Token | The |
Token ID | 383 |
Feature activation | -6.19e-03 |
Pos logit contributions | |
icia | +0.006 |
icker | +0.006 |
ifying | +0.006 |
basement | +0.006 |
arse | +0.006 |
Neg logit contributions | |
pengu | -0.006 |
monkey | -0.005 |
hipp | -0.005 |
wo | -0.005 |
clown | -0.005 |
Token | pistol |
Token ID | 16790 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
basement | +0.014 |
icia | +0.014 |
icker | +0.014 |
ifying | +0.014 |
Jessica | +0.013 |
Neg logit contributions | |
pengu | -0.009 |
wo | -0.007 |
hipp | -0.007 |
monkey | -0.006 |
gir | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -3.13e-03 |
Pos logit contributions | |
pengu | +0.020 |
wo | +0.017 |
hipp | +0.016 |
monkey | +0.016 |
gir | +0.015 |
Neg logit contributions | |
icia | -0.024 |
basement | -0.024 |
ifying | -0.022 |
icker | -0.022 |
diary | -0.022 |
Token | gone |
Token ID | 3750 |
Feature activation | -5.38e-03 |
Pos logit contributions | |
icia | +0.005 |
basement | +0.005 |
icker | +0.005 |
ifying | +0.005 |
Jessica | +0.005 |
Neg logit contributions | |
pengu | -0.006 |
wo | -0.005 |
hipp | -0.005 |
monkey | -0.005 |
gir | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
icia | +0.004 |
icker | +0.004 |
basement | +0.004 |
ifying | +0.003 |
Jessica | +0.003 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
gir | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e-03 |
Pos logit contributions | |
icker | +0.025 |
ifying | +0.025 |
icia | +0.025 |
basement | +0.025 |
Jessica | +0.023 |
Neg logit contributions | |
pengu | -0.027 |
wo | -0.023 |
hipp | -0.023 |
monkey | -0.022 |
gir | -0.022 |
Token | Lily |
Token ID | 20037 |
Feature activation | -8.81e-03 |
Pos logit contributions | |
pengu | +0.003 |
hipp | +0.002 |
wo | +0.002 |
monkey | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icia | -0.003 |
basement | -0.003 |
icker | -0.003 |
ifying | -0.003 |
Jessica | -0.003 |
Token | saw |
Token ID | 2497 |
Feature activation | -6.40e-03 |
Pos logit contributions | |
icia | +0.015 |
basement | +0.015 |
icker | +0.013 |
Jessica | +0.013 |
Kelly | +0.013 |
Neg logit contributions | |
pengu | -0.018 |
wo | -0.016 |
hipp | -0.015 |
haw | -0.015 |
clown | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +6.95e-03 |
Pos logit contributions | |
basement | +0.010 |
icia | +0.009 |
icker | +0.009 |
ifying | +0.009 |
Kelly | +0.009 |
Neg logit contributions | |
pengu | -0.014 |
wo | -0.013 |
hipp | -0.012 |
monkey | -0.012 |
gir | -0.012 |
Token | sad |
Token ID | 6507 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
pengu | +0.012 |
wo | +0.010 |
hipp | +0.010 |
monkey | +0.010 |
gir | +0.010 |
Neg logit contributions | |
icia | -0.013 |
basement | -0.013 |
icker | -0.013 |
ifying | -0.013 |
Jessica | -0.012 |
Token | puppy |
Token ID | 26188 |
Feature activation | +4.20e-03 |
Pos logit contributions | |
pengu | +0.045 |
wo | +0.039 |
hipp | +0.035 |
haw | +0.035 |
monkey | +0.034 |
Neg logit contributions | |
icker | -0.061 |
basement | -0.061 |
icia | -0.061 |
diary | -0.058 |
ifying | -0.057 |
Token | in |
Token ID | 287 |
Feature activation | +2.72e-02 |
Pos logit contributions | |
pengu | +0.008 |
wo | +0.007 |
hipp | +0.007 |
monkey | +0.007 |
clown | +0.006 |
Neg logit contributions | |
icia | -0.007 |
basement | -0.007 |
icker | -0.007 |
ifying | -0.007 |
Jessica | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
pengu | +0.048 |
monkey | +0.039 |
clown | +0.039 |
hipp | +0.038 |
gir | +0.037 |
Neg logit contributions | |
icker | -0.059 |
icia | -0.055 |
arse | -0.054 |
ifying | -0.054 |
leys | -0.051 |
Token | cage |
Token ID | 17186 |
Feature activation | +4.74e-03 |
Pos logit contributions | |
pengu | +0.014 |
monkey | +0.012 |
hipp | +0.012 |
clown | +0.011 |
gir | +0.011 |
Neg logit contributions | |
icia | -0.017 |
icker | -0.016 |
ifying | -0.016 |
arse | -0.015 |
iper | -0.015 |
Token | at |
Token ID | 379 |
Feature activation | +4.71e-03 |
Pos logit contributions | |
pengu | +0.008 |
monkey | +0.007 |
wo | +0.007 |
hipp | +0.007 |
gir | +0.007 |
Neg logit contributions | |
icia | -0.009 |
icker | -0.009 |
ifying | -0.009 |
basement | -0.009 |
Jessica | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | -9.62e-04 |
Pos logit contributions | |
pengu | +0.003 |
monkey | +0.003 |
hipp | +0.002 |
wo | +0.002 |
gir | +0.002 |
Neg logit contributions | |
icia | -0.005 |
ifying | -0.005 |
icker | -0.005 |
basement | -0.005 |
igsaw | -0.005 |
Token | Maybe |
Token ID | 13300 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
icia | +0.002 |
basement | +0.002 |
ifying | +0.002 |
icker | +0.002 |
iper | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.002 |
monkey | -0.001 |
hipp | -0.001 |
clown | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | +8.13e-03 |
Pos logit contributions | |
pengu | +0.020 |
monkey | +0.017 |
hipp | +0.017 |
clown | +0.016 |
wo | +0.016 |
Neg logit contributions | |
icker | -0.021 |
icia | -0.021 |
ifying | -0.020 |
basement | -0.020 |
arse | -0.019 |
Token | 's |
Token ID | 338 |
Feature activation | +2.76e-03 |
Pos logit contributions | |
pengu | +0.017 |
wo | +0.015 |
hipp | +0.015 |
monkey | +0.014 |
clown | +0.014 |
Neg logit contributions | |
icia | -0.013 |
basement | -0.013 |
ifying | -0.012 |
icker | -0.012 |
diary | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +7.91e-03 |
Pos logit contributions | |
pengu | +0.005 |
hipp | +0.004 |
monkey | +0.004 |
clown | +0.004 |
gir | +0.004 |
Neg logit contributions | |
icker | -0.006 |
icia | -0.006 |
ifying | -0.006 |
igsaw | -0.005 |
Jessica | -0.005 |
Token | jungle |
Token ID | 20712 |
Feature activation | -1.25e-03 |
Pos logit contributions | |
pengu | +0.014 |
hipp | +0.012 |
wo | +0.012 |
monkey | +0.012 |
clown | +0.011 |
Neg logit contributions | |
icia | -0.015 |
icker | -0.015 |
ifying | -0.015 |
basement | -0.015 |
Jessica | -0.014 |
Token | cat |
Token ID | 3797 |
Feature activation | +4.59e-03 |
Pos logit contributions | |
icia | +0.002 |
basement | +0.002 |
icker | +0.002 |
ifying | +0.002 |
Jessica | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.002 |
hipp | -0.002 |
monkey | -0.002 |
clown | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
pengu | +0.009 |
hipp | +0.007 |
wo | +0.007 |
monkey | +0.007 |
gir | +0.007 |
Neg logit contributions | |
icia | -0.008 |
icker | -0.008 |
ifying | -0.008 |
basement | -0.008 |
Jessica | -0.008 |
Token | It |
Token ID | 632 |
Feature activation | +9.92e-03 |
Pos logit contributions | |
pengu | +0.014 |
monkey | +0.012 |
hipp | +0.011 |
wo | +0.011 |
gir | +0.011 |
Neg logit contributions | |
icia | -0.017 |
icker | -0.016 |
basement | -0.016 |
arse | -0.015 |
igsaw | -0.015 |
Token | looks |
Token ID | 3073 |
Feature activation | +1.20e-03 |
Pos logit contributions | |
pengu | +0.020 |
wo | +0.019 |
clown | +0.018 |
hipp | +0.017 |
monkey | +0.017 |
Neg logit contributions | |
basement | -0.014 |
icia | -0.014 |
ifying | -0.014 |
Margaret | -0.012 |
icker | -0.012 |
Token | scary |
Token ID | 14343 |
Feature activation | -1.02e-02 |
Pos logit contributions | |
pengu | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
wo | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icia | -0.003 |
icker | -0.003 |
basement | -0.002 |
ifying | -0.002 |
Jessica | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | -3.73e-03 |
Pos logit contributions | |
pengu | +0.002 |
wo | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
gir | +0.002 |
Neg logit contributions | |
icia | -0.002 |
basement | -0.002 |
icker | -0.002 |
ifying | -0.002 |
Jessica | -0.002 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.17e-03 |
Pos logit contributions | |
icia | +0.007 |
basement | +0.007 |
icker | +0.006 |
ifying | +0.006 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.007 |
wo | -0.006 |
monkey | -0.006 |
hipp | -0.006 |
gir | -0.006 |
Token | too |
Token ID | 1165 |
Feature activation | -1.51e-04 |
Pos logit contributions | |
pengu | +0.005 |
wo | +0.005 |
haw | +0.004 |
hipp | +0.004 |
gir | +0.004 |
Neg logit contributions | |
basement | -0.003 |
icker | -0.003 |
Jessica | -0.002 |
icia | -0.002 |
ifying | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +4.59e-03 |
Pos logit contributions | |
icia | +0.000 |
basement | +0.000 |
ifying | +0.000 |
icker | +0.000 |
Jessica | +0.000 |
Neg logit contributions | |
pengu | -0.000 |
hipp | -0.000 |
wo | -0.000 |
monkey | -0.000 |
clown | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | +2.37e-03 |
Pos logit contributions | |
pengu | +0.008 |
hipp | +0.007 |
clown | +0.007 |
monkey | +0.006 |
wo | +0.006 |
Neg logit contributions | |
icia | -0.009 |
arse | -0.009 |
icker | -0.009 |
basement | -0.009 |
iper | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +2.19e-03 |
Pos logit contributions | |
pengu | +0.005 |
wo | +0.005 |
hipp | +0.005 |
monkey | +0.005 |
clown | +0.005 |
Neg logit contributions | |
icia | -0.003 |
ifying | -0.003 |
basement | -0.003 |
icker | -0.003 |
Jessica | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | +7.13e-03 |
Pos logit contributions | |
pengu | +0.004 |
wo | +0.004 |
hipp | +0.004 |
monkey | +0.004 |
clown | +0.004 |
Neg logit contributions | |
icia | -0.004 |
icker | -0.004 |
basement | -0.004 |
ifying | -0.004 |
Jessica | -0.003 |
Token | Let |
Token ID | 5756 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
pengu | +0.014 |
hipp | +0.012 |
monkey | +0.012 |
wo | +0.012 |
gir | +0.011 |
Neg logit contributions | |
ifying | -0.012 |
icia | -0.012 |
Jessica | -0.012 |
basement | -0.012 |
icker | -0.011 |
Token | 's |
Token ID | 338 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
pengu | +0.003 |
wo | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icia | -0.002 |
icker | -0.002 |
basement | -0.002 |
ifying | -0.002 |
Jessica | -0.002 |
Token | make |
Token ID | 787 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
icker | +0.039 |
ifying | +0.039 |
Jessica | +0.038 |
Kelly | +0.038 |
icia | +0.038 |
Neg logit contributions | |
pengu | -0.028 |
hipp | -0.023 |
monkey | -0.022 |
clown | -0.022 |
wo | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ifying | +0.025 |
icker | +0.025 |
basement | +0.025 |
icia | +0.025 |
Jessica | +0.023 |
Neg logit contributions | |
pengu | -0.026 |
wo | -0.021 |
hipp | -0.021 |
monkey | -0.021 |
clown | -0.021 |
Token | kept |
Token ID | 4030 |
Feature activation | -4.98e-03 |
Pos logit contributions | |
icia | +0.018 |
basement | +0.017 |
icker | +0.017 |
ifying | +0.017 |
iper | +0.016 |
Neg logit contributions | |
pengu | -0.015 |
wo | -0.013 |
hipp | -0.012 |
clown | -0.012 |
monkey | -0.012 |
Token | his |
Token ID | 465 |
Feature activation | -8.42e-03 |
Pos logit contributions | |
icker | +0.011 |
ifying | +0.011 |
basement | +0.011 |
icia | +0.011 |
igsaw | +0.010 |
Neg logit contributions | |
pengu | -0.008 |
hipp | -0.006 |
wo | -0.006 |
monkey | -0.006 |
clown | -0.006 |
Token | pipes |
Token ID | 19860 |
Feature activation | +1.33e-02 |
Pos logit contributions | |
icia | +0.016 |
ifying | +0.016 |
icker | +0.015 |
Kelly | +0.015 |
Jessica | +0.015 |
Neg logit contributions | |
pengu | -0.016 |
monkey | -0.014 |
hipp | -0.014 |
gir | -0.013 |
clown | -0.013 |
Token | safe |
Token ID | 3338 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
pengu | +0.025 |
wo | +0.021 |
hipp | +0.021 |
monkey | +0.021 |
gir | +0.020 |
Neg logit contributions | |
icia | -0.024 |
basement | -0.023 |
icker | -0.023 |
ifying | -0.023 |
Jessica | -0.022 |
Token | in |
Token ID | 287 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
icia | +0.031 |
icker | +0.030 |
ifying | +0.030 |
basement | +0.030 |
Jessica | +0.029 |
Neg logit contributions | |
pengu | -0.021 |
hipp | -0.016 |
monkey | -0.016 |
gir | -0.015 |
clown | -0.015 |
Token | his |
Token ID | 465 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
pengu | +0.019 |
hipp | +0.015 |
monkey | +0.015 |
gir | +0.014 |
clown | +0.014 |
Neg logit contributions | |
ifying | -0.027 |
icker | -0.026 |
icia | -0.026 |
iper | -0.024 |
arse | -0.024 |
Token | pocket |
Token ID | 10000 |
Feature activation | -7.08e-04 |
Pos logit contributions | |
pengu | +0.024 |
hipp | +0.021 |
monkey | +0.021 |
gir | +0.020 |
ot | +0.019 |
Neg logit contributions | |
ifying | -0.021 |
icia | -0.021 |
Jessica | -0.020 |
Jennifer | -0.019 |
Kelly | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
icia | +0.002 |
ifying | +0.002 |
basement | +0.002 |
icker | +0.002 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
monkey | -0.001 |
hipp | -0.001 |
gir | -0.001 |
wo | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -5.27e-04 |
Pos logit contributions | |
icia | +0.036 |
basement | +0.036 |
icker | +0.035 |
ifying | +0.035 |
Jessica | +0.033 |
Neg logit contributions | |
pengu | -0.031 |
wo | -0.027 |
hipp | -0.026 |
monkey | -0.025 |
clown | -0.025 |
Token | he |
Token ID | 339 |
Feature activation | -4.28e-03 |
Pos logit contributions | |
icia | +0.001 |
icker | +0.001 |
basement | +0.001 |
ifying | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
gir | -0.001 |
Token | never |
Token ID | 1239 |
Feature activation | -4.54e-03 |
Pos logit contributions | |
icia | +0.008 |
icker | +0.008 |
basement | +0.008 |
ifying | +0.007 |
iper | +0.007 |
Neg logit contributions | |
pengu | -0.008 |
wo | -0.007 |
hipp | -0.007 |
monkey | -0.006 |
clown | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
pengu | +0.025 |
hipp | +0.020 |
monkey | +0.020 |
wo | +0.020 |
clown | +0.019 |
Neg logit contributions | |
icia | -0.030 |
icker | -0.030 |
basement | -0.030 |
ifying | -0.030 |
Jessica | -0.028 |
Token | but |
Token ID | 475 |
Feature activation | +9.79e-03 |
Pos logit contributions | |
icia | +0.026 |
icker | +0.026 |
basement | +0.026 |
ifying | +0.025 |
Jessica | +0.024 |
Neg logit contributions | |
pengu | -0.023 |
hipp | -0.019 |
monkey | -0.019 |
wo | -0.019 |
gir | -0.018 |
Token | she |
Token ID | 673 |
Feature activation | -5.31e-04 |
Pos logit contributions | |
pengu | +0.017 |
hipp | +0.013 |
monkey | +0.013 |
clown | +0.013 |
gir | +0.013 |
Neg logit contributions | |
icker | -0.020 |
icia | -0.020 |
basement | -0.020 |
ifying | -0.020 |
arse | -0.018 |
Token | was |
Token ID | 373 |
Feature activation | -9.88e-03 |
Pos logit contributions | |
icia | +0.001 |
icker | +0.001 |
basement | +0.001 |
ifying | +0.001 |
Jessica | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
gir | -0.001 |
Token | not |
Token ID | 407 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
icker | +0.020 |
ifying | +0.020 |
basement | +0.020 |
icia | +0.019 |
igsaw | +0.019 |
Neg logit contributions | |
pengu | -0.016 |
monkey | -0.014 |
hipp | -0.013 |
wo | -0.013 |
gir | -0.013 |
Token | alone |
Token ID | 3436 |
Feature activation | +7.15e-03 |
Pos logit contributions | |
icker | +0.041 |
basement | +0.041 |
ifying | +0.040 |
icia | +0.040 |
Jessica | +0.037 |
Neg logit contributions | |
pengu | -0.035 |
monkey | -0.029 |
hipp | -0.029 |
wo | -0.028 |
gir | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | -3.52e-03 |
Pos logit contributions | |
pengu | +0.013 |
monkey | +0.011 |
hipp | +0.011 |
wo | +0.010 |
clown | +0.010 |
Neg logit contributions | |
icker | -0.014 |
icia | -0.014 |
basement | -0.013 |
ifying | -0.013 |
Jessica | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -5.06e-04 |
Pos logit contributions | |
icker | +0.007 |
icia | +0.007 |
basement | +0.007 |
arse | +0.007 |
ifying | +0.007 |
Neg logit contributions | |
pengu | -0.006 |
monkey | -0.005 |
hipp | -0.005 |
wo | -0.005 |
clown | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -1.47e-03 |
Pos logit contributions | |
ifying | +0.001 |
icia | +0.001 |
basement | +0.001 |
icker | +0.001 |
arse | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
monkey | -0.001 |
wo | -0.001 |
hipp | -0.001 |
clown | -0.001 |
Token | She |
Token ID | 3347 |
Feature activation | +4.51e-03 |
Pos logit contributions | |
ifying | +0.003 |
icia | +0.003 |
icker | +0.003 |
basement | +0.003 |
arse | +0.003 |
Neg logit contributions | |
pengu | -0.003 |
monkey | -0.002 |
wo | -0.002 |
clown | -0.002 |
hipp | -0.002 |
Token | hugged |
Token ID | 41130 |
Feature activation | +4.79e-03 |
Pos logit contributions | |
pengu | +0.007 |
wo | +0.006 |
hipp | +0.006 |
monkey | +0.005 |
clown | +0.005 |
Neg logit contributions | |
icia | -0.010 |
basement | -0.009 |
icker | -0.009 |
ifying | -0.009 |
Jessica | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +3.49e-04 |
Pos logit contributions | |
pengu | +0.001 |
wo | +0.001 |
monkey | +0.001 |
hipp | +0.001 |
clown | +0.001 |
Neg logit contributions | |
ifying | -0.001 |
icia | -0.001 |
basement | -0.001 |
icker | -0.001 |
arse | -0.001 |
Token | From |
Token ID | 4863 |
Feature activation | -8.83e-04 |
Pos logit contributions | |
pengu | +0.001 |
wo | +0.001 |
monkey | +0.001 |
hipp | +0.001 |
clown | +0.001 |
Neg logit contributions | |
icia | -0.001 |
ifying | -0.001 |
icker | -0.001 |
basement | -0.001 |
arse | -0.001 |
Token | then |
Token ID | 788 |
Feature activation | +2.00e-03 |
Pos logit contributions | |
ifying | +0.002 |
icker | +0.002 |
icia | +0.002 |
basement | +0.002 |
arse | +0.002 |
Neg logit contributions | |
pengu | -0.001 |
monkey | -0.001 |
hipp | -0.001 |
clown | -0.001 |
wo | -0.001 |
Token | on |
Token ID | 319 |
Feature activation | +5.02e-03 |
Pos logit contributions | |
pengu | +0.003 |
monkey | +0.002 |
wo | +0.002 |
gir | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icker | -0.005 |
icia | -0.004 |
ifying | -0.004 |
Jessica | -0.004 |
basement | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.91e-03 |
Pos logit contributions | |
pengu | +0.006 |
hipp | +0.004 |
monkey | +0.004 |
clown | +0.004 |
gir | +0.004 |
Neg logit contributions | |
icker | -0.013 |
ifying | -0.013 |
icia | -0.012 |
basement | -0.012 |
arse | -0.012 |
Token | Jake |
Token ID | 14757 |
Feature activation | -3.03e-03 |
Pos logit contributions | |
pengu | +0.004 |
hipp | +0.003 |
monkey | +0.003 |
clown | +0.003 |
wo | +0.003 |
Neg logit contributions | |
icker | -0.004 |
icia | -0.004 |
ifying | -0.004 |
basement | -0.004 |
arse | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +7.37e-03 |
Pos logit contributions | |
icia | +0.006 |
basement | +0.006 |
icker | +0.005 |
ifying | +0.005 |
Jessica | +0.005 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.005 |
hipp | -0.005 |
monkey | -0.004 |
clown | -0.004 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -6.93e-03 |
Pos logit contributions | |
pengu | +0.015 |
wo | +0.012 |
hipp | +0.012 |
monkey | +0.012 |
clown | +0.012 |
Neg logit contributions | |
icia | -0.013 |
icker | -0.012 |
basement | -0.012 |
ifying | -0.012 |
Jessica | -0.011 |
Token | were |
Token ID | 547 |
Feature activation | +4.90e-03 |
Pos logit contributions | |
icia | +0.015 |
icker | +0.015 |
basement | +0.015 |
ifying | +0.015 |
Jessica | +0.014 |
Neg logit contributions | |
pengu | -0.011 |
wo | -0.009 |
hipp | -0.008 |
monkey | -0.008 |
gir | -0.008 |
Token | much |
Token ID | 881 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
pengu | +0.008 |
monkey | +0.007 |
hipp | +0.007 |
wo | +0.007 |
gir | +0.007 |
Neg logit contributions | |
ifying | -0.010 |
icker | -0.010 |
icia | -0.010 |
basement | -0.010 |
igsaw | -0.009 |
Token | more |
Token ID | 517 |
Feature activation | +9.43e-03 |
Pos logit contributions | |
pengu | +0.024 |
wo | +0.021 |
hipp | +0.020 |
monkey | +0.020 |
gir | +0.019 |
Neg logit contributions | |
icia | -0.020 |
icker | -0.020 |
basement | -0.020 |
ifying | -0.020 |
Jessica | -0.018 |
Token | special |
Token ID | 2041 |
Feature activation | +4.13e-03 |
Pos logit contributions | |
pengu | +0.024 |
hipp | +0.020 |
monkey | +0.020 |
clown | +0.019 |
gir | +0.019 |
Neg logit contributions | |
ifying | -0.023 |
icker | -0.022 |
icia | -0.022 |
Kelly | -0.021 |
basement | -0.020 |
Token | carpet |
Token ID | 20710 |
Feature activation | -6.36e-03 |
Pos logit contributions | |
pengu | +0.009 |
hipp | +0.007 |
monkey | +0.007 |
clown | +0.007 |
wo | +0.007 |
Neg logit contributions | |
ifying | -0.007 |
icia | -0.007 |
icker | -0.007 |
basement | -0.006 |
Kelly | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -9.21e-03 |
Pos logit contributions | |
icia | +0.013 |
icker | +0.013 |
ifying | +0.013 |
basement | +0.012 |
Kelly | +0.012 |
Neg logit contributions | |
pengu | -0.011 |
monkey | -0.009 |
hipp | -0.009 |
gir | -0.008 |
clown | -0.008 |
Token | From |
Token ID | 3574 |
Feature activation | -1.85e-03 |
Pos logit contributions | |
icia | +0.015 |
icker | +0.015 |
basement | +0.015 |
ifying | +0.015 |
Jessica | +0.014 |
Neg logit contributions | |
pengu | -0.019 |
wo | -0.016 |
hipp | -0.016 |
monkey | -0.016 |
clown | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | -4.56e-03 |
Pos logit contributions | |
ifying | +0.004 |
icker | +0.004 |
basement | +0.004 |
icia | +0.004 |
arse | +0.004 |
Neg logit contributions | |
pengu | -0.003 |
monkey | -0.002 |
hipp | -0.002 |
wo | -0.002 |
clown | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
ifying | +0.009 |
icker | +0.008 |
icia | +0.008 |
basement | +0.008 |
Jessica | +0.008 |
Neg logit contributions | |
pengu | -0.008 |
hipp | -0.007 |
monkey | -0.007 |
wo | -0.007 |
clown | -0.007 |
Token | on |
Token ID | 319 |
Feature activation | +3.31e-03 |
Pos logit contributions | |
icia | +0.023 |
icker | +0.022 |
basement | +0.022 |
ifying | +0.022 |
igsaw | +0.022 |
Neg logit contributions | |
pengu | -0.016 |
wo | -0.014 |
monkey | -0.014 |
clown | -0.013 |
hipp | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -3.94e-03 |
Pos logit contributions | |
pengu | +0.004 |
monkey | +0.003 |
hipp | +0.003 |
clown | +0.003 |
gir | +0.002 |
Neg logit contributions | |
ifying | -0.009 |
icker | -0.009 |
basement | -0.008 |
icia | -0.008 |
arse | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
icia | +0.008 |
icker | +0.008 |
basement | +0.008 |
ifying | +0.007 |
Jessica | +0.007 |
Neg logit contributions | |
pengu | -0.007 |
wo | -0.006 |
hipp | -0.006 |
monkey | -0.006 |
clown | -0.005 |
Token | both |
Token ID | 1111 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ifying | +0.027 |
basement | +0.026 |
icker | +0.026 |
icia | +0.026 |
igsaw | +0.025 |
Neg logit contributions | |
pengu | -0.017 |
hipp | -0.013 |
wo | -0.013 |
monkey | -0.013 |
gir | -0.013 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +2.36e-03 |
Pos logit contributions | |
pengu | +0.016 |
wo | +0.013 |
hipp | +0.013 |
monkey | +0.013 |
clown | +0.012 |
Neg logit contributions | |
icia | -0.024 |
icker | -0.024 |
basement | -0.024 |
ifying | -0.024 |
Jessica | -0.022 |
Token | visit |
Token ID | 3187 |
Feature activation | -7.23e-03 |
Pos logit contributions | |
pengu | +0.005 |
hipp | +0.004 |
monkey | +0.004 |
clown | +0.004 |
wo | +0.004 |
Neg logit contributions | |
ifying | -0.005 |
icker | -0.005 |
icia | -0.005 |
iper | -0.005 |
arse | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
ifying | +0.016 |
arse | +0.015 |
icker | +0.015 |
basement | +0.015 |
icia | +0.015 |
Neg logit contributions | |
pengu | -0.011 |
clown | -0.009 |
monkey | -0.009 |
wo | -0.009 |
hipp | -0.009 |
Token | grandma |
Token ID | 49890 |
Feature activation | +1.09e-03 |
Pos logit contributions | |
pengu | +0.003 |
monkey | +0.003 |
hipp | +0.003 |
clown | +0.003 |
gir | +0.003 |
Neg logit contributions | |
icker | -0.002 |
ifying | -0.002 |
icia | -0.002 |
arse | -0.002 |
basement | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.27e-03 |
Pos logit contributions | |
pengu | +0.002 |
monkey | +0.001 |
hipp | +0.001 |
clown | +0.001 |
gir | +0.001 |
Neg logit contributions | |
icker | -0.002 |
basement | -0.002 |
icia | -0.002 |
ifying | -0.002 |
igsaw | -0.002 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.80e-03 |
Pos logit contributions | |
pengu | +0.002 |
monkey | +0.002 |
hipp | +0.001 |
clown | +0.001 |
wo | +0.001 |
Neg logit contributions | |
icia | -0.003 |
icker | -0.003 |
ifying | -0.003 |
basement | -0.003 |
arse | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -7.22e-03 |
Pos logit contributions | |
icia | +0.008 |
basement | +0.007 |
Jessica | +0.007 |
Jessica | +0.007 |
iper | +0.007 |
Neg logit contributions | |
pengu | -0.007 |
wo | -0.006 |
hipp | -0.006 |
monkey | -0.005 |
gir | -0.005 |
Token | so |
Token ID | 523 |
Feature activation | -3.64e-03 |
Pos logit contributions | |
icia | +0.012 |
basement | +0.012 |
icker | +0.012 |
ifying | +0.011 |
Jessica | +0.011 |
Neg logit contributions | |
pengu | -0.014 |
wo | -0.013 |
hipp | -0.012 |
monkey | -0.012 |
haw | -0.012 |
Token | excited |
Token ID | 6568 |
Feature activation | +9.85e-03 |
Pos logit contributions | |
icia | +0.008 |
icker | +0.008 |
basement | +0.007 |
ifying | +0.007 |
Jessica | +0.007 |
Neg logit contributions | |
pengu | -0.006 |
wo | -0.005 |
hipp | -0.005 |
monkey | -0.005 |
gir | -0.004 |
Token | because |
Token ID | 780 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
pengu | +0.019 |
wo | +0.016 |
hipp | +0.016 |
monkey | +0.015 |
gir | +0.015 |
Neg logit contributions | |
icia | -0.017 |
basement | -0.017 |
icker | -0.017 |
ifying | -0.017 |
Jessica | -0.016 |
Token | she |
Token ID | 673 |
Feature activation | +7.42e-03 |
Pos logit contributions | |
pengu | +0.021 |
hipp | +0.018 |
monkey | +0.018 |
clown | +0.017 |
wo | +0.017 |
Neg logit contributions | |
icker | -0.022 |
icia | -0.022 |
ifying | -0.021 |
basement | -0.021 |
arse | -0.020 |
Token | loved |
Token ID | 6151 |
Feature activation | +6.38e-03 |
Pos logit contributions | |
pengu | +0.012 |
wo | +0.011 |
hipp | +0.010 |
monkey | +0.010 |
gir | +0.010 |
Neg logit contributions | |
icia | -0.015 |
Jessica | -0.014 |
Jessica | -0.014 |
basement | -0.014 |
icker | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -9.24e-05 |
Pos logit contributions | |
pengu | +0.002 |
monkey | +0.002 |
wo | +0.002 |
hipp | +0.002 |
clown | +0.002 |
Neg logit contributions | |
icia | -0.002 |
ifying | -0.002 |
icker | -0.002 |
basement | -0.002 |
arse | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +1.22e-03 |
Pos logit contributions | |
ifying | +0.000 |
icia | +0.000 |
basement | +0.000 |
icker | +0.000 |
igsaw | +0.000 |
Neg logit contributions | |
pengu | -0.000 |
wo | -0.000 |
monkey | -0.000 |
hipp | -0.000 |
clown | -0.000 |
Token | Tim |
Token ID | 14967 |
Feature activation | +2.81e-03 |
Pos logit contributions | |
pengu | +0.002 |
monkey | +0.002 |
wo | +0.002 |
hipp | +0.002 |
gir | +0.002 |
Neg logit contributions | |
icia | -0.002 |
ifying | -0.002 |
icker | -0.002 |
basement | -0.002 |
Jessica | -0.002 |
Token | does |
Token ID | 857 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
pengu | +0.005 |
hipp | +0.005 |
wo | +0.005 |
monkey | +0.004 |
gir | +0.004 |
Neg logit contributions | |
icia | -0.005 |
basement | -0.005 |
icker | -0.005 |
ifying | -0.005 |
Jennifer | -0.004 |
Token | not |
Token ID | 407 |
Feature activation | -8.56e-03 |
Pos logit contributions | |
pengu | +0.007 |
wo | +0.006 |
hipp | +0.006 |
monkey | +0.006 |
clown | +0.006 |
Neg logit contributions | |
icia | -0.008 |
ifying | -0.008 |
basement | -0.008 |
icker | -0.008 |
Jessica | -0.007 |
Token | listen |
Token ID | 6004 |
Feature activation | -8.86e-03 |
Pos logit contributions | |
icker | +0.013 |
icia | +0.013 |
basement | +0.013 |
ifying | +0.012 |
Jessica | +0.012 |
Neg logit contributions | |
pengu | -0.018 |
hipp | -0.015 |
wo | -0.015 |
gir | -0.015 |
monkey | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +5.58e-03 |
Pos logit contributions | |
icia | +0.015 |
basement | +0.015 |
icker | +0.015 |
ifying | +0.015 |
Jessica | +0.014 |
Neg logit contributions | |
pengu | -0.018 |
wo | -0.015 |
hipp | -0.015 |
monkey | -0.015 |
clown | -0.014 |
Token | He |
Token ID | 679 |
Feature activation | +1.71e-03 |
Pos logit contributions | |
pengu | +0.007 |
monkey | +0.005 |
hipp | +0.005 |
wo | +0.005 |
clown | +0.005 |
Neg logit contributions | |
icia | -0.014 |
ifying | -0.014 |
icker | -0.014 |
basement | -0.014 |
Jessica | -0.013 |
Token | tries |
Token ID | 8404 |
Feature activation | -8.82e-03 |
Pos logit contributions | |
pengu | +0.003 |
hipp | +0.003 |
wo | +0.003 |
monkey | +0.003 |
clown | +0.003 |
Neg logit contributions | |
icia | -0.003 |
basement | -0.003 |
ifying | -0.003 |
icker | -0.003 |
iper | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -5.82e-03 |
Pos logit contributions | |
icia | +0.017 |
ifying | +0.017 |
icker | +0.017 |
basement | +0.017 |
Jessica | +0.016 |
Neg logit contributions | |
pengu | -0.015 |
wo | -0.013 |
hipp | -0.013 |
monkey | -0.013 |
clown | -0.012 |
Token | go |
Token ID | 467 |
Feature activation | +3.80e-03 |
Pos logit contributions | |
icia | +0.010 |
basement | +0.009 |
icker | +0.009 |
ifying | +0.009 |
Jessica | +0.009 |
Neg logit contributions | |
pengu | -0.012 |
hipp | -0.010 |
wo | -0.010 |
gir | -0.010 |
monkey | -0.010 |
Token | cried |
Token ID | 16896 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
icker | +0.014 |
icia | +0.014 |
ifying | +0.014 |
basement | +0.014 |
Jessica | +0.013 |
Neg logit contributions | |
pengu | -0.010 |
hipp | -0.008 |
monkey | -0.008 |
wo | -0.007 |
clown | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
pengu | +0.027 |
monkey | +0.022 |
hipp | +0.022 |
wo | +0.021 |
gir | +0.021 |
Neg logit contributions | |
icia | -0.036 |
basement | -0.035 |
Jessica | -0.034 |
icker | -0.034 |
Kelly | -0.034 |
Token | lot |
Token ID | 1256 |
Feature activation | +4.71e-03 |
Pos logit contributions | |
pengu | +0.025 |
hipp | +0.020 |
monkey | +0.020 |
wo | +0.020 |
gir | +0.020 |
Neg logit contributions | |
icia | -0.026 |
icker | -0.026 |
basement | -0.025 |
ifying | -0.025 |
Jessica | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -2.16e-03 |
Pos logit contributions | |
pengu | +0.007 |
monkey | +0.006 |
hipp | +0.006 |
gir | +0.005 |
clown | +0.005 |
Neg logit contributions | |
icia | -0.011 |
icker | -0.010 |
ifying | -0.010 |
Jessica | -0.010 |
basement | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | -4.70e-03 |
Pos logit contributions | |
icker | +0.004 |
icia | +0.004 |
ifying | +0.004 |
basement | +0.004 |
arse | +0.004 |
Neg logit contributions | |
pengu | -0.004 |
monkey | -0.003 |
hipp | -0.003 |
wo | -0.003 |
gir | -0.003 |
Token | missed |
Token ID | 6825 |
Feature activation | -7.72e-03 |
Pos logit contributions | |
icia | +0.011 |
icker | +0.010 |
basement | +0.010 |
ifying | +0.010 |
Jessica | +0.010 |
Neg logit contributions | |
pengu | -0.007 |
wo | -0.005 |
hipp | -0.005 |
monkey | -0.005 |
clown | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -8.26e-03 |
Pos logit contributions | |
icker | +0.014 |
ifying | +0.014 |
icia | +0.014 |
basement | +0.014 |
Jessica | +0.013 |
Neg logit contributions | |
pengu | -0.015 |
hipp | -0.013 |
monkey | -0.012 |
wo | -0.012 |
clown | -0.012 |
Token | friend |
Token ID | 1545 |
Feature activation | +6.56e-04 |
Pos logit contributions | |
icia | +0.015 |
icker | +0.015 |
basement | +0.015 |
ifying | +0.015 |
Jessica | +0.014 |
Neg logit contributions | |
pengu | -0.015 |
wo | -0.013 |
hipp | -0.013 |
monkey | -0.013 |
clown | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -2.33e-03 |
Pos logit contributions | |
pengu | +0.001 |
monkey | +0.001 |
hipp | +0.001 |
wo | +0.001 |
clown | +0.001 |
Neg logit contributions | |
icker | -0.001 |
icia | -0.001 |
basement | -0.001 |
ifying | -0.001 |
Jessica | -0.001 |
Token | wished |
Token ID | 16555 |
Feature activation | -3.60e-03 |
Pos logit contributions | |
icia | +0.005 |
basement | +0.005 |
icker | +0.004 |
ifying | +0.004 |
Jessica | +0.004 |
Neg logit contributions | |
pengu | -0.004 |
wo | -0.003 |
hipp | -0.003 |
monkey | -0.003 |
gir | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
icia | +0.007 |
ifying | +0.007 |
icker | +0.007 |
basement | +0.007 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.006 |
hipp | -0.005 |
monkey | -0.005 |
wo | -0.005 |
clown | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -1.11e-03 |
Pos logit contributions | |
icia | +0.007 |
icker | +0.006 |
basement | +0.006 |
ifying | +0.006 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.008 |
hipp | -0.007 |
wo | -0.007 |
monkey | -0.006 |
clown | -0.006 |
Token | He |
Token ID | 679 |
Feature activation | -2.45e-03 |
Pos logit contributions | |
icia | +0.002 |
basement | +0.002 |
icker | +0.002 |
ifying | +0.002 |
Jessica | +0.002 |
Neg logit contributions | |
pengu | -0.002 |
wo | -0.002 |
hipp | -0.002 |
monkey | -0.002 |
clown | -0.002 |
Token | quickly |
Token ID | 2952 |
Feature activation | +2.07e-03 |
Pos logit contributions | |
icia | +0.005 |
iper | +0.004 |
Jessica | +0.004 |
basement | +0.004 |
icker | +0.004 |
Neg logit contributions | |
pengu | -0.004 |
wo | -0.004 |
hipp | -0.004 |
cest | -0.003 |
haw | -0.003 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +7.53e-03 |
Pos logit contributions | |
pengu | +0.003 |
wo | +0.003 |
hipp | +0.003 |
clown | +0.002 |
monkey | +0.002 |
Neg logit contributions | |
icia | -0.004 |
iper | -0.004 |
ifying | -0.004 |
basement | -0.004 |
icker | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +6.27e-04 |
Pos logit contributions | |
pengu | +0.015 |
wo | +0.013 |
hipp | +0.013 |
monkey | +0.013 |
clown | +0.012 |
Neg logit contributions | |
icia | -0.013 |
icker | -0.012 |
ifying | -0.012 |
basement | -0.012 |
Jessica | -0.011 |
Token | little |
Token ID | 1310 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
pengu | +0.001 |
wo | +0.001 |
hipp | +0.001 |
monkey | +0.001 |
clown | +0.001 |
Neg logit contributions | |
ifying | -0.001 |
icker | -0.001 |
basement | -0.001 |
icia | -0.001 |
diary | -0.001 |
Token | bit |
Token ID | 1643 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
ifying | +0.022 |
icker | +0.022 |
basement | +0.022 |
diary | +0.022 |
igsaw | +0.021 |
Neg logit contributions | |
pengu | -0.025 |
wo | -0.023 |
hipp | -0.021 |
clown | -0.021 |
haw | -0.020 |
Token | of |
Token ID | 286 |
Feature activation | -2.64e-03 |
Pos logit contributions | |
icker | +0.007 |
ifying | +0.007 |
icia | +0.006 |
basement | +0.006 |
.' | +0.006 |
Neg logit contributions | |
pengu | -0.007 |
wo | -0.006 |
hipp | -0.006 |
clown | -0.006 |
monkey | -0.005 |
Token | cheese |
Token ID | 9891 |
Feature activation | -6.33e-04 |
Pos logit contributions | |
icia | +0.004 |
icker | +0.004 |
basement | +0.004 |
ifying | +0.004 |
Jennifer | +0.003 |
Neg logit contributions | |
pengu | -0.006 |
wo | -0.005 |
hipp | -0.005 |
monkey | -0.005 |
gir | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +5.81e-03 |
Pos logit contributions | |
icia | +0.001 |
basement | +0.001 |
icker | +0.001 |
ifying | +0.001 |
diary | +0.001 |
Neg logit contributions | |
pengu | -0.001 |
wo | -0.001 |
hipp | -0.001 |
monkey | -0.001 |
clown | -0.001 |
Token | tried |
Token ID | 3088 |
Feature activation | -6.86e-04 |
Pos logit contributions | |
pengu | +0.009 |
wo | +0.008 |
hipp | +0.008 |
clown | +0.007 |
haw | +0.007 |
Neg logit contributions | |
icia | -0.011 |
Jennifer | -0.010 |
Jessica | -0.010 |
Piper | -0.010 |
Emily | -0.010 |
Token | walking |
Token ID | 6155 |
Feature activation | +5.66e-03 |
Pos logit contributions | |
pengu | +0.014 |
hipp | +0.011 |
monkey | +0.011 |
clown | +0.011 |
gir | +0.011 |
Neg logit contributions | |
ifying | -0.019 |
icker | -0.019 |
icia | -0.019 |
basement | -0.019 |
igsaw | -0.018 |
Token | through |
Token ID | 832 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
pengu | +0.011 |
monkey | +0.009 |
hipp | +0.009 |
wo | +0.009 |
clown | +0.009 |
Neg logit contributions | |
icia | -0.011 |
ifying | -0.010 |
icker | -0.010 |
basement | -0.010 |
Kelly | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -6.21e-03 |
Pos logit contributions | |
pengu | +0.029 |
clown | +0.021 |
monkey | +0.021 |
hipp | +0.021 |
ducks | +0.020 |
Neg logit contributions | |
icia | -0.046 |
icker | -0.046 |
arse | -0.044 |
ifying | -0.044 |
iper | -0.043 |
Token | woods |
Token ID | 16479 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
icia | +0.013 |
ifying | +0.013 |
icker | +0.013 |
arse | +0.012 |
iper | +0.012 |
Neg logit contributions | |
pengu | -0.011 |
monkey | -0.009 |
hipp | -0.009 |
clown | -0.009 |
gir | -0.009 |
Token | one |
Token ID | 530 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
icia | +0.020 |
ifying | +0.020 |
icker | +0.020 |
basement | +0.019 |
Jessica | +0.019 |
Neg logit contributions | |
pengu | -0.020 |
hipp | -0.016 |
monkey | -0.016 |
wo | -0.016 |
gir | -0.016 |
Token | day |
Token ID | 1110 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
pengu | +0.033 |
monkey | +0.029 |
hipp | +0.026 |
gir | +0.024 |
clown | +0.024 |
Neg logit contributions | |
icia | -0.049 |
ifying | -0.044 |
basement | -0.043 |
Jessica | -0.043 |
icker | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +3.57e-03 |
Pos logit contributions | |
icia | +0.092 |
basement | +0.088 |
ifying | +0.085 |
iper | +0.081 |
icker | +0.081 |
Neg logit contributions | |
pengu | -0.049 |
monkey | -0.038 |
hipp | -0.037 |
gir | -0.037 |
ducks | -0.036 |
Token | Mary |
Token ID | 5335 |
Feature activation | -3.48e-03 |
Pos logit contributions | |
pengu | +0.007 |
monkey | +0.006 |
hipp | +0.006 |
wo | +0.006 |
gir | +0.006 |
Neg logit contributions | |
ifying | -0.006 |
icker | -0.006 |
icia | -0.006 |
basement | -0.005 |
arse | -0.005 |
Token | saw |
Token ID | 2497 |
Feature activation | -7.28e-03 |
Pos logit contributions | |
icia | +0.008 |
icker | +0.008 |
basement | +0.008 |
ifying | +0.008 |
Jessica | +0.007 |
Neg logit contributions | |
pengu | -0.005 |
wo | -0.004 |
hipp | -0.004 |
monkey | -0.004 |
clown | -0.004 |
Token | something |
Token ID | 1223 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
icia | +0.012 |
basement | +0.012 |
icker | +0.012 |
ifying | +0.012 |
Jessica | +0.011 |
Neg logit contributions | |
pengu | -0.015 |
wo | -0.013 |
hipp | -0.012 |
monkey | -0.012 |
clown | -0.012 |
Token | glitter |
Token ID | 31133 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
pengu | +0.031 |
wo | +0.026 |
hipp | +0.025 |
monkey | +0.025 |
clown | +0.024 |
Neg logit contributions | |
icia | -0.031 |
icker | -0.031 |
basement | -0.030 |
ifying | -0.030 |
Jessica | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | +4.85e-03 |
Pos logit contributions | |
pengu | +0.010 |
hipp | +0.009 |
monkey | +0.009 |
wo | +0.009 |
clown | +0.008 |
Neg logit contributions | |
icia | -0.009 |
ifying | -0.009 |
icker | -0.009 |
basement | -0.009 |
arse | -0.009 |
Token | want |
Token ID | 765 |
Feature activation | -6.57e-03 |
Pos logit contributions | |
pengu | +0.008 |
wo | +0.007 |
hipp | +0.007 |
monkey | +0.007 |
gir | +0.007 |
Neg logit contributions | |
icia | -0.009 |
basement | -0.009 |
icker | -0.009 |
ifying | -0.009 |
Jessica | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -4.15e-03 |
Pos logit contributions | |
icia | +0.012 |
basement | +0.012 |
icker | +0.012 |
ifying | +0.012 |
Jessica | +0.011 |
Neg logit contributions | |
pengu | -0.012 |
wo | -0.010 |
hipp | -0.010 |
monkey | -0.010 |
gir | -0.010 |
Token | eat |
Token ID | 4483 |
Feature activation | +3.94e-03 |
Pos logit contributions | |
basement | +0.007 |
icia | +0.007 |
icker | +0.007 |
ifying | +0.007 |
Jessica | +0.007 |
Neg logit contributions | |
pengu | -0.008 |
wo | -0.007 |
hipp | -0.006 |
monkey | -0.006 |
gir | -0.006 |
Token | something |
Token ID | 1223 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
pengu | +0.007 |
hipp | +0.006 |
monkey | +0.006 |
wo | +0.006 |
clown | +0.005 |
Neg logit contributions | |
icia | -0.008 |
ifying | -0.008 |
icker | -0.008 |
basement | -0.008 |
Jessica | -0.007 |
Token | y |
Token ID | 331 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
pengu | +0.039 |
wo | +0.035 |
monkey | +0.032 |
hipp | +0.032 |
gir | +0.032 |
Neg logit contributions | |
basement | -0.034 |
icker | -0.034 |
icia | -0.033 |
ifying | -0.032 |
.' | -0.030 |
Token | ummy |
Token ID | 13513 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
icia | +0.055 |
icker | +0.055 |
basement | +0.055 |
ifying | +0.054 |
Jessica | +0.050 |
Neg logit contributions | |
pengu | -0.079 |
wo | -0.069 |
hipp | -0.068 |
monkey | -0.067 |
clown | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | +4.65e-03 |
Pos logit contributions | |
icia | +0.020 |
icker | +0.020 |
basement | +0.020 |
ifying | +0.020 |
Jessica | +0.018 |
Neg logit contributions | |
pengu | -0.023 |
wo | -0.020 |
hipp | -0.020 |
monkey | -0.020 |
clown | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | +3.69e-03 |
Pos logit contributions | |
pengu | +0.008 |
hipp | +0.007 |
monkey | +0.007 |
clown | +0.006 |
ducks | +0.006 |
Neg logit contributions | |
icia | -0.009 |
basement | -0.009 |
ifying | -0.009 |
icker | -0.009 |
diary | -0.009 |
Token | go |
Token ID | 467 |
Feature activation | +4.61e-03 |
Pos logit contributions | |
pengu | +0.006 |
hipp | +0.005 |
monkey | +0.005 |
wo | +0.005 |
gir | +0.005 |
Neg logit contributions | |
icker | -0.008 |
basement | -0.007 |
ifying | -0.007 |
icia | -0.007 |
Jessica | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -3.15e-03 |
Pos logit contributions | |
pengu | +0.008 |
wo | +0.007 |
hipp | +0.007 |
monkey | +0.007 |
clown | +0.007 |
Neg logit contributions | |
icia | -0.009 |
icker | -0.008 |
basement | -0.008 |
ifying | -0.008 |
Jessica | -0.008 |
Token | wear |
Token ID | 5806 |
Feature activation | -4.89e-03 |
Pos logit contributions | |
icia | +0.006 |
basement | +0.006 |
ifying | +0.006 |
icker | +0.006 |
Jessica | +0.006 |
Neg logit contributions | |
pengu | -0.006 |
wo | -0.005 |
monkey | -0.005 |
hipp | -0.005 |
clown | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -8.26e-03 |
Pos logit contributions | |
icker | +0.011 |
basement | +0.011 |
icia | +0.010 |
arse | +0.010 |
ifying | +0.010 |
Neg logit contributions | |
pengu | -0.007 |
clown | -0.006 |
monkey | -0.006 |
wo | -0.006 |
hipp | -0.006 |
Token | purple |
Token ID | 14032 |
Feature activation | -4.78e-03 |
Pos logit contributions | |
icker | +0.017 |
basement | +0.016 |
icia | +0.016 |
ifying | +0.016 |
arse | +0.015 |
Neg logit contributions | |
pengu | -0.014 |
monkey | -0.012 |
gir | -0.012 |
clown | -0.011 |
hipp | -0.011 |
Token | tie |
Token ID | 9839 |
Feature activation | -9.07e-03 |
Pos logit contributions | |
icia | +0.008 |
icker | +0.008 |
basement | +0.008 |
ifying | +0.008 |
Jessica | +0.008 |
Neg logit contributions | |
pengu | -0.009 |
monkey | -0.008 |
wo | -0.008 |
hipp | -0.008 |
clown | -0.008 |
Token | one |
Token ID | 530 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
icker | +0.019 |
icia | +0.019 |
basement | +0.019 |
ifying | +0.019 |
arse | +0.018 |
Neg logit contributions | |
pengu | -0.014 |
monkey | -0.012 |
wo | -0.011 |
clown | -0.011 |
hipp | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
pengu | +0.028 |
monkey | +0.023 |
clown | +0.021 |
hipp | +0.021 |
wo | +0.020 |
Neg logit contributions | |
icia | -0.040 |
icker | -0.039 |
basement | -0.039 |
Kelly | -0.038 |
ifying | -0.037 |
Token | when |
Token ID | 618 |
Feature activation | -7.64e-03 |
Pos logit contributions | |
basement | +0.076 |
icker | +0.075 |
icia | +0.075 |
arse | +0.071 |
ifying | +0.071 |
Neg logit contributions | |
pengu | -0.051 |
clown | -0.042 |
monkey | -0.041 |
wo | -0.039 |
gir | -0.039 |
Token | she |
Token ID | 673 |
Feature activation | +6.53e-04 |
Pos logit contributions | |
icker | +0.015 |
icia | +0.015 |
ifying | +0.015 |
arse | +0.014 |
basement | +0.014 |
Neg logit contributions | |
pengu | -0.013 |
clown | -0.011 |
hipp | -0.010 |
monkey | -0.010 |
wo | -0.010 |
Token | was |
Token ID | 373 |
Feature activation | -9.01e-03 |
Pos logit contributions | |
pengu | +0.001 |
hipp | +0.001 |
wo | +0.001 |
monkey | +0.001 |
gir | +0.001 |
Neg logit contributions | |
icia | -0.001 |
icker | -0.001 |
ifying | -0.001 |
basement | -0.001 |
Jessica | -0.001 |
Token | older |
Token ID | 4697 |
Feature activation | +2.50e-04 |
Pos logit contributions | |
basement | +0.017 |
ifying | +0.017 |
icker | +0.017 |
icia | +0.017 |
igsaw | +0.015 |
Neg logit contributions | |
pengu | -0.016 |
wo | -0.013 |
clown | -0.013 |
hipp | -0.013 |
monkey | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.52e-03 |
Pos logit contributions | |
pengu | +0.000 |
monkey | +0.000 |
wo | +0.000 |
hipp | +0.000 |
clown | +0.000 |
Neg logit contributions | |
icker | -0.000 |
icia | -0.000 |
basement | -0.000 |
ifying | -0.000 |
Jessica | -0.000 |
Token | walking |
Token ID | 6155 |
Feature activation | +1.13e-03 |
Pos logit contributions | |
pengu | +0.002 |
hipp | +0.001 |
clown | +0.001 |
monkey | +0.001 |
wo | +0.001 |
Neg logit contributions | |
icia | -0.002 |
icker | -0.002 |
basement | -0.002 |
ifying | -0.002 |
igsaw | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +4.27e-03 |
Pos logit contributions | |
pengu | +0.002 |
hipp | +0.002 |
monkey | +0.002 |
clown | +0.002 |
wo | +0.002 |
Neg logit contributions | |
icia | -0.002 |
icker | -0.002 |
basement | -0.002 |
ifying | -0.002 |
Kelly | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -6.17e-03 |
Pos logit contributions | |
pengu | +0.008 |
hipp | +0.006 |
monkey | +0.006 |
clown | +0.006 |
wo | +0.006 |
Neg logit contributions | |
icia | -0.009 |
ifying | -0.009 |
icker | -0.009 |
iper | -0.008 |
basement | -0.008 |
Token | park |
Token ID | 3952 |
Feature activation | -7.03e-03 |
Pos logit contributions | |
icia | +0.011 |
icker | +0.011 |
ifying | +0.011 |
iper | +0.011 |
basement | +0.011 |
Neg logit contributions | |
pengu | -0.012 |
hipp | -0.010 |
monkey | -0.010 |
clown | -0.010 |
gir | -0.009 |
Token | one |
Token ID | 530 |
Feature activation | +2.42e-02 |
Pos logit contributions | |
icia | +0.013 |
icker | +0.013 |
ifying | +0.013 |
basement | +0.013 |
Jessica | +0.012 |
Neg logit contributions | |
pengu | -0.013 |
hipp | -0.011 |
monkey | -0.011 |
wo | -0.011 |
clown | -0.010 |
Token | day |
Token ID | 1110 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
pengu | +0.042 |
monkey | +0.034 |
hipp | +0.033 |
clown | +0.032 |
wo | +0.031 |
Neg logit contributions | |
icia | -0.053 |
basement | -0.049 |
ifying | -0.048 |
icker | -0.048 |
Kelly | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -3.13e-04 |
Pos logit contributions | |
icia | +0.087 |
basement | +0.087 |
ifying | +0.081 |
icker | +0.081 |
igsaw | +0.079 |
Neg logit contributions | |
pengu | -0.056 |
monkey | -0.044 |
hipp | -0.043 |
clown | -0.043 |
gir | -0.042 |
Token | John |
Token ID | 1757 |
Feature activation | -9.01e-03 |
Pos logit contributions | |
icia | +0.001 |
icker | +0.001 |
basement | +0.001 |
ifying | +0.001 |
Jessica | +0.000 |
Neg logit contributions | |
pengu | -0.001 |
hipp | -0.001 |
wo | -0.001 |
monkey | -0.001 |
clown | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | -6.43e-03 |
Pos logit contributions | |
icia | +0.019 |
icker | +0.019 |
basement | +0.018 |
ifying | +0.018 |
Jessica | +0.018 |
Neg logit contributions | |
pengu | -0.014 |
wo | -0.011 |
hipp | -0.011 |
monkey | -0.011 |
clown | -0.010 |
Token | 3 |
Token ID | 513 |
Feature activation | +7.31e-03 |
Pos logit contributions | |
ifying | +0.010 |
basement | +0.010 |
icia | +0.010 |
icker | +0.010 |
Jessica | +0.009 |
Neg logit contributions | |
pengu | -0.013 |
wo | -0.012 |
hipp | -0.011 |
monkey | -0.011 |
gir | -0.011 |
Token | years |
Token ID | 812 |
Feature activation | +1.46e-03 |
Pos logit contributions | |
pengu | +0.016 |
wo | +0.014 |
hipp | +0.014 |
monkey | +0.013 |
Rib | +0.013 |
Neg logit contributions | |
basement | -0.009 |
icia | -0.009 |
Jessica | -0.009 |
icker | -0.009 |
Jessica | -0.009 |
Token | set |
Token ID | 900 |
Feature activation | -1.91e-03 |
Pos logit contributions | |
Jessica | +0.041 |
Kelly | +0.041 |
igsaw | +0.041 |
enna | +0.040 |
Jennifer | +0.039 |
Neg logit contributions | |
pengu | -0.026 |
hipp | -0.021 |
monkey | -0.020 |
clown | -0.019 |
ducks | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +4.73e-03 |
Pos logit contributions | |
ifying | +0.004 |
basement | +0.004 |
icia | +0.004 |
Jessica | +0.004 |
icker | +0.004 |
Neg logit contributions | |
pengu | -0.003 |
hipp | -0.003 |
monkey | -0.003 |
clown | -0.002 |
wo | -0.002 |
Token | timer |
Token ID | 19781 |
Feature activation | -3.55e-03 |
Pos logit contributions | |
pengu | +0.009 |
hipp | +0.007 |
wo | +0.007 |
monkey | +0.007 |
clown | +0.007 |
Neg logit contributions | |
icia | -0.009 |
icker | -0.009 |
ifying | -0.009 |
basement | -0.009 |
Jessica | -0.008 |
Token | for |
Token ID | 329 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
icia | +0.008 |
ifying | +0.007 |
icker | +0.007 |
basement | +0.007 |
Jessica | +0.007 |
Neg logit contributions | |
pengu | -0.006 |
monkey | -0.004 |
wo | -0.004 |
hipp | -0.004 |
gir | -0.004 |
Token | 30 |
Token ID | 1542 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ifying | +0.025 |
icker | +0.025 |
icia | +0.025 |
basement | +0.024 |
arse | +0.023 |
Neg logit contributions | |
pengu | -0.023 |
hipp | -0.018 |
clown | -0.018 |
wo | -0.018 |
monkey | -0.018 |
Token | minutes |
Token ID | 2431 |
Feature activation | -3.58e-02 |
Pos logit contributions | |
pengu | +0.024 |
wo | +0.022 |
hipp | +0.021 |
monkey | +0.021 |
clown | +0.021 |
Neg logit contributions | |
icia | -0.013 |
icker | -0.013 |
basement | -0.013 |
ifying | -0.013 |
Jessica | -0.012 |
Token | ," |
Token ID | 553 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
icia | +0.077 |
basement | +0.076 |
icker | +0.076 |
ifying | +0.076 |
Jessica | +0.071 |
Neg logit contributions | |
pengu | -0.055 |
hipp | -0.044 |
wo | -0.044 |
monkey | -0.044 |
clown | -0.042 |
Token | dad |
Token ID | 9955 |
Feature activation | +8.55e-03 |
Pos logit contributions | |
ifying | +0.003 |
icia | +0.003 |
icker | +0.003 |
basement | +0.003 |
arse | +0.003 |
Neg logit contributions | |
pengu | -0.003 |
monkey | -0.002 |
clown | -0.002 |
hipp | -0.002 |
wo | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +7.26e-03 |
Pos logit contributions | |
pengu | +0.015 |
hipp | +0.013 |
wo | +0.012 |
monkey | +0.012 |
gir | +0.012 |
Neg logit contributions | |
icia | -0.016 |
icker | -0.016 |
Jessica | -0.016 |
Jessica | -0.015 |
Kelly | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +3.18e-03 |
Pos logit contributions | |
pengu | +0.015 |
wo | +0.013 |
hipp | +0.013 |
monkey | +0.012 |
clown | +0.012 |
Neg logit contributions | |
icia | -0.012 |
icker | -0.012 |
basement | -0.012 |
ifying | -0.012 |
Jessica | -0.011 |
Token | " |
Token ID | 366 |
Feature activation | +4.60e-05 |
Pos logit contributions | |
pengu | +0.006 |
wo | +0.005 |
hipp | +0.005 |
haw | +0.005 |
gir | +0.005 |
Neg logit contributions | |
basement | -0.006 |
icia | -0.005 |
icker | -0.005 |
Jessica | -0.005 |
Jennifer | -0.005 |