Token | Let |
Token ID | 5756 |
Feature activation | -3.64e-02 |
Pos logit contributions | |
Evan | +0.006 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.005 |
pen | +0.005 |
Neg logit contributions | |
Judy | -0.005 |
Janet | -0.005 |
arge | -0.005 |
imi | -0.005 |
Betty | -0.005 |
Token | 's |
Token ID | 338 |
Feature activation | -5.55e-02 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
eighty | +0.000 |
pen | +0.000 |
cash | +0.000 |
Neg logit contributions | |
Judy | -0.001 |
Janet | -0.001 |
imi | -0.001 |
arge | -0.001 |
Betty | -0.001 |
Token | tie |
Token ID | 9839 |
Feature activation | -3.22e-02 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
marry | +0.001 |
cash | +0.001 |
eighty | +0.001 |
Neg logit contributions | |
anne | -0.002 |
arge | -0.002 |
Judy | -0.002 |
imi | -0.002 |
Janet | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +9.84e-01 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.000 |
eighty | +0.000 |
cash | +0.000 |
penn | +0.000 |
Neg logit contributions | |
arge | -0.001 |
anne | -0.001 |
Judy | -0.001 |
Bet | -0.001 |
Janet | -0.001 |
Token | r |
Token ID | 374 |
Feature activation | +3.22e-01 |
Pos logit contributions | |
anne | +0.027 |
Judy | +0.027 |
arge | +0.027 |
Janet | +0.027 |
imi | +0.025 |
Neg logit contributions | |
cand | -0.024 |
eighty | -0.023 |
Evan | -0.022 |
cash | -0.022 |
penn | -0.021 |
Token | ags |
Token ID | 3775 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
Judy | +0.009 |
Janet | +0.008 |
anne | +0.008 |
Betty | +0.008 |
Bet | +0.008 |
Neg logit contributions | |
cand | -0.007 |
Evan | -0.007 |
cash | -0.007 |
eighty | -0.007 |
himself | -0.007 |
Token | together |
Token ID | 1978 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
Bet | +0.111 |
imi | +0.105 |
iqu | +0.104 |
arl | +0.104 |
Jud | +0.104 |
Neg logit contributions | |
with | -0.042 |
himself | -0.030 |
in | -0.029 |
e | -0.027 |
from | -0.025 |
Token | ," |
Token ID | 553 |
Feature activation | +8.99e-01 |
Pos logit contributions | |
Janet | +0.023 |
arge | +0.022 |
Judy | +0.022 |
Bet | +0.022 |
imi | +0.022 |
Neg logit contributions | |
Evan | -0.023 |
cand | -0.022 |
eighty | -0.021 |
pen | -0.020 |
cash | -0.020 |
Token | Tom |
Token ID | 4186 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Bet | +0.025 |
iet | +0.025 |
imi | +0.025 |
anne | +0.024 |
arge | +0.024 |
Neg logit contributions | |
Evan | -0.021 |
cand | -0.019 |
cash | -0.018 |
penn | -0.017 |
eighty | -0.017 |
Token | says |
Token ID | 1139 |
Feature activation | -5.49e-01 |
Pos logit contributions | |
arge | +0.005 |
Bet | +0.005 |
Janet | +0.005 |
Judy | +0.005 |
imi | +0.005 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.007 |
eighty | -0.007 |
cash | -0.006 |
pen | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +5.38e-02 |
Pos logit contributions | |
Evan | +0.015 |
cand | +0.014 |
eighty | +0.014 |
cash | +0.013 |
pen | +0.013 |
Neg logit contributions | |
Judy | -0.013 |
Janet | -0.013 |
arge | -0.012 |
anne | -0.012 |
Betty | -0.012 |
Token | helps |
Token ID | 5419 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Judy | +0.011 |
arge | +0.011 |
Janet | +0.011 |
imi | +0.010 |
Betty | +0.010 |
Neg logit contributions | |
Evan | -0.011 |
cand | -0.010 |
eighty | -0.010 |
cash | -0.010 |
pen | -0.009 |
Token | Tom |
Token ID | 4186 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
cash | +0.003 |
eighty | +0.003 |
pen | +0.003 |
Neg logit contributions | |
arge | -0.003 |
Judy | -0.003 |
Janet | -0.003 |
imi | -0.003 |
anne | -0.003 |
Token | tie |
Token ID | 9839 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Evan | +0.008 |
cand | +0.007 |
eighty | +0.007 |
cash | +0.007 |
penn | +0.006 |
Neg logit contributions | |
Judy | -0.011 |
Janet | -0.011 |
arge | -0.010 |
imi | -0.010 |
Betty | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Evan | +0.006 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.005 |
pen | +0.005 |
Neg logit contributions | |
Janet | -0.009 |
Judy | -0.009 |
arge | -0.009 |
Betty | -0.009 |
imi | -0.009 |
Token | r |
Token ID | 374 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
Judy | +0.034 |
arge | +0.034 |
Janet | +0.034 |
anne | +0.034 |
imi | +0.033 |
Neg logit contributions | |
cand | -0.033 |
eighty | -0.031 |
cash | -0.031 |
Evan | -0.031 |
penn | -0.030 |
Token | ags |
Token ID | 3775 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
Judy | +0.006 |
anne | +0.005 |
Betty | +0.005 |
Janet | +0.005 |
June | +0.005 |
Neg logit contributions | |
cand | -0.006 |
cash | -0.005 |
penn | -0.005 |
himself | -0.005 |
eighty | -0.005 |
Token | with |
Token ID | 351 |
Feature activation | -4.06e-02 |
Pos logit contributions | |
imi | +0.103 |
Bet | +0.102 |
arl | +0.101 |
arge | +0.100 |
oky | +0.100 |
Neg logit contributions | |
himself | -0.037 |
with | -0.031 |
Evan | -0.028 |
his | -0.026 |
penn | -0.025 |
Token | knots |
Token ID | 33620 |
Feature activation | -4.24e-01 |
Pos logit contributions | |
Evan | +0.001 |
eighty | +0.001 |
cand | +0.001 |
pen | +0.001 |
cash | +0.001 |
Neg logit contributions | |
Judy | -0.001 |
Janet | -0.001 |
arge | -0.001 |
Betty | -0.001 |
imi | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Evan | +0.011 |
cand | +0.010 |
eighty | +0.010 |
cash | +0.010 |
pen | +0.010 |
Neg logit contributions | |
Judy | -0.010 |
Janet | -0.010 |
arge | -0.010 |
Betty | -0.010 |
imi | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
iet | +0.007 |
anne | +0.007 |
imi | +0.007 |
arge | +0.007 |
inda | +0.007 |
Neg logit contributions | |
Evan | -0.004 |
cash | -0.003 |
Qu | -0.003 |
eighty | -0.003 |
himself | -0.003 |
Token | put |
Token ID | 1234 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
Janet | +0.006 |
Judy | +0.006 |
arge | +0.006 |
imi | +0.006 |
Betty | +0.006 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.004 |
pen | -0.004 |
Token | don |
Token ID | 836 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
Evan | +0.005 |
cand | +0.004 |
eighty | +0.004 |
cash | +0.004 |
pen | +0.004 |
Neg logit contributions | |
Judy | -0.006 |
Janet | -0.006 |
arge | -0.006 |
imi | -0.006 |
Betty | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
Judy | +0.024 |
arge | +0.024 |
Janet | +0.024 |
imi | +0.024 |
Betty | +0.023 |
Neg logit contributions | |
Evan | -0.021 |
cand | -0.020 |
eighty | -0.019 |
cash | -0.019 |
pen | -0.018 |
Token | you |
Token ID | 345 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
Judy | +0.009 |
Janet | +0.009 |
Betty | +0.009 |
imi | +0.009 |
Maria | +0.009 |
Neg logit contributions | |
Evan | -0.012 |
eighty | -0.012 |
pen | -0.011 |
cand | -0.011 |
ninety | -0.011 |
Token | write |
Token ID | 3551 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.002 |
cash | +0.001 |
penn | +0.001 |
Neg logit contributions | |
Janet | -0.003 |
Judy | -0.003 |
arge | -0.003 |
Betty | -0.003 |
imi | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
arge | -0.002 |
Judy | -0.002 |
Janet | -0.002 |
imi | -0.002 |
Bet | -0.002 |
Token | nice |
Token ID | 3621 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
Judy | +0.022 |
arge | +0.022 |
Janet | +0.022 |
imi | +0.021 |
Betty | +0.021 |
Neg logit contributions | |
Evan | -0.016 |
cand | -0.016 |
eighty | -0.015 |
cash | -0.015 |
penn | -0.014 |
Token | message |
Token ID | 3275 |
Feature activation | +6.16e-01 |
Pos logit contributions | |
Janet | +0.065 |
Judy | +0.065 |
imi | +0.064 |
arge | +0.064 |
Betty | +0.063 |
Neg logit contributions | |
Evan | -0.062 |
eighty | -0.056 |
cand | -0.056 |
pen | -0.054 |
cash | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
arge | +0.019 |
Bet | +0.019 |
Judy | +0.019 |
imi | +0.019 |
Janet | +0.019 |
Neg logit contributions | |
cand | -0.012 |
Evan | -0.011 |
marry | -0.011 |
eighty | -0.010 |
cash | -0.010 |
Token | each |
Token ID | 1123 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
Judy | +0.052 |
Janet | +0.052 |
arge | +0.051 |
imi | +0.051 |
Betty | +0.050 |
Neg logit contributions | |
Evan | -0.039 |
cand | -0.037 |
eighty | -0.035 |
cash | -0.034 |
pen | -0.033 |
Token | other |
Token ID | 584 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Evan | +0.005 |
cand | +0.005 |
cash | +0.005 |
eighty | +0.005 |
marry | +0.004 |
Neg logit contributions | |
Judy | -0.014 |
arge | -0.014 |
Janet | -0.014 |
imi | -0.014 |
Bet | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
Judy | +0.009 |
Bet | +0.009 |
Janet | +0.009 |
arge | +0.009 |
Betty | +0.008 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.007 |
marry | -0.007 |
eighty | -0.006 |
cash | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
imi | +0.001 |
zie | +0.001 |
arge | +0.001 |
iet | +0.001 |
arter | +0.001 |
Neg logit contributions | |
Evan | -0.001 |
cash | -0.001 |
Qu | -0.001 |
goodbye | -0.001 |
eighty | -0.001 |
Token | We |
Token ID | 1135 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
Judy | +0.008 |
arge | +0.008 |
Janet | +0.008 |
imi | +0.007 |
Betty | +0.007 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.008 |
eighty | -0.008 |
cash | -0.008 |
pen | -0.008 |
Token | tied |
Token ID | 8165 |
Feature activation | +4.54e-02 |
Pos logit contributions | |
Judy | +0.010 |
arge | +0.010 |
Janet | +0.010 |
imi | +0.009 |
Betty | +0.009 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.006 |
eighty | -0.005 |
cash | -0.005 |
pen | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +9.15e-01 |
Pos logit contributions | |
arge | +0.001 |
Judy | +0.001 |
Janet | +0.001 |
imi | +0.001 |
anne | +0.001 |
Neg logit contributions | |
Evan | -0.001 |
cand | -0.001 |
eighty | -0.001 |
cash | -0.001 |
penn | -0.001 |
Token | r |
Token ID | 374 |
Feature activation | +4.85e-01 |
Pos logit contributions | |
Judy | +0.023 |
arge | +0.023 |
Janet | +0.023 |
imi | +0.022 |
Betty | +0.022 |
Neg logit contributions | |
Evan | -0.023 |
cand | -0.022 |
eighty | -0.021 |
cash | -0.020 |
pen | -0.020 |
Token | ags |
Token ID | 3775 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
Judy | +0.012 |
Janet | +0.011 |
Betty | +0.011 |
anne | +0.011 |
Bet | +0.011 |
Neg logit contributions | |
cand | -0.013 |
Evan | -0.013 |
cash | -0.012 |
eighty | -0.012 |
penn | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
imi | +0.096 |
Bet | +0.094 |
arge | +0.093 |
Janet | +0.093 |
Judy | +0.091 |
Neg logit contributions | |
with | -0.027 |
himself | -0.026 |
e | -0.024 |
penn | -0.023 |
cand | -0.022 |
Token | we |
Token ID | 356 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
arge | +0.000 |
Judy | +0.000 |
Janet | +0.000 |
imi | +0.000 |
Bet | +0.000 |
Neg logit contributions | |
Evan | -0.000 |
cand | -0.000 |
eighty | -0.000 |
cash | -0.000 |
pen | -0.000 |
Token | were |
Token ID | 547 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
Judy | +0.006 |
Janet | +0.006 |
arge | +0.006 |
imi | +0.006 |
Betty | +0.006 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.004 |
pen | -0.004 |
Token | alert |
Token ID | 7995 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
arge | +0.016 |
Judy | +0.016 |
imi | +0.016 |
Janet | +0.016 |
Bet | +0.016 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.009 |
eighty | -0.009 |
cash | -0.008 |
penn | -0.008 |
Token | ." |
Token ID | 526 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Evan | +0.023 |
cand | +0.022 |
eighty | +0.021 |
cash | +0.020 |
pen | +0.019 |
Neg logit contributions | |
Janet | -0.032 |
Judy | -0.032 |
arge | -0.032 |
Bet | -0.031 |
imi | -0.031 |
Token | beard |
Token ID | 21213 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
Evan | +0.028 |
cand | +0.026 |
eighty | +0.024 |
cash | +0.024 |
penn | +0.023 |
Neg logit contributions | |
Janet | -0.028 |
Judy | -0.028 |
arge | -0.028 |
iet | -0.028 |
imi | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -4.05e-02 |
Pos logit contributions | |
Evan | +0.014 |
eighty | +0.013 |
cand | +0.013 |
cash | +0.013 |
penn | +0.012 |
Neg logit contributions | |
arge | -0.010 |
Janet | -0.010 |
Judy | -0.010 |
anne | -0.010 |
imi | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | -6.69e-02 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
penn | +0.001 |
cash | +0.001 |
Neg logit contributions | |
Judy | -0.001 |
Janet | -0.001 |
arge | -0.001 |
Betty | -0.001 |
imi | -0.001 |
Token | wore |
Token ID | 12408 |
Feature activation | +1.53e-01 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
arge | -0.002 |
Janet | -0.002 |
Judy | -0.002 |
imi | -0.002 |
anne | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
Janet | +0.005 |
Judy | +0.005 |
arge | +0.005 |
Betty | +0.005 |
imi | +0.005 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.002 |
eighty | -0.002 |
cash | -0.002 |
pen | -0.002 |
Token | very |
Token ID | 845 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
Judy | +0.012 |
arge | +0.011 |
Janet | +0.011 |
Betty | +0.011 |
imi | +0.011 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.009 |
eighty | -0.008 |
re | -0.008 |
penn | -0.008 |
Token | old |
Token ID | 1468 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Bet | +0.077 |
Janet | +0.076 |
Judy | +0.075 |
Lynn | +0.073 |
Betty | +0.073 |
Neg logit contributions | |
cand | -0.047 |
Evan | -0.047 |
penn | -0.045 |
goodbye | -0.045 |
eighty | -0.044 |
Token | coat |
Token ID | 13209 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
cand | +0.004 |
Evan | +0.004 |
cash | +0.004 |
eighty | +0.004 |
penn | +0.004 |
Neg logit contributions | |
Judy | -0.006 |
arge | -0.006 |
imi | -0.006 |
Bet | -0.006 |
Janet | -0.006 |
Token | which |
Token ID | 543 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
eighty | +0.003 |
cash | +0.003 |
penn | +0.003 |
Neg logit contributions | |
Janet | -0.004 |
arge | -0.004 |
Judy | -0.003 |
imi | -0.003 |
Betty | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Evan | +0.020 |
cand | +0.018 |
eighty | +0.018 |
pen | +0.018 |
cash | +0.018 |
Neg logit contributions | |
Judy | -0.026 |
Janet | -0.026 |
Betty | -0.025 |
arge | -0.025 |
Lynn | -0.024 |
Token | thick |
Token ID | 6546 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.010 |
eighty | +0.010 |
re | +0.009 |
marry | +0.009 |
Neg logit contributions | |
Judy | -0.016 |
arge | -0.016 |
imi | -0.016 |
Janet | -0.016 |
anne | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
eighty | +0.000 |
cash | +0.000 |
pen | +0.000 |
Neg logit contributions | |
Judy | -0.000 |
arge | -0.000 |
Janet | -0.000 |
imi | -0.000 |
Betty | -0.000 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +3.37e-01 |
Pos logit contributions | |
imi | +0.007 |
iet | +0.006 |
Bet | +0.006 |
Bree | +0.006 |
Janet | +0.006 |
Neg logit contributions | |
Evan | -0.006 |
eighty | -0.006 |
himself | -0.006 |
cand | -0.006 |
cash | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
arge | +0.011 |
imi | +0.011 |
Janet | +0.011 |
Judy | +0.011 |
Bet | +0.011 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.005 |
eighty | -0.005 |
cash | -0.005 |
penn | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
imi | +0.013 |
arge | +0.012 |
iet | +0.012 |
Janet | +0.012 |
arl | +0.012 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.011 |
eighty | -0.011 |
cash | -0.011 |
hairc | -0.010 |
Token | folder |
Token ID | 9483 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
Judy | +0.016 |
arge | +0.016 |
Janet | +0.016 |
imi | +0.016 |
anne | +0.015 |
Neg logit contributions | |
Evan | -0.014 |
cand | -0.014 |
cash | -0.013 |
eighty | -0.013 |
re | -0.012 |
Token | fell |
Token ID | 3214 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Judy | +0.001 |
arge | +0.001 |
Janet | +0.001 |
imi | +0.001 |
Betty | +0.001 |
Neg logit contributions | |
Evan | -0.001 |
cand | -0.001 |
eighty | -0.001 |
cash | -0.001 |
pen | -0.001 |
Token | from |
Token ID | 422 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
arge | +0.086 |
Judy | +0.084 |
imi | +0.080 |
anne | +0.080 |
Rachel | +0.079 |
Neg logit contributions | |
Evan | -0.038 |
cand | -0.036 |
re | -0.035 |
eighty | -0.035 |
goodbye | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
leys | +0.006 |
arge | +0.006 |
imi | +0.006 |
anne | +0.006 |
iet | +0.006 |
Neg logit contributions | |
Evan | -0.002 |
him | -0.002 |
eighty | -0.002 |
himself | -0.002 |
re | -0.002 |
Token | sky |
Token ID | 6766 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
Judy | +0.007 |
imi | +0.007 |
Janet | +0.007 |
arge | +0.007 |
anne | +0.007 |
Neg logit contributions | |
cash | -0.009 |
cand | -0.009 |
Evan | -0.008 |
eighty | -0.008 |
marry | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
imi | +0.008 |
arge | +0.008 |
Judy | +0.008 |
Janet | +0.008 |
Bet | +0.008 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
pen | -0.004 |
cash | -0.004 |
eighty | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | +1.86e-01 |
Pos logit contributions | |
imi | +0.002 |
iet | +0.002 |
Janet | +0.002 |
arge | +0.002 |
Bet | +0.002 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.002 |
eighty | -0.002 |
himself | -0.002 |
cash | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +7.32e-01 |
Pos logit contributions | |
Judy | +0.011 |
Janet | +0.011 |
arge | +0.011 |
imi | +0.011 |
Betty | +0.011 |
Neg logit contributions | |
cand | -0.008 |
Evan | -0.008 |
cash | -0.007 |
eighty | -0.007 |
pen | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
Judy | +0.021 |
arge | +0.021 |
Janet | +0.021 |
imi | +0.021 |
Betty | +0.021 |
Neg logit contributions | |
Evan | -0.015 |
cand | -0.014 |
eighty | -0.014 |
cash | -0.013 |
pen | -0.013 |
Token | big |
Token ID | 1263 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
arge | +0.020 |
Judy | +0.020 |
Janet | +0.020 |
imi | +0.020 |
anne | +0.019 |
Neg logit contributions | |
Evan | -0.016 |
cand | -0.014 |
cash | -0.014 |
re | -0.014 |
eighty | -0.013 |
Token | canvas |
Token ID | 21978 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
arge | +0.031 |
leys | +0.030 |
anne | +0.030 |
Janet | +0.029 |
Judy | +0.029 |
Neg logit contributions | |
Evan | -0.025 |
cand | -0.024 |
eighty | -0.023 |
re | -0.023 |
cash | -0.023 |
Token | sack |
Token ID | 23704 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
Judy | +0.008 |
arge | +0.008 |
imi | +0.008 |
Janet | +0.008 |
Betty | +0.008 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.006 |
pen | -0.005 |
eighty | -0.005 |
cash | -0.005 |
Token | fell |
Token ID | 3214 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
arge | +0.007 |
Judy | +0.007 |
Janet | +0.007 |
imi | +0.007 |
Betty | +0.007 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.006 |
eighty | -0.006 |
cash | -0.005 |
pen | -0.005 |
Token | from |
Token ID | 422 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
arge | +0.085 |
Judy | +0.083 |
anne | +0.081 |
imi | +0.081 |
Rachel | +0.079 |
Neg logit contributions | |
Evan | -0.039 |
himself | -0.036 |
cand | -0.036 |
eighty | -0.035 |
goodbye | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
anne | +0.014 |
arge | +0.014 |
imi | +0.014 |
iet | +0.014 |
Judy | +0.014 |
Neg logit contributions | |
Evan | -0.004 |
himself | -0.004 |
him | -0.004 |
eighty | -0.003 |
re | -0.003 |
Token | sky |
Token ID | 6766 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Judy | +0.009 |
arge | +0.009 |
Janet | +0.009 |
imi | +0.009 |
anne | +0.009 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.010 |
cash | -0.010 |
eighty | -0.009 |
penn | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +8.99e-02 |
Pos logit contributions | |
imi | +0.009 |
arge | +0.009 |
Janet | +0.009 |
Judy | +0.009 |
Bet | +0.009 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
pen | -0.005 |
cash | -0.005 |
eighty | -0.005 |
Token | Jo |
Token ID | 5302 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
Judy | +0.002 |
Janet | +0.002 |
arge | +0.002 |
imi | +0.002 |
Bet | +0.002 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.002 |
cash | -0.002 |
pen | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
arge | +0.019 |
imi | +0.019 |
Judy | +0.019 |
Janet | +0.019 |
Bet | +0.019 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.009 |
eighty | -0.008 |
cash | -0.008 |
pen | -0.008 |
Token | Emma |
Token ID | 18966 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Judy | +0.019 |
Janet | +0.019 |
Maria | +0.018 |
arge | +0.018 |
Betty | +0.018 |
Neg logit contributions | |
Evan | -0.015 |
cand | -0.015 |
eighty | -0.015 |
pen | -0.014 |
cash | -0.014 |
Token | could |
Token ID | 714 |
Feature activation | -2.88e-01 |
Pos logit contributions | |
Judy | +0.005 |
Janet | +0.005 |
arge | +0.005 |
anne | +0.005 |
imi | +0.005 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.004 |
penn | -0.004 |
Token | hear |
Token ID | 3285 |
Feature activation | -4.91e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.006 |
Neg logit contributions | |
Judy | -0.008 |
Janet | -0.008 |
arge | -0.008 |
imi | -0.008 |
Betty | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.009 |
eighty | +0.009 |
cash | +0.009 |
pen | +0.008 |
Neg logit contributions | |
Judy | -0.015 |
Janet | -0.014 |
arge | -0.014 |
Betty | -0.014 |
Maria | -0.014 |
Token | wh |
Token ID | 348 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
cash | +0.002 |
eighty | +0.002 |
pen | +0.002 |
Neg logit contributions | |
Judy | -0.002 |
arge | -0.002 |
Janet | -0.002 |
imi | -0.002 |
Betty | -0.002 |
Token | inn |
Token ID | 3732 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
Betty | +0.055 |
Judy | +0.055 |
Janet | +0.054 |
Bet | +0.052 |
Lynn | +0.051 |
Neg logit contributions | |
Evan | -0.067 |
pen | -0.065 |
eighty | -0.062 |
cand | -0.061 |
yle | -0.061 |
Token | ying |
Token ID | 1112 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
Judy | +0.023 |
Janet | +0.022 |
arge | +0.022 |
Bet | +0.022 |
imi | +0.022 |
Neg logit contributions | |
Evan | -0.022 |
cand | -0.021 |
eighty | -0.020 |
cash | -0.019 |
pen | -0.019 |
Token | sound |
Token ID | 2128 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
Evan | +0.011 |
cand | +0.011 |
eighty | +0.010 |
cash | +0.010 |
pen | +0.010 |
Neg logit contributions | |
Judy | -0.014 |
arge | -0.014 |
Janet | -0.014 |
imi | -0.014 |
Betty | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
Evan | +0.012 |
cand | +0.011 |
eighty | +0.011 |
cash | +0.011 |
pen | +0.010 |
Neg logit contributions | |
Judy | -0.014 |
arge | -0.014 |
Janet | -0.014 |
imi | -0.013 |
Betty | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | +1.44e-01 |
Pos logit contributions | |
Evan | +0.001 |
cash | +0.001 |
cand | +0.001 |
eighty | +0.001 |
pen | +0.001 |
Neg logit contributions | |
iet | -0.001 |
imi | -0.001 |
arge | -0.001 |
Bet | -0.001 |
Janet | -0.001 |
Token | escape |
Token ID | 6654 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.007 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.006 |
Neg logit contributions | |
Judy | -0.011 |
arge | -0.011 |
Janet | -0.011 |
imi | -0.011 |
Betty | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-01 |
Pos logit contributions | |
arge | +0.021 |
imi | +0.020 |
anne | +0.020 |
Janet | +0.020 |
Judy | +0.020 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.009 |
himself | -0.008 |
eighty | -0.008 |
cash | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
arge | +0.004 |
imi | +0.004 |
iet | +0.004 |
Judy | +0.004 |
Janet | +0.004 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.004 |
cash | -0.003 |
eighty | -0.003 |
pen | -0.003 |
Token | used |
Token ID | 973 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
Judy | +0.008 |
arge | +0.008 |
Janet | +0.008 |
imi | +0.008 |
Betty | +0.008 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.007 |
eighty | -0.006 |
cash | -0.006 |
pen | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
arge | +0.040 |
imi | +0.040 |
anne | +0.039 |
Judy | +0.039 |
Janet | +0.039 |
Neg logit contributions | |
Evan | -0.023 |
cand | -0.022 |
eighty | -0.021 |
cash | -0.020 |
penn | -0.020 |
Token | big |
Token ID | 1263 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
arge | +0.052 |
Janet | +0.052 |
Bet | +0.051 |
Judy | +0.051 |
oky | +0.049 |
Neg logit contributions | |
cand | -0.037 |
re | -0.037 |
Evan | -0.037 |
penn | -0.036 |
eighty | -0.035 |
Token | trunk |
Token ID | 21427 |
Feature activation | +9.67e-01 |
Pos logit contributions | |
arge | +0.065 |
Janet | +0.062 |
imi | +0.062 |
Judy | +0.062 |
Bet | +0.061 |
Neg logit contributions | |
cand | -0.057 |
Evan | -0.057 |
eighty | -0.054 |
penn | -0.053 |
cash | -0.051 |
Token | to |
Token ID | 284 |
Feature activation | +6.79e-01 |
Pos logit contributions | |
arge | +0.028 |
imi | +0.028 |
Judy | +0.027 |
Janet | +0.027 |
Bet | +0.027 |
Neg logit contributions | |
Evan | -0.020 |
cand | -0.020 |
eighty | -0.019 |
cash | -0.018 |
penn | -0.018 |
Token | make |
Token ID | 787 |
Feature activation | +5.79e-01 |
Pos logit contributions | |
Judy | +0.020 |
Janet | +0.019 |
Betty | +0.019 |
arge | +0.019 |
Bet | +0.019 |
Neg logit contributions | |
Evan | -0.015 |
cand | -0.014 |
eighty | -0.013 |
cash | -0.013 |
pen | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
Judy | +0.017 |
Janet | +0.017 |
arge | +0.017 |
Betty | +0.016 |
imi | +0.016 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.011 |
eighty | -0.011 |
cash | -0.011 |
pen | -0.010 |
Token | hole |
Token ID | 7604 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Judy | +0.006 |
Betty | +0.006 |
arge | +0.006 |
imi | +0.006 |
Janet | +0.005 |
Neg logit contributions | |
Evan | -0.014 |
cand | -0.014 |
eighty | -0.013 |
pen | -0.013 |
yle | -0.013 |
Token | she |
Token ID | 673 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
Judy | +0.015 |
Janet | +0.015 |
arge | +0.015 |
Betty | +0.014 |
Maria | +0.014 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.009 |
eighty | -0.008 |
cash | -0.008 |
pen | -0.008 |
Token | spun |
Token ID | 26843 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
Evan | +0.005 |
cand | +0.005 |
eighty | +0.005 |
cash | +0.004 |
pen | +0.004 |
Neg logit contributions | |
Judy | -0.006 |
arge | -0.006 |
Janet | -0.006 |
imi | -0.006 |
Betty | -0.006 |
Token | around |
Token ID | 1088 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
Judy | +0.009 |
arge | +0.009 |
Janet | +0.009 |
imi | +0.009 |
Betty | +0.009 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.007 |
eighty | -0.007 |
cash | -0.007 |
pen | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
Evan | +0.016 |
cand | +0.015 |
eighty | +0.015 |
cash | +0.014 |
pen | +0.014 |
Neg logit contributions | |
Judy | -0.022 |
Janet | -0.022 |
arge | -0.022 |
Betty | -0.022 |
imi | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
Judy | +0.009 |
Janet | +0.009 |
arge | +0.009 |
Betty | +0.009 |
Maria | +0.009 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.008 |
eighty | -0.008 |
cash | -0.007 |
pen | -0.007 |
Token | wh |
Token ID | 348 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.009 |
cash | +0.008 |
eighty | +0.008 |
pen | +0.008 |
Neg logit contributions | |
Judy | -0.009 |
Janet | -0.009 |
arge | -0.009 |
imi | -0.009 |
Betty | -0.009 |
Token | irl |
Token ID | 1901 |
Feature activation | +3.71e-01 |
Pos logit contributions | |
Betty | +0.054 |
Judy | +0.052 |
June | +0.051 |
Janet | +0.051 |
Bree | +0.050 |
Neg logit contributions | |
Evan | -0.066 |
pen | -0.064 |
yle | -0.062 |
eighty | -0.062 |
cand | -0.060 |
Token | ig |
Token ID | 328 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
Judy | +0.010 |
arge | +0.010 |
Janet | +0.010 |
imi | +0.010 |
Betty | +0.009 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.008 |
eighty | -0.008 |
cash | -0.008 |
pen | -0.008 |
Token | ig |
Token ID | 328 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
Judy | +0.011 |
arge | +0.010 |
imi | +0.010 |
Janet | +0.010 |
Bet | +0.010 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.010 |
eighty | -0.009 |
pen | -0.009 |
cash | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
Judy | +0.010 |
arge | +0.010 |
imi | +0.010 |
Janet | +0.010 |
Bet | +0.010 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.010 |
eighty | -0.009 |
pen | -0.009 |
cash | -0.009 |
Token | |
Token ID | 220 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
imi | +0.003 |
arge | +0.003 |
Janet | +0.003 |
Judy | +0.003 |
iet | +0.003 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.002 |
cash | -0.002 |
pen | -0.002 |
Token | Mom |
Token ID | 11254 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
arge | +0.015 |
Judy | +0.015 |
Janet | +0.015 |
imi | +0.015 |
anne | +0.015 |
Neg logit contributions | |
Evan | -0.011 |
cand | -0.011 |
eighty | -0.010 |
cash | -0.010 |
pen | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
arge | +0.006 |
iet | +0.006 |
lights | +0.006 |
Bet | +0.005 |
eways | +0.005 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.003 |
eighty | -0.003 |
pen | -0.003 |
re | -0.003 |
Token | A |
Token ID | 317 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Evan | +0.006 |
cand | +0.005 |
eighty | +0.005 |
cash | +0.005 |
pen | +0.005 |
Neg logit contributions | |
Judy | -0.007 |
arge | -0.007 |
Janet | -0.007 |
imi | -0.007 |
Betty | -0.007 |
Token | big |
Token ID | 1263 |
Feature activation | +9.11e-01 |
Pos logit contributions | |
Janet | +0.008 |
arge | +0.008 |
Judy | +0.008 |
imi | +0.008 |
zie | +0.008 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
re | -0.005 |
cash | -0.005 |
eighty | -0.004 |
Token | dog |
Token ID | 3290 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
arge | +0.028 |
Janet | +0.028 |
Judy | +0.028 |
anne | +0.028 |
Bet | +0.027 |
Neg logit contributions | |
Evan | -0.017 |
cand | -0.017 |
eighty | -0.016 |
cash | -0.016 |
re | -0.015 |
Token | ruined |
Token ID | 20484 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
arge | +0.006 |
Judy | +0.006 |
Janet | +0.006 |
imi | +0.005 |
Bet | +0.005 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.004 |
eighty | -0.004 |
pen | -0.004 |
cash | -0.004 |
Token | our |
Token ID | 674 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
anne | +0.074 |
arge | +0.074 |
Janet | +0.072 |
Bet | +0.072 |
Judy | +0.071 |
Neg logit contributions | |
Evan | -0.046 |
cand | -0.045 |
himself | -0.041 |
re | -0.041 |
cash | -0.041 |
Token | snow |
Token ID | 6729 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Janet | +0.014 |
Judy | +0.014 |
arge | +0.014 |
anne | +0.013 |
Bet | +0.013 |
Neg logit contributions | |
Evan | -0.017 |
cand | -0.017 |
eighty | -0.017 |
cash | -0.016 |
penn | -0.016 |
Token | man |
Token ID | 805 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Janet | +0.007 |
Judy | +0.007 |
Donna | +0.007 |
arge | +0.007 |
Maria | +0.007 |
Neg logit contributions | |
cand | -0.005 |
cash | -0.005 |
re | -0.005 |
Evan | -0.005 |
himself | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
Judy | +0.039 |
arge | +0.039 |
Janet | +0.039 |
imi | +0.038 |
Bet | +0.037 |
Neg logit contributions | |
Evan | -0.032 |
cand | -0.031 |
eighty | -0.029 |
cash | -0.028 |
pen | -0.028 |
Token | He |
Token ID | 679 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
Evan | +0.011 |
cand | +0.011 |
eighty | +0.010 |
penn | +0.010 |
pen | +0.010 |
Neg logit contributions | |
Judy | -0.013 |
Janet | -0.013 |
Betty | -0.013 |
arge | -0.013 |
imi | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.002 |
eighty | +0.002 |
pen | +0.002 |
cash | +0.002 |
Neg logit contributions | |
arge | -0.003 |
Judy | -0.003 |
Janet | -0.003 |
imi | -0.003 |
Betty | -0.003 |
Token | who |
Token ID | 508 |
Feature activation | -1.15e-01 |
Pos logit contributions | |
arge | +0.017 |
imi | +0.017 |
Judy | +0.017 |
anne | +0.017 |
Janet | +0.017 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.007 |
eighty | -0.007 |
cash | -0.006 |
pen | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.002 |
cash | +0.002 |
pen | +0.002 |
Neg logit contributions | |
Judy | -0.004 |
Janet | -0.003 |
arge | -0.003 |
imi | -0.003 |
Betty | -0.003 |
Token | wearing |
Token ID | 5762 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
cash | +0.002 |
eighty | +0.002 |
pen | +0.002 |
Neg logit contributions | |
Judy | -0.002 |
Janet | -0.002 |
arge | -0.002 |
imi | -0.002 |
Betty | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
eighty | +0.004 |
cash | +0.003 |
pen | +0.003 |
Neg logit contributions | |
Judy | -0.006 |
Janet | -0.006 |
arge | -0.006 |
Betty | -0.006 |
imi | -0.006 |
Token | very |
Token ID | 845 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
cand | +0.005 |
Evan | +0.005 |
eighty | +0.005 |
marry | +0.005 |
re | +0.005 |
Neg logit contributions | |
arge | -0.007 |
Judy | -0.007 |
Janet | -0.007 |
imi | -0.007 |
Betty | -0.007 |
Token | fine |
Token ID | 3734 |
Feature activation | +9.47e-01 |
Pos logit contributions | |
Bet | +0.084 |
Janet | +0.081 |
arge | +0.079 |
Judy | +0.079 |
Betty | +0.078 |
Neg logit contributions | |
cand | -0.036 |
Evan | -0.034 |
penn | -0.033 |
goodbye | -0.033 |
marry | -0.033 |
Token | dress |
Token ID | 6576 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
arge | +0.028 |
Judy | +0.028 |
Janet | +0.028 |
imi | +0.027 |
Bet | +0.027 |
Neg logit contributions | |
Evan | -0.019 |
cand | -0.019 |
eighty | -0.018 |
marry | -0.017 |
cash | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +5.58e-02 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
eighty | +0.004 |
cash | +0.004 |
pen | +0.004 |
Neg logit contributions | |
Judy | -0.006 |
arge | -0.006 |
Janet | -0.005 |
imi | -0.005 |
Bet | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +4.95e-02 |
Pos logit contributions | |
iet | +0.002 |
arge | +0.002 |
imi | +0.002 |
lights | +0.002 |
anne | +0.002 |
Neg logit contributions | |
Evan | -0.001 |
cand | -0.001 |
cash | -0.001 |
eighty | -0.001 |
Qu | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
arge | +0.002 |
Janet | +0.002 |
imi | +0.002 |
lights | +0.002 |
Judy | +0.002 |
Neg logit contributions | |
Evan | -0.001 |
pen | -0.001 |
eighty | -0.001 |
cand | -0.001 |
Mont | -0.001 |
Token | lies |
Token ID | 7363 |
Feature activation | -2.79e-02 |
Pos logit contributions | |
Evan | +0.012 |
cand | +0.011 |
eighty | +0.010 |
cash | +0.010 |
yle | +0.010 |
Neg logit contributions | |
Judy | -0.009 |
Betty | -0.009 |
anne | -0.009 |
imi | -0.009 |
arge | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | +9.05e-02 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
penn | +0.001 |
Neg logit contributions | |
arge | -0.001 |
Janet | -0.001 |
Judy | -0.001 |
imi | -0.001 |
Bet | -0.001 |
Token | his |
Token ID | 465 |
Feature activation | -1.89e-01 |
Pos logit contributions | |
Judy | +0.003 |
arge | +0.003 |
Janet | +0.003 |
imi | +0.003 |
Betty | +0.003 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.001 |
eighty | -0.001 |
cash | -0.001 |
pen | -0.001 |
Token | bed |
Token ID | 3996 |
Feature activation | -9.79e-02 |
Pos logit contributions | |
Evan | +0.005 |
eighty | +0.005 |
pen | +0.005 |
cand | +0.004 |
cash | +0.004 |
Neg logit contributions | |
imi | -0.004 |
arge | -0.004 |
Judy | -0.004 |
Betty | -0.004 |
anne | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.002 |
cash | +0.002 |
pen | +0.002 |
Neg logit contributions | |
Judy | -0.003 |
Janet | -0.003 |
arge | -0.003 |
imi | -0.003 |
Betty | -0.003 |
Token | wh |
Token ID | 348 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
pen | +0.001 |
cash | +0.001 |
Neg logit contributions | |
Judy | -0.001 |
arge | -0.001 |
Janet | -0.001 |
imi | -0.001 |
Betty | -0.001 |
Token | ines |
Token ID | 1127 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
Betty | +0.042 |
Judy | +0.042 |
Janet | +0.040 |
Bet | +0.039 |
Bree | +0.038 |
Neg logit contributions | |
Evan | -0.076 |
pen | -0.073 |
eighty | -0.072 |
penn | -0.071 |
cand | -0.070 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
Judy | +0.039 |
arge | +0.039 |
Janet | +0.038 |
imi | +0.038 |
Betty | +0.038 |
Neg logit contributions | |
Evan | -0.040 |
eighty | -0.037 |
cand | -0.037 |
cash | -0.035 |
penn | -0.034 |
Token | Anna |
Token ID | 11735 |
Feature activation | +4.45e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
eighty | +0.003 |
cash | +0.003 |
pen | +0.003 |
Neg logit contributions | |
Judy | -0.003 |
arge | -0.003 |
Janet | -0.003 |
imi | -0.003 |
Betty | -0.003 |
Token | is |
Token ID | 318 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
imi | +0.010 |
Lynn | +0.009 |
iet | +0.009 |
Judy | +0.009 |
anne | +0.009 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.012 |
eighty | -0.011 |
penn | -0.011 |
cash | -0.011 |
Token | worried |
Token ID | 7960 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
cash | +0.004 |
pen | +0.004 |
eighty | +0.003 |
Neg logit contributions | |
Judy | -0.003 |
Janet | -0.003 |
arge | -0.003 |
Betty | -0.003 |
imi | -0.003 |
Token | him |
Token ID | 683 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
Evan | +0.005 |
eighty | +0.004 |
cand | +0.004 |
pen | +0.004 |
cash | +0.004 |
Neg logit contributions | |
Judy | -0.009 |
Janet | -0.009 |
arge | -0.009 |
Betty | -0.009 |
imi | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.009 |
eighty | +0.009 |
cash | +0.008 |
penn | +0.008 |
Neg logit contributions | |
Janet | -0.012 |
Judy | -0.012 |
Betty | -0.012 |
arge | -0.012 |
imi | -0.012 |
Token | He |
Token ID | 679 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
cash | +0.003 |
eighty | +0.002 |
traded | +0.002 |
Neg logit contributions | |
iet | -0.005 |
arge | -0.005 |
imi | -0.005 |
Judy | -0.005 |
Janet | -0.005 |
Token | used |
Token ID | 973 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Evan | +0.006 |
cand | +0.006 |
eighty | +0.005 |
pen | +0.005 |
penn | +0.005 |
Neg logit contributions | |
Janet | -0.006 |
Judy | -0.005 |
arge | -0.005 |
Betty | -0.005 |
imi | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Janet | +0.040 |
Judy | +0.040 |
arge | +0.039 |
Betty | +0.039 |
imi | +0.039 |
Neg logit contributions | |
Evan | -0.021 |
cand | -0.019 |
eighty | -0.018 |
cash | -0.017 |
pen | -0.017 |
Token | big |
Token ID | 1263 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
arge | +0.038 |
Judy | +0.037 |
imi | +0.037 |
Janet | +0.036 |
anne | +0.036 |
Neg logit contributions | |
Evan | -0.034 |
cand | -0.034 |
cash | -0.032 |
penn | -0.032 |
eighty | -0.032 |
Token | truck |
Token ID | 7779 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Judy | +0.050 |
arge | +0.050 |
Janet | +0.050 |
imi | +0.049 |
Betty | +0.048 |
Neg logit contributions | |
Evan | -0.068 |
cand | -0.065 |
eighty | -0.063 |
cash | -0.062 |
pen | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
Janet | +0.009 |
Judy | +0.009 |
Betty | +0.009 |
arge | +0.009 |
Bet | +0.008 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.011 |
eighty | -0.011 |
yle | -0.010 |
penn | -0.010 |
Token | reverse |
Token ID | 9575 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
Judy | +0.024 |
arge | +0.024 |
Janet | +0.024 |
imi | +0.024 |
Betty | +0.024 |
Neg logit contributions | |
Evan | -0.014 |
cand | -0.013 |
eighty | -0.012 |
cash | -0.012 |
pen | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
arge | +0.016 |
Judy | +0.016 |
imi | +0.016 |
Janet | +0.015 |
Bet | +0.015 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.010 |
eighty | -0.009 |
cash | -0.009 |
pen | -0.009 |
Token | car |
Token ID | 1097 |
Feature activation | +8.64e-01 |
Pos logit contributions | |
Judy | +0.022 |
Janet | +0.021 |
arge | +0.021 |
imi | +0.021 |
anne | +0.021 |
Neg logit contributions | |
Evan | -0.022 |
cand | -0.021 |
cash | -0.020 |
eighty | -0.020 |
penn | -0.019 |
Token | ay |
Token ID | 323 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
Evan | +0.026 |
cand | +0.026 |
eighty | +0.025 |
pen | +0.025 |
cash | +0.024 |
Neg logit contributions | |
Judy | -0.017 |
arge | -0.017 |
Janet | -0.016 |
Betty | -0.016 |
imi | -0.016 |
Token | ons |
Token ID | 684 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
cand | +0.003 |
Evan | +0.002 |
pen | +0.002 |
penn | +0.002 |
eighty | +0.002 |
Neg logit contributions | |
Judy | -0.003 |
Bet | -0.003 |
arge | -0.003 |
imi | -0.003 |
Janet | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -3.54e-02 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
Judy | -0.001 |
Janet | -0.001 |
arge | -0.001 |
imi | -0.001 |
Betty | -0.001 |
Token | write |
Token ID | 3551 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
arge | -0.001 |
Judy | -0.001 |
imi | -0.001 |
Janet | -0.001 |
Betty | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
imi | +0.006 |
arge | +0.006 |
Bet | +0.006 |
Judy | +0.006 |
Janet | +0.006 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.003 |
pen | -0.003 |
Token | nice |
Token ID | 3621 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
zie | +0.033 |
imi | +0.032 |
Betty | +0.032 |
Judy | +0.032 |
anne | +0.032 |
Neg logit contributions | |
cand | -0.024 |
marry | -0.022 |
cash | -0.022 |
trade | -0.021 |
eighty | -0.021 |
Token | message |
Token ID | 3275 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
arge | +0.058 |
imi | +0.057 |
Bet | +0.057 |
Judy | +0.057 |
Janet | +0.056 |
Neg logit contributions | |
cand | -0.060 |
Evan | -0.057 |
cash | -0.056 |
eighty | -0.053 |
marry | -0.053 |
Token | to |
Token ID | 284 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
imi | +0.017 |
arge | +0.017 |
Bet | +0.017 |
Judy | +0.017 |
Janet | +0.017 |
Neg logit contributions | |
cand | -0.009 |
Evan | -0.009 |
marry | -0.008 |
eighty | -0.008 |
cash | -0.008 |
Token | each |
Token ID | 1123 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
arge | +0.043 |
Judy | +0.043 |
Janet | +0.043 |
imi | +0.043 |
Bet | +0.043 |
Neg logit contributions | |
Evan | -0.030 |
cand | -0.028 |
eighty | -0.027 |
cash | -0.026 |
pen | -0.025 |
Token | other |
Token ID | 584 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.007 |
cash | +0.006 |
eighty | +0.006 |
pen | +0.006 |
Neg logit contributions | |
arge | -0.018 |
imi | -0.018 |
Judy | -0.018 |
Janet | -0.018 |
Bet | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.007 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.006 |
Neg logit contributions | |
Judy | -0.007 |
Janet | -0.007 |
arge | -0.007 |
imi | -0.007 |
Betty | -0.007 |
Token | farm |
Token ID | 5318 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
Janet | +0.018 |
Judy | +0.017 |
imi | +0.017 |
anne | +0.017 |
arge | +0.017 |
Neg logit contributions | |
cand | -0.017 |
Evan | -0.017 |
cash | -0.017 |
re | -0.016 |
eighty | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +6.66e-02 |
Pos logit contributions | |
imi | +0.020 |
arge | +0.019 |
Janet | +0.019 |
Judy | +0.019 |
Bet | +0.019 |
Neg logit contributions | |
Evan | -0.013 |
cand | -0.012 |
cash | -0.012 |
pen | -0.011 |
eighty | -0.011 |
Token | He |
Token ID | 679 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
Judy | +0.002 |
arge | +0.002 |
Janet | +0.002 |
imi | +0.002 |
Betty | +0.002 |
Neg logit contributions | |
Evan | -0.001 |
cand | -0.001 |
eighty | -0.001 |
cash | -0.001 |
pen | -0.001 |
Token | used |
Token ID | 973 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
eighty | +0.004 |
cash | +0.004 |
pen | +0.004 |
Neg logit contributions | |
Judy | -0.005 |
arge | -0.005 |
Janet | -0.005 |
imi | -0.005 |
Betty | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
arge | +0.040 |
Judy | +0.040 |
Janet | +0.040 |
imi | +0.040 |
anne | +0.039 |
Neg logit contributions | |
Evan | -0.020 |
cand | -0.018 |
eighty | -0.017 |
cash | -0.016 |
pen | -0.016 |
Token | big |
Token ID | 1263 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
arge | +0.048 |
Janet | +0.047 |
Judy | +0.046 |
imi | +0.046 |
lights | +0.046 |
Neg logit contributions | |
cand | -0.030 |
re | -0.030 |
penn | -0.030 |
coin | -0.029 |
Evan | -0.029 |
Token | rake |
Token ID | 47885 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
arge | +0.068 |
Janet | +0.066 |
Judy | +0.065 |
anne | +0.064 |
Maria | +0.064 |
Neg logit contributions | |
cand | -0.050 |
eighty | -0.048 |
Evan | -0.048 |
penn | -0.047 |
re | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
Judy | +0.023 |
arge | +0.023 |
Janet | +0.023 |
imi | +0.022 |
Betty | +0.022 |
Neg logit contributions | |
Evan | -0.020 |
cand | -0.019 |
eighty | -0.018 |
cash | -0.018 |
pen | -0.018 |
Token | scrape |
Token ID | 42778 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
arge | +0.031 |
imi | +0.031 |
Judy | +0.031 |
Janet | +0.031 |
anne | +0.031 |
Neg logit contributions | |
Evan | -0.018 |
cand | -0.017 |
cash | -0.016 |
eighty | -0.015 |
pen | -0.015 |
Token | all |
Token ID | 477 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
Judy | +0.023 |
arge | +0.023 |
Janet | +0.023 |
imi | +0.023 |
anne | +0.022 |
Neg logit contributions | |
Evan | -0.014 |
cand | -0.013 |
eighty | -0.013 |
cash | -0.012 |
pen | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +5.61e-02 |
Pos logit contributions | |
arge | +0.011 |
Judy | +0.011 |
Janet | +0.011 |
imi | +0.011 |
Bet | +0.011 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.006 |
eighty | -0.005 |
cash | -0.005 |
pen | -0.005 |
Token | listened |
Token ID | 16399 |
Feature activation | -9.82e-01 |
Pos logit contributions | |
arge | +0.027 |
Judy | +0.027 |
imi | +0.027 |
Janet | +0.027 |
Bet | +0.026 |
Neg logit contributions | |
Evan | -0.019 |
cand | -0.018 |
eighty | -0.017 |
pen | -0.016 |
cash | -0.016 |
Token | carefully |
Token ID | 7773 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
Evan | +0.018 |
cand | +0.017 |
eighty | +0.016 |
cash | +0.016 |
pen | +0.015 |
Neg logit contributions | |
imi | -0.031 |
arge | -0.031 |
Janet | -0.031 |
Judy | -0.031 |
Bet | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
Judy | -0.002 |
arge | -0.002 |
Janet | -0.002 |
imi | -0.002 |
Betty | -0.001 |
Token | heard |
Token ID | 2982 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
Judy | -0.001 |
Janet | -0.001 |
Betty | -0.001 |
arge | -0.001 |
Maria | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
eighty | +0.003 |
cash | +0.003 |
pen | +0.003 |
Neg logit contributions | |
Judy | -0.005 |
Janet | -0.005 |
arge | -0.005 |
imi | -0.005 |
Betty | -0.005 |
Token | wh |
Token ID | 348 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
arge | +0.000 |
Janet | +0.000 |
imi | +0.000 |
Judy | +0.000 |
anne | +0.000 |
Neg logit contributions | |
Evan | -0.000 |
cand | -0.000 |
eighty | -0.000 |
pen | -0.000 |
cash | -0.000 |
Token | izzy |
Token ID | 40593 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
Betty | +0.053 |
Judy | +0.052 |
Janet | +0.050 |
June | +0.050 |
Lynn | +0.049 |
Neg logit contributions | |
Evan | -0.063 |
pen | -0.061 |
yle | -0.059 |
eighty | -0.059 |
penn | -0.058 |
Token | sound |
Token ID | 2128 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
Judy | +0.006 |
arge | +0.006 |
Janet | +0.006 |
imi | +0.006 |
anne | +0.006 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.003 |
eighty | -0.003 |
cash | -0.003 |
pen | -0.003 |
Token | until |
Token ID | 1566 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
Evan | +0.013 |
cand | +0.013 |
eighty | +0.012 |
cash | +0.012 |
penn | +0.011 |
Neg logit contributions | |
Judy | -0.014 |
Janet | -0.014 |
arge | -0.014 |
anne | -0.014 |
Betty | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
Judy | +0.018 |
arge | +0.018 |
Janet | +0.018 |
imi | +0.018 |
Betty | +0.018 |
Neg logit contributions | |
Evan | -0.013 |
cand | -0.013 |
eighty | -0.012 |
cash | -0.012 |
pen | -0.011 |
Token | went |
Token ID | 1816 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
eighty | +0.003 |
pen | +0.003 |
cash | +0.003 |
Neg logit contributions | |
arge | -0.005 |
imi | -0.005 |
Janet | -0.005 |
Judy | -0.005 |
Betty | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
Evan | +0.012 |
cand | +0.011 |
eighty | +0.010 |
cash | +0.010 |
pen | +0.010 |
Neg logit contributions | |
arge | -0.020 |
Judy | -0.020 |
imi | -0.020 |
Janet | -0.020 |
Bet | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
Judy | -0.001 |
Janet | -0.001 |
arge | -0.001 |
Betty | -0.001 |
imi | -0.001 |
Token | printer |
Token ID | 20632 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
Judy | +0.001 |
arge | +0.001 |
Janet | +0.001 |
imi | +0.001 |
Bet | +0.001 |
Neg logit contributions | |
Evan | -0.001 |
cand | -0.001 |
cash | -0.001 |
eighty | -0.001 |
penn | -0.000 |
Token | began |
Token ID | 2540 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
Judy | +0.001 |
Janet | +0.001 |
arge | +0.001 |
imi | +0.001 |
Betty | +0.001 |
Neg logit contributions | |
Evan | -0.001 |
cand | -0.001 |
eighty | -0.001 |
cash | -0.001 |
pen | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
imi | +0.003 |
arge | +0.003 |
Judy | +0.003 |
Janet | +0.003 |
anne | +0.003 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.002 |
cash | -0.002 |
pen | -0.002 |
Token | wh |
Token ID | 348 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Evan | +0.015 |
cand | +0.014 |
eighty | +0.013 |
cash | +0.013 |
pen | +0.013 |
Neg logit contributions | |
imi | -0.019 |
arge | -0.019 |
Judy | -0.019 |
anne | -0.019 |
Janet | -0.019 |
Token | ir |
Token ID | 343 |
Feature activation | +5.34e-01 |
Pos logit contributions | |
Betty | +0.054 |
Judy | +0.052 |
Janet | +0.050 |
June | +0.050 |
Bet | +0.050 |
Neg logit contributions | |
Evan | -0.063 |
pen | -0.063 |
yle | -0.059 |
eighty | -0.059 |
penn | -0.058 |
Token | r |
Token ID | 81 |
Feature activation | +8.96e-01 |
Pos logit contributions | |
Judy | +0.015 |
arge | +0.014 |
Janet | +0.014 |
imi | +0.014 |
anne | +0.014 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.012 |
eighty | -0.011 |
cash | -0.011 |
penn | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -7.91e-02 |
Pos logit contributions | |
Judy | +0.024 |
arge | +0.024 |
Janet | +0.024 |
imi | +0.024 |
Betty | +0.023 |
Neg logit contributions | |
Evan | -0.021 |
cand | -0.019 |
eighty | -0.019 |
cash | -0.018 |
pen | -0.018 |
Token | print |
Token ID | 3601 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
imi | -0.002 |
arge | -0.002 |
iet | -0.002 |
Judy | -0.002 |
Bet | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
arge | +0.005 |
Judy | +0.005 |
imi | +0.005 |
Janet | +0.005 |
Bet | +0.005 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.004 |
eighty | -0.003 |
cash | -0.003 |
pen | -0.003 |
Token | faster |
Token ID | 5443 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
arge | +0.012 |
Judy | +0.012 |
Janet | +0.012 |
imi | +0.012 |
anne | +0.011 |
Neg logit contributions | |
Evan | -0.011 |
cand | -0.011 |
eighty | -0.010 |
cash | -0.010 |
pen | -0.010 |
Token | than |
Token ID | 621 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.007 |
cash | +0.006 |
eighty | +0.006 |
pen | +0.006 |
Neg logit contributions | |
Judy | -0.008 |
Janet | -0.008 |
arge | -0.008 |
imi | -0.008 |
Betty | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Evan | +0.007 |
cash | +0.007 |
cand | +0.007 |
eighty | +0.006 |
pen | +0.006 |
Neg logit contributions | |
Judy | -0.010 |
Janet | -0.010 |
Betty | -0.010 |
Maria | -0.010 |
arge | -0.010 |
Token | clouds |
Token ID | 15114 |
Feature activation | +2.48e-01 |
Pos logit contributions | |
Evan | +0.011 |
cand | +0.010 |
eighty | +0.009 |
cash | +0.009 |
pen | +0.009 |
Neg logit contributions | |
arge | -0.012 |
Judy | -0.012 |
Janet | -0.011 |
imi | -0.011 |
Betty | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
Judy | +0.006 |
Janet | +0.006 |
Betty | +0.006 |
anne | +0.006 |
Maria | +0.006 |
Neg logit contributions | |
Evan | -0.006 |
cash | -0.006 |
cand | -0.006 |
eighty | -0.006 |
penn | -0.005 |
Token | wh |
Token ID | 348 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
cash | +0.000 |
eighty | +0.000 |
pen | +0.000 |
Neg logit contributions | |
Judy | -0.000 |
Janet | -0.000 |
Betty | -0.000 |
arge | -0.000 |
Lynn | -0.000 |
Token | izz |
Token ID | 6457 |
Feature activation | -9.16e-02 |
Pos logit contributions | |
Judy | +0.051 |
Betty | +0.051 |
Janet | +0.050 |
Lynn | +0.048 |
Bet | +0.048 |
Neg logit contributions | |
Evan | -0.066 |
pen | -0.062 |
cand | -0.061 |
eighty | -0.061 |
yle | -0.060 |
Token | ed |
Token ID | 276 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.002 |
cash | +0.002 |
pen | +0.002 |
Neg logit contributions | |
Judy | -0.002 |
arge | -0.002 |
Janet | -0.002 |
imi | -0.002 |
anne | -0.002 |
Token | past |
Token ID | 1613 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.007 |
eighty | +0.007 |
cash | +0.007 |
yle | +0.006 |
Neg logit contributions | |
Judy | -0.007 |
Janet | -0.007 |
Betty | -0.007 |
Maria | -0.007 |
arge | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
Evan | +0.003 |
eighty | +0.003 |
cash | +0.003 |
cand | +0.003 |
marry | +0.002 |
Neg logit contributions | |
Judy | -0.005 |
arge | -0.005 |
imi | -0.005 |
Betty | -0.005 |
Janet | -0.005 |
Token | trees |
Token ID | 7150 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
arge | +0.004 |
Judy | +0.004 |
imi | +0.004 |
Janet | +0.004 |
iet | +0.004 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
eighty | -0.005 |
cash | -0.005 |
pen | -0.004 |
Token | icked |
Token ID | 9484 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Evan | +0.019 |
cand | +0.018 |
cash | +0.018 |
eighty | +0.018 |
hairc | +0.017 |
Neg logit contributions | |
Judy | -0.014 |
Janet | -0.014 |
imi | -0.014 |
arge | -0.014 |
Betty | -0.014 |
Token | Anna |
Token ID | 11735 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
Judy | +0.049 |
Janet | +0.047 |
arge | +0.047 |
imi | +0.047 |
Betty | +0.047 |
Neg logit contributions | |
Evan | -0.040 |
cand | -0.038 |
eighty | -0.036 |
cash | -0.035 |
pen | -0.035 |
Token | and |
Token ID | 290 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
anne | +0.008 |
iet | +0.007 |
Judy | +0.007 |
June | +0.007 |
Betty | +0.007 |
Neg logit contributions | |
Evan | -0.010 |
eighty | -0.009 |
yle | -0.009 |
cash | -0.008 |
cand | -0.008 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.008 |
eighty | +0.008 |
cash | +0.008 |
pen | +0.008 |
Neg logit contributions | |
Judy | -0.009 |
arge | -0.009 |
Janet | -0.009 |
imi | -0.009 |
Betty | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
Judy | +0.003 |
June | +0.003 |
anne | +0.003 |
Betty | +0.003 |
Maria | +0.003 |
Neg logit contributions | |
Evan | -0.004 |
eighty | -0.003 |
cash | -0.003 |
yle | -0.003 |
ninety | -0.003 |
Token | wh |
Token ID | 348 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Evan | +0.012 |
cand | +0.011 |
eighty | +0.011 |
cash | +0.010 |
penn | +0.010 |
Neg logit contributions | |
arge | -0.016 |
imi | -0.016 |
Janet | -0.016 |
Judy | -0.016 |
Bet | -0.015 |
Token | ined |
Token ID | 1389 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Judy | +0.053 |
Betty | +0.053 |
Janet | +0.051 |
Lynn | +0.050 |
arge | +0.050 |
Neg logit contributions | |
Evan | -0.062 |
cand | -0.059 |
eighty | -0.058 |
pen | -0.058 |
penn | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -3.57e-02 |
Pos logit contributions | |
Judy | +0.033 |
Janet | +0.033 |
arge | +0.033 |
imi | +0.032 |
Betty | +0.032 |
Neg logit contributions | |
Evan | -0.029 |
cand | -0.028 |
eighty | -0.027 |
cash | -0.026 |
pen | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
Evan | +0.001 |
eighty | +0.000 |
Qu | +0.000 |
himself | +0.000 |
cand | +0.000 |
Neg logit contributions | |
arge | -0.001 |
Janet | -0.001 |
iet | -0.001 |
imi | -0.001 |
anne | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.79e-03 |
Pos logit contributions | |
Evan | +0.000 |
himself | +0.000 |
eighty | +0.000 |
cand | +0.000 |
Qu | +0.000 |
Neg logit contributions | |
arge | -0.000 |
Janet | -0.000 |
Judy | -0.000 |
iet | -0.000 |
anne | -0.000 |
Token | " |
Token ID | 1 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
Janet | +0.000 |
arge | +0.000 |
Judy | +0.000 |
imi | +0.000 |
anne | +0.000 |
Neg logit contributions | |
Evan | -0.000 |
eighty | -0.000 |
cand | -0.000 |
cash | -0.000 |
pen | -0.000 |
Token | round |
Token ID | 744 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
Evan | +0.038 |
cand | +0.036 |
cash | +0.035 |
eighty | +0.034 |
penn | +0.033 |
Neg logit contributions | |
anne | -0.037 |
Judy | -0.035 |
arge | -0.035 |
Janet | -0.034 |
Bet | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Evan | +0.011 |
cand | +0.010 |
eighty | +0.010 |
cash | +0.009 |
pen | +0.009 |
Neg logit contributions | |
Judy | -0.011 |
arge | -0.011 |
Janet | -0.011 |
imi | -0.011 |
Betty | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.005 |
Neg logit contributions | |
imi | -0.009 |
arge | -0.009 |
Janet | -0.009 |
Judy | -0.009 |
Bet | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
Evan | +0.013 |
cand | +0.012 |
eighty | +0.011 |
cash | +0.011 |
pen | +0.011 |
Neg logit contributions | |
Janet | -0.016 |
Judy | -0.016 |
arge | -0.016 |
imi | -0.016 |
Betty | -0.015 |
Token | S |
Token ID | 50 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Evan | +0.016 |
cand | +0.015 |
eighty | +0.015 |
cash | +0.014 |
pen | +0.014 |
Neg logit contributions | |
Judy | -0.012 |
arge | -0.012 |
iet | -0.011 |
Bet | -0.011 |
Janet | -0.011 |
Token | oph |
Token ID | 2522 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
Evan | +0.033 |
cand | +0.030 |
eighty | +0.030 |
cash | +0.029 |
penn | +0.028 |
Neg logit contributions | |
Judy | -0.028 |
arge | -0.028 |
Janet | -0.028 |
imi | -0.028 |
anne | -0.027 |
Token | ie |
Token ID | 494 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
Evan | +0.078 |
cand | +0.077 |
eighty | +0.073 |
penn | +0.070 |
cash | +0.070 |
Neg logit contributions | |
Janet | -0.064 |
Judy | -0.062 |
Bet | -0.062 |
Betty | -0.061 |
arge | -0.061 |
Token | had |
Token ID | 550 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
cash | +0.002 |
eighty | +0.002 |
penn | +0.002 |
Neg logit contributions | |
Judy | -0.003 |
arge | -0.003 |
Janet | -0.003 |
anne | -0.003 |
imi | -0.003 |
Token | had |
Token ID | 550 |
Feature activation | +3.62e-02 |
Pos logit contributions | |
Judy | +0.007 |
arge | +0.007 |
Janet | +0.007 |
imi | +0.007 |
Betty | +0.007 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
eighty | -0.004 |
cash | -0.004 |
pen | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
Judy | +0.001 |
arge | +0.001 |
Janet | +0.001 |
imi | +0.001 |
Betty | +0.001 |
Neg logit contributions | |
Evan | -0.001 |
cand | -0.001 |
eighty | -0.001 |
cash | -0.001 |
pen | -0.001 |
Token | very |
Token ID | 845 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Evan | +0.012 |
cand | +0.011 |
eighty | +0.011 |
cash | +0.010 |
penn | +0.010 |
Neg logit contributions | |
Judy | -0.014 |
Janet | -0.014 |
arge | -0.014 |
imi | -0.013 |
Betty | -0.013 |
Token | so |
Token ID | 523 |
Feature activation | -2.21e-01 |
Pos logit contributions | |
Judy | +0.014 |
Janet | +0.014 |
arge | +0.014 |
imi | +0.013 |
Betty | +0.013 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.008 |
eighty | -0.008 |
cash | -0.007 |
pen | -0.007 |
Token | much |
Token ID | 881 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
Evan | +0.007 |
cash | +0.007 |
eighty | +0.006 |
pen | +0.006 |
etr | +0.006 |
Neg logit contributions | |
anne | -0.004 |
arge | -0.004 |
Judy | -0.004 |
Maria | -0.004 |
Janet | -0.004 |
Token | fun |
Token ID | 1257 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Judy | +0.006 |
Janet | +0.006 |
arge | +0.006 |
imi | +0.006 |
Betty | +0.006 |
Neg logit contributions | |
Evan | -0.018 |
eighty | -0.017 |
cash | -0.016 |
cand | -0.016 |
yle | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
Judy | +0.006 |
arge | +0.006 |
Janet | +0.006 |
Bet | +0.006 |
imi | +0.006 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
pen | -0.005 |
eighty | -0.005 |
penn | -0.005 |
Token | K |
Token ID | 509 |
Feature activation | -7.70e-01 |
Pos logit contributions | |
Judy | +0.009 |
arge | +0.009 |
Janet | +0.009 |
imi | +0.009 |
Betty | +0.009 |
Neg logit contributions | |
Evan | -0.011 |
cand | -0.010 |
eighty | -0.010 |
cash | -0.010 |
pen | -0.010 |
Token | ait |
Token ID | 4548 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
Evan | +0.021 |
cand | +0.020 |
eighty | +0.019 |
cash | +0.018 |
penn | +0.018 |
Neg logit contributions | |
Janet | -0.018 |
Judy | -0.018 |
arge | -0.017 |
Betty | -0.017 |
Bet | -0.017 |
Token | lyn |
Token ID | 6213 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Evan | +0.084 |
cand | +0.080 |
eighty | +0.078 |
cash | +0.076 |
pen | +0.075 |
Neg logit contributions | |
Judy | -0.057 |
Janet | -0.057 |
arge | -0.057 |
imi | -0.056 |
Betty | -0.054 |
Token | was |
Token ID | 373 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
Judy | +0.003 |
Janet | +0.003 |
arge | +0.003 |
anne | +0.003 |
imi | +0.003 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.002 |
cash | -0.002 |
penn | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
cand | +0.006 |
Evan | +0.005 |
pen | +0.005 |
cash | +0.005 |
penn | +0.005 |
Neg logit contributions | |
Janet | -0.005 |
Judy | -0.005 |
arge | -0.005 |
Maria | -0.005 |
Betty | -0.005 |
Token | happy |
Token ID | 3772 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
cand | +0.006 |
Evan | +0.006 |
cash | +0.005 |
pen | +0.005 |
eighty | +0.005 |
Neg logit contributions | |
Judy | -0.004 |
Janet | -0.004 |
arge | -0.004 |
Maria | -0.004 |
Betty | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
eighty | +0.002 |
cash | +0.002 |
pen | +0.002 |
Neg logit contributions | |
arge | -0.004 |
Judy | -0.004 |
Janet | -0.004 |
imi | -0.004 |
Bet | -0.004 |
Token | It |
Token ID | 1026 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
Judy | +0.011 |
Bet | +0.011 |
arge | +0.011 |
Janet | +0.011 |
oky | +0.010 |
Neg logit contributions | |
Evan | -0.015 |
cand | -0.015 |
cash | -0.014 |
eighty | -0.014 |
penn | -0.014 |
Token | is |
Token ID | 318 |
Feature activation | -7.18e-03 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
eighty | +0.000 |
cash | +0.000 |
pen | +0.000 |
Neg logit contributions | |
Judy | -0.000 |
Janet | -0.000 |
arge | -0.000 |
imi | -0.000 |
Betty | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
eighty | +0.000 |
re | +0.000 |
himself | +0.000 |
Neg logit contributions | |
anne | -0.000 |
arge | -0.000 |
imi | -0.000 |
Bet | -0.000 |
iet | -0.000 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
Evan | +0.018 |
pen | +0.017 |
cand | +0.017 |
eighty | +0.015 |
yle | +0.015 |
Neg logit contributions | |
arge | -0.019 |
imi | -0.019 |
Judy | -0.019 |
Janet | -0.019 |
Betty | -0.019 |
Token | in |
Token ID | 259 |
Feature activation | +6.14e-02 |
Pos logit contributions | |
Evan | +0.043 |
goodbye | +0.041 |
cash | +0.040 |
cand | +0.038 |
eighty | +0.038 |
Neg logit contributions | |
imi | -0.028 |
oky | -0.027 |
iet | -0.025 |
web | -0.025 |
iders | -0.025 |
Token | oc |
Token ID | 420 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
Betty | +0.002 |
imi | +0.002 |
arge | +0.002 |
oky | +0.002 |
Judy | +0.002 |
Neg logit contributions | |
Evan | -0.001 |
cash | -0.001 |
cand | -0.001 |
pen | -0.001 |
eighty | -0.001 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Evan | +0.096 |
My | +0.087 |
marry | +0.084 |
rejuven | +0.084 |
traded | +0.083 |
Neg logit contributions | |
oky | -0.041 |
imi | -0.040 |
arge | -0.037 |
ower | -0.036 |
eds | -0.035 |
Token | !" |
Token ID | 2474 |
Feature activation | -6.98e-01 |
Pos logit contributions | |
Judy | +0.006 |
arge | +0.005 |
imi | +0.005 |
Janet | +0.005 |
Betty | +0.005 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.006 |
cash | -0.006 |
eighty | -0.006 |
pen | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Evan | +0.011 |
himself | +0.009 |
cand | +0.009 |
eighty | +0.008 |
Qu | +0.008 |
Neg logit contributions | |
imi | -0.025 |
arge | -0.025 |
zie | -0.025 |
anne | -0.024 |
Janet | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.006 |
Neg logit contributions | |
arge | -0.012 |
Janet | -0.012 |
Judy | -0.012 |
anne | -0.011 |
imi | -0.011 |
Token | The |
Token ID | 464 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
Evan | +0.006 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.005 |
Neg logit contributions | |
Janet | -0.005 |
Judy | -0.005 |
arge | -0.005 |
imi | -0.005 |
Betty | -0.005 |
Token | It |
Token ID | 632 |
Feature activation | -5.40e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.007 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.006 |
Neg logit contributions | |
arge | -0.011 |
Janet | -0.011 |
imi | -0.011 |
Judy | -0.011 |
anne | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.009 |
eighty | +0.009 |
cash | +0.008 |
pen | +0.008 |
Neg logit contributions | |
Judy | -0.017 |
Janet | -0.017 |
arge | -0.017 |
imi | -0.017 |
Betty | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
anne | +0.004 |
arge | +0.004 |
imi | +0.004 |
Bet | +0.004 |
Janet | +0.004 |
Neg logit contributions | |
Evan | -0.002 |
eighty | -0.002 |
re | -0.002 |
cand | -0.002 |
himself | -0.002 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
Evan | +0.026 |
cand | +0.025 |
eighty | +0.024 |
cash | +0.023 |
pen | +0.023 |
Neg logit contributions | |
Judy | -0.027 |
arge | -0.027 |
Janet | -0.027 |
imi | -0.027 |
Betty | -0.026 |
Token | in |
Token ID | 259 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Evan | +0.039 |
cash | +0.036 |
goodbye | +0.036 |
eighty | +0.035 |
cand | +0.035 |
Neg logit contributions | |
imi | -0.029 |
oky | -0.028 |
iet | -0.027 |
arge | -0.026 |
lights | -0.026 |
Token | oc |
Token ID | 420 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
Evan | +0.002 |
eighty | +0.002 |
cash | +0.002 |
cand | +0.002 |
pen | +0.002 |
Neg logit contributions | |
arge | -0.003 |
imi | -0.003 |
Judy | -0.003 |
anne | -0.003 |
oky | -0.003 |
Token | eros |
Token ID | 27498 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Evan | +0.093 |
My | +0.085 |
marry | +0.083 |
rejuven | +0.079 |
eighty | +0.079 |
Neg logit contributions | |
oky | -0.046 |
arge | -0.042 |
imi | -0.041 |
lights | -0.040 |
zie | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e-01 |
Pos logit contributions | |
Judy | +0.006 |
anne | +0.005 |
imi | +0.005 |
Betty | +0.005 |
arge | +0.005 |
Neg logit contributions | |
Evan | -0.006 |
cash | -0.006 |
eighty | -0.006 |
cand | -0.006 |
penn | -0.005 |
Token | It |
Token ID | 632 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
eighty | +0.004 |
cash | +0.003 |
Qu | +0.003 |
Neg logit contributions | |
arge | -0.007 |
imi | -0.007 |
Janet | -0.007 |
anne | -0.007 |
Judy | -0.007 |
Token | lifted |
Token ID | 13663 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.009 |
eighty | +0.009 |
cash | +0.009 |
pen | +0.009 |
Neg logit contributions | |
Judy | -0.012 |
arge | -0.012 |
Janet | -0.012 |
imi | -0.012 |
Betty | -0.012 |
Token | its |
Token ID | 663 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
Judy | +0.007 |
Janet | +0.007 |
arge | +0.007 |
imi | +0.007 |
Betty | +0.007 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.005 |
eighty | -0.005 |
cash | -0.005 |
pen | -0.005 |
Token | have |
Token ID | 423 |
Feature activation | -3.38e-02 |
Pos logit contributions | |
Judy | +0.003 |
Janet | +0.003 |
arge | +0.003 |
imi | +0.003 |
Betty | +0.002 |
Neg logit contributions | |
Evan | -0.001 |
cand | -0.001 |
eighty | -0.001 |
cash | -0.001 |
pen | -0.001 |
Token | stopped |
Token ID | 5025 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
Judy | -0.001 |
arge | -0.001 |
Janet | -0.001 |
imi | -0.001 |
Betty | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
anne | +0.051 |
arge | +0.051 |
Janet | +0.051 |
Judy | +0.051 |
Bet | +0.050 |
Neg logit contributions | |
Evan | -0.035 |
cand | -0.032 |
eighty | -0.031 |
re | -0.030 |
marry | -0.030 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
arge | +0.008 |
Judy | +0.008 |
Janet | +0.008 |
imi | +0.008 |
Betty | +0.008 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.005 |
eighty | -0.005 |
pen | -0.005 |
cash | -0.005 |
Token | in |
Token ID | 259 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
Evan | +0.036 |
goodbye | +0.032 |
eighty | +0.032 |
cand | +0.031 |
himself | +0.030 |
Neg logit contributions | |
oky | -0.028 |
imi | -0.028 |
arge | -0.026 |
iet | -0.026 |
iders | -0.025 |
Token | oc |
Token ID | 420 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
arge | +0.013 |
Judy | +0.013 |
imi | +0.013 |
Janet | +0.012 |
Betty | +0.012 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.006 |
eighty | -0.006 |
penn | -0.005 |
pen | -0.005 |
Token | eros |
Token ID | 27498 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
Evan | +0.089 |
My | +0.080 |
rejuven | +0.077 |
eighty | +0.076 |
marry | +0.075 |
Neg logit contributions | |
oky | -0.047 |
arge | -0.044 |
imi | -0.043 |
arl | -0.039 |
eds | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -6.49e-01 |
Pos logit contributions | |
Judy | +0.017 |
arge | +0.017 |
Janet | +0.017 |
imi | +0.016 |
Betty | +0.016 |
Neg logit contributions | |
Evan | -0.015 |
cand | -0.014 |
eighty | -0.014 |
cash | -0.013 |
pen | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
Evan | +0.017 |
cand | +0.016 |
eighty | +0.016 |
pen | +0.015 |
cash | +0.015 |
Neg logit contributions | |
Judy | -0.016 |
Janet | -0.015 |
arge | -0.015 |
Betty | -0.015 |
imi | -0.015 |
Token | is |
Token ID | 318 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
Evan | +0.006 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.006 |
Neg logit contributions | |
Judy | -0.005 |
Janet | -0.005 |
arge | -0.005 |
imi | -0.005 |
Betty | -0.005 |
Token | sleeping |
Token ID | 11029 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
arge | +0.006 |
Judy | +0.006 |
imi | +0.005 |
Janet | +0.005 |
Bet | +0.005 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.004 |
marry | -0.004 |
Token | In |
Token ID | 818 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
Judy | +0.010 |
arge | +0.010 |
Janet | +0.010 |
imi | +0.010 |
anne | +0.009 |
Neg logit contributions | |
Evan | -0.013 |
cand | -0.012 |
eighty | -0.012 |
cash | -0.011 |
pen | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
Judy | +0.026 |
Janet | +0.026 |
arge | +0.026 |
imi | +0.026 |
Betty | +0.025 |
Neg logit contributions | |
Evan | -0.015 |
cand | -0.014 |
eighty | -0.013 |
cash | -0.013 |
pen | -0.012 |
Token | end |
Token ID | 886 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
Evan | +0.009 |
eighty | +0.008 |
cand | +0.008 |
yle | +0.008 |
pen | +0.008 |
Neg logit contributions | |
Janet | -0.014 |
arge | -0.013 |
Judy | -0.013 |
iet | -0.013 |
imi | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
arge | +0.022 |
Judy | +0.022 |
Janet | +0.021 |
imi | +0.021 |
anne | +0.021 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.009 |
eighty | -0.008 |
cash | -0.008 |
penn | -0.007 |
Token | K |
Token ID | 509 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
arge | +0.013 |
anne | +0.013 |
oky | +0.013 |
iet | +0.013 |
imi | +0.013 |
Neg logit contributions | |
Evan | -0.014 |
cand | -0.013 |
cash | -0.012 |
penn | -0.012 |
hairc | -0.011 |
Token | ait |
Token ID | 4548 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
Evan | +0.007 |
eighty | +0.006 |
cand | +0.006 |
cash | +0.006 |
penn | +0.006 |
Neg logit contributions | |
Janet | -0.007 |
Judy | -0.007 |
Bet | -0.006 |
Betty | -0.006 |
arge | -0.006 |
Token | lyn |
Token ID | 6213 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
Evan | +0.078 |
cand | +0.073 |
eighty | +0.072 |
cash | +0.070 |
pen | +0.068 |
Neg logit contributions | |
Janet | -0.056 |
Judy | -0.056 |
arge | -0.055 |
imi | -0.054 |
Betty | -0.053 |
Token | picked |
Token ID | 6497 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
Judy | +0.007 |
arge | +0.007 |
Janet | +0.007 |
anne | +0.007 |
imi | +0.006 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
eighty | -0.005 |
cash | -0.004 |
penn | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
arge | +0.004 |
Judy | +0.004 |
imi | +0.004 |
Janet | +0.004 |
Bet | +0.004 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.003 |
eighty | -0.003 |
cash | -0.003 |
pen | -0.002 |
Token | spark |
Token ID | 9009 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
imi | +0.004 |
Bet | +0.003 |
arge | +0.003 |
Judy | +0.003 |
Betty | +0.003 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.003 |
eighty | -0.003 |
cash | -0.002 |
pen | -0.002 |
Token | ly |
Token ID | 306 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Janet | +0.009 |
Judy | +0.009 |
arge | +0.009 |
anne | +0.009 |
imi | +0.009 |
Neg logit contributions | |
Evan | -0.007 |
eighty | -0.007 |
cand | -0.006 |
cash | -0.006 |
pen | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
Evan | +0.011 |
himself | +0.009 |
cand | +0.009 |
eighty | +0.008 |
Qu | +0.008 |
Neg logit contributions | |
imi | -0.025 |
arge | -0.025 |
zie | -0.025 |
anne | -0.024 |
Janet | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.006 |
Neg logit contributions | |
arge | -0.012 |
Janet | -0.012 |
Judy | -0.012 |
anne | -0.011 |
imi | -0.011 |
Token | The |
Token ID | 464 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
Evan | +0.006 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.005 |
Neg logit contributions | |
Janet | -0.005 |
Judy | -0.005 |
arge | -0.005 |
imi | -0.005 |
Betty | -0.005 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
imi | +0.011 |
window | +0.010 |
mist | +0.010 |
vine | +0.010 |
arl | +0.010 |
Neg logit contributions | |
pen | -0.006 |
Evan | -0.006 |
yle | -0.005 |
etr | -0.005 |
hop | -0.005 |
Token | in |
Token ID | 259 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
Evan | +0.040 |
goodbye | +0.037 |
cand | +0.035 |
cash | +0.035 |
eighty | +0.035 |
Neg logit contributions | |
imi | -0.027 |
iet | -0.025 |
oky | -0.025 |
web | -0.024 |
iders | -0.023 |
Token | oc |
Token ID | 420 |
Feature activation | -2.66e+00 |
Pos logit contributions | |
anne | +0.003 |
imi | +0.003 |
arge | +0.003 |
Judy | +0.003 |
iet | +0.003 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
yle | -0.002 |
pen | -0.002 |
penn | -0.002 |
Token | eros |
Token ID | 27498 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Evan | +0.092 |
My | +0.086 |
contain | +0.084 |
pen | +0.084 |
rejuven | +0.084 |
Neg logit contributions | |
imi | -0.035 |
oky | -0.033 |
arge | -0.031 |
eds | -0.031 |
arl | -0.029 |
Token | walked |
Token ID | 6807 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
anne | +0.004 |
Judy | +0.004 |
iet | +0.004 |
arge | +0.004 |
Betty | +0.004 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
penn | -0.005 |
yle | -0.005 |
pen | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | -5.15e-01 |
Pos logit contributions | |
Evan | +0.018 |
cand | +0.017 |
eighty | +0.016 |
pen | +0.016 |
cash | +0.016 |
Neg logit contributions | |
Judy | -0.013 |
Janet | -0.013 |
arge | -0.012 |
Betty | -0.012 |
Bet | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
cand | +0.011 |
Evan | +0.011 |
eighty | +0.010 |
penn | +0.010 |
pen | +0.010 |
Neg logit contributions | |
Judy | -0.014 |
Janet | -0.014 |
arge | -0.014 |
Betty | -0.014 |
imi | -0.014 |
Token | fence |
Token ID | 13990 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
arge | +0.005 |
window | +0.005 |
vine | +0.005 |
imi | +0.005 |
oky | +0.005 |
Neg logit contributions | |
Evan | -0.006 |
pen | -0.006 |
cand | -0.006 |
yle | -0.006 |
eighty | -0.006 |
Token | had |
Token ID | 550 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
anne | +0.002 |
Janet | +0.002 |
Judy | +0.002 |
Betty | +0.002 |
Bet | +0.002 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.003 |
cash | -0.003 |
eighty | -0.003 |
pen | -0.003 |
Token | never |
Token ID | 1239 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
Judy | +0.013 |
Janet | +0.013 |
Betty | +0.013 |
arge | +0.012 |
Bet | +0.012 |
Neg logit contributions | |
Evan | -0.012 |
pen | -0.011 |
cand | -0.011 |
eighty | -0.011 |
cash | -0.011 |
Token | seen |
Token ID | 1775 |
Feature activation | -4.33e-01 |
Pos logit contributions | |
Janet | +0.004 |
Judy | +0.004 |
Betty | +0.004 |
Maria | +0.004 |
Bet | +0.004 |
Neg logit contributions | |
Evan | -0.005 |
cash | -0.004 |
eighty | -0.004 |
yle | -0.004 |
penn | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Evan | +0.008 |
cand | +0.008 |
eighty | +0.007 |
cash | +0.007 |
pen | +0.007 |
Neg logit contributions | |
Judy | -0.013 |
Janet | -0.013 |
Betty | -0.013 |
arge | -0.013 |
imi | -0.013 |
Token | av |
Token ID | 1196 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.007 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.006 |
Neg logit contributions | |
Judy | -0.009 |
arge | -0.009 |
Janet | -0.009 |
imi | -0.009 |
Betty | -0.009 |
Token | oc |
Token ID | 420 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
Evan | +0.020 |
cand | +0.016 |
eighty | +0.015 |
cash | +0.015 |
yle | +0.015 |
Neg logit contributions | |
Bet | -0.036 |
Janet | -0.036 |
Judy | -0.036 |
Betty | -0.035 |
arge | -0.035 |
Token | ados |
Token ID | 22484 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
Evan | +0.082 |
Qu | +0.070 |
eighty | +0.070 |
yle | +0.068 |
marry | +0.068 |
Neg logit contributions | |
Betty | -0.051 |
Judy | -0.051 |
arge | -0.050 |
Janet | -0.050 |
oky | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
Judy | +0.014 |
arge | +0.013 |
Betty | +0.013 |
Janet | +0.013 |
Maria | +0.013 |
Neg logit contributions | |
Evan | -0.017 |
cand | -0.015 |
cash | -0.015 |
eighty | -0.015 |
penn | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
Evan | +0.005 |
cand | +0.004 |
cash | +0.004 |
Qu | +0.004 |
eighty | +0.004 |
Neg logit contributions | |
imi | -0.006 |
arge | -0.006 |
iet | -0.005 |
Judy | -0.005 |
Janet | -0.005 |
Token | wished |
Token ID | 16555 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Janet | +0.002 |
Judy | +0.002 |
Bet | +0.002 |
Betty | +0.002 |
arge | +0.002 |
Neg logit contributions | |
Evan | -0.002 |
eighty | -0.002 |
cand | -0.002 |
pen | -0.002 |
cash | -0.002 |
Token | they |
Token ID | 484 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
Judy | +0.024 |
Janet | +0.024 |
Betty | +0.023 |
arge | +0.023 |
imi | +0.022 |
Neg logit contributions | |
Evan | -0.036 |
cand | -0.035 |
pen | -0.034 |
eighty | -0.034 |
cash | -0.033 |
Token | careful |
Token ID | 8161 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
imi | +0.015 |
arge | +0.015 |
Janet | +0.015 |
anne | +0.015 |
Judy | +0.015 |
Neg logit contributions | |
Evan | -0.009 |
eighty | -0.009 |
cand | -0.008 |
himself | -0.008 |
pen | -0.008 |
Token | ." |
Token ID | 526 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
Evan | +0.014 |
cand | +0.013 |
eighty | +0.012 |
himself | +0.011 |
pen | +0.011 |
Neg logit contributions | |
arge | -0.021 |
Janet | -0.021 |
Judy | -0.020 |
Bet | -0.020 |
imi | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -6.68e-02 |
Pos logit contributions | |
Evan | +0.016 |
cand | +0.015 |
eighty | +0.015 |
marry | +0.014 |
re | +0.014 |
Neg logit contributions | |
Judy | -0.016 |
Janet | -0.015 |
Betty | -0.015 |
arge | -0.015 |
Bet | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.002 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
Judy | -0.002 |
arge | -0.002 |
Janet | -0.002 |
imi | -0.002 |
Bet | -0.002 |
Token | S |
Token ID | 50 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
hairc | +0.002 |
eighty | +0.002 |
re | +0.002 |
Neg logit contributions | |
Judy | -0.001 |
iet | -0.001 |
Bet | -0.001 |
arge | -0.001 |
Janet | -0.001 |
Token | oph |
Token ID | 2522 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
Evan | +0.026 |
cand | +0.024 |
eighty | +0.024 |
cash | +0.023 |
pen | +0.022 |
Neg logit contributions | |
Judy | -0.027 |
arge | -0.027 |
Janet | -0.027 |
imi | -0.027 |
Betty | -0.026 |
Token | ie |
Token ID | 494 |
Feature activation | +5.05e-02 |
Pos logit contributions | |
Evan | +0.082 |
cand | +0.078 |
eighty | +0.076 |
cash | +0.075 |
pen | +0.073 |
Neg logit contributions | |
Judy | -0.050 |
arge | -0.050 |
Janet | -0.050 |
imi | -0.049 |
Betty | -0.047 |
Token | thanked |
Token ID | 26280 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
Judy | +0.001 |
Janet | +0.001 |
Betty | +0.001 |
anne | +0.001 |
arge | +0.001 |
Neg logit contributions | |
Evan | -0.001 |
cand | -0.001 |
eighty | -0.001 |
cash | -0.001 |
pen | -0.001 |
Token | him |
Token ID | 683 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Judy | +0.005 |
Janet | +0.005 |
Betty | +0.004 |
Maria | +0.004 |
arge | +0.004 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.004 |
eighty | -0.003 |
pen | -0.003 |
penn | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -3.48e-01 |
Pos logit contributions | |
Evan | +0.028 |
cand | +0.027 |
eighty | +0.025 |
penn | +0.024 |
cash | +0.024 |
Neg logit contributions | |
Judy | -0.026 |
Janet | -0.026 |
Betty | -0.025 |
arge | -0.025 |
Lynn | -0.025 |
Token | gave |
Token ID | 2921 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.008 |
eighty | +0.008 |
pen | +0.008 |
hairc | +0.008 |
Neg logit contributions | |
Judy | -0.009 |
Janet | -0.009 |
Betty | -0.009 |
Maria | -0.008 |
Lynn | -0.008 |
Token | pushed |
Token ID | 7121 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.008 |
eighty | +0.008 |
cash | +0.008 |
hairc | +0.008 |
Neg logit contributions | |
Judy | -0.011 |
Betty | -0.011 |
Janet | -0.011 |
arge | -0.011 |
Bet | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
Judy | +0.010 |
Janet | +0.010 |
Betty | +0.010 |
Bet | +0.009 |
arge | +0.009 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.007 |
eighty | -0.006 |
cash | -0.006 |
pen | -0.006 |
Token | pulled |
Token ID | 5954 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.007 |
eighty | +0.007 |
cash | +0.006 |
pen | +0.006 |
Neg logit contributions | |
Judy | -0.008 |
Betty | -0.008 |
Janet | -0.008 |
Bet | -0.008 |
Maria | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | -2.45e-01 |
Pos logit contributions | |
Judy | +0.009 |
Janet | +0.009 |
Betty | +0.009 |
arge | +0.009 |
Bet | +0.009 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.008 |
eighty | -0.007 |
cash | -0.007 |
yle | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
Evan | +0.006 |
cand | +0.005 |
eighty | +0.005 |
cash | +0.005 |
yle | +0.005 |
Neg logit contributions | |
Judy | -0.007 |
Betty | -0.007 |
Janet | -0.007 |
Maria | -0.006 |
arge | -0.006 |
Token | seaw |
Token ID | 32085 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Judy | +0.001 |
arge | +0.001 |
Janet | +0.001 |
imi | +0.001 |
Betty | +0.001 |
Neg logit contributions | |
Evan | -0.001 |
cand | -0.001 |
eighty | -0.001 |
cash | -0.001 |
pen | -0.001 |
Token | eed |
Token ID | 2308 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
Evan | +0.059 |
cand | +0.054 |
eighty | +0.052 |
cash | +0.051 |
hairc | +0.048 |
Neg logit contributions | |
arge | -0.072 |
imi | -0.071 |
iet | -0.071 |
Judy | -0.071 |
anne | -0.069 |
Token | until |
Token ID | 1566 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
Evan | +0.023 |
cand | +0.021 |
eighty | +0.021 |
cash | +0.020 |
pen | +0.019 |
Neg logit contributions | |
Judy | -0.025 |
Janet | -0.024 |
arge | -0.024 |
Betty | -0.024 |
imi | -0.023 |
Token | finally |
Token ID | 3443 |
Feature activation | +2.98e-01 |
Pos logit contributions | |
Judy | +0.009 |
Betty | +0.009 |
Janet | +0.009 |
Maria | +0.008 |
arge | +0.008 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.007 |
eighty | -0.007 |
cash | -0.007 |
pen | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
Judy | +0.008 |
Betty | +0.008 |
Janet | +0.008 |
Maria | +0.007 |
Donna | +0.007 |
Neg logit contributions | |
cash | -0.007 |
cand | -0.007 |
Evan | -0.007 |
eighty | -0.007 |
hairc | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
Judy | +0.004 |
Janet | +0.004 |
Betty | +0.004 |
arge | +0.004 |
Bet | +0.004 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.003 |
eighty | -0.003 |
cash | -0.003 |
pen | -0.003 |
Token | hair |
Token ID | 4190 |
Feature activation | -9.36e-02 |
Pos logit contributions | |
arge | +0.003 |
imi | +0.003 |
Judy | +0.003 |
Janet | +0.003 |
anne | +0.003 |
Neg logit contributions | |
Evan | -0.002 |
eighty | -0.002 |
cand | -0.002 |
pen | -0.002 |
cash | -0.002 |
Token | ! |
Token ID | 0 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.002 |
cash | +0.002 |
pen | +0.002 |
Neg logit contributions | |
Judy | -0.003 |
arge | -0.003 |
Janet | -0.003 |
imi | -0.003 |
Betty | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
eighty | +0.004 |
cash | +0.003 |
pen | +0.003 |
Neg logit contributions | |
Judy | -0.004 |
Janet | -0.004 |
arge | -0.004 |
imi | -0.004 |
Betty | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.010 |
eighty | +0.010 |
cash | +0.010 |
pen | +0.009 |
Neg logit contributions | |
Judy | -0.008 |
arge | -0.008 |
imi | -0.008 |
iet | -0.008 |
Janet | -0.008 |
Token | S |
Token ID | 50 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.009 |
eighty | +0.009 |
hairc | +0.009 |
ninety | +0.008 |
Neg logit contributions | |
iet | -0.008 |
Bet | -0.008 |
arge | -0.007 |
Judy | -0.007 |
Janet | -0.007 |
Token | oph |
Token ID | 2522 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Evan | +0.028 |
cand | +0.026 |
eighty | +0.026 |
cash | +0.025 |
pen | +0.024 |
Neg logit contributions | |
Judy | -0.024 |
arge | -0.024 |
Janet | -0.024 |
imi | -0.024 |
iet | -0.023 |
Token | ie |
Token ID | 494 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Evan | +0.083 |
cand | +0.079 |
eighty | +0.077 |
cash | +0.076 |
pen | +0.075 |
Neg logit contributions | |
Judy | -0.049 |
arge | -0.049 |
imi | -0.048 |
Janet | -0.048 |
anne | -0.046 |
Token | smiled |
Token ID | 13541 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
Evan | +0.011 |
cand | +0.010 |
eighty | +0.009 |
cash | +0.009 |
pen | +0.009 |
Neg logit contributions | |
Judy | -0.015 |
arge | -0.014 |
Janet | -0.014 |
imi | -0.014 |
anne | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
Judy | +0.005 |
Janet | +0.005 |
arge | +0.005 |
Maria | +0.005 |
Betty | +0.005 |
Neg logit contributions | |
cand | -0.006 |
Evan | -0.006 |
cash | -0.005 |
eighty | -0.005 |
pen | -0.005 |
Token | She |
Token ID | 1375 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Evan | +0.016 |
cand | +0.015 |
eighty | +0.015 |
cash | +0.014 |
pen | +0.014 |
Neg logit contributions | |
arge | -0.013 |
Judy | -0.013 |
Janet | -0.013 |
imi | -0.013 |
Betty | -0.013 |
Token | knew |
Token ID | 2993 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
Judy | +0.006 |
Janet | +0.006 |
arge | +0.006 |
imi | +0.006 |
Betty | +0.006 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.004 |
pen | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
arge | +0.008 |
Judy | +0.008 |
imi | +0.008 |
Janet | +0.008 |
Bet | +0.008 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.006 |
eighty | -0.006 |
pen | -0.005 |
cash | -0.005 |
Token | |
Token ID | 220 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
arge | +0.008 |
Judy | +0.008 |
Janet | +0.008 |
imi | +0.008 |
iet | +0.008 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.006 |
eighty | -0.006 |
cash | -0.006 |
pen | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
arge | +0.018 |
Janet | +0.017 |
Judy | +0.017 |
imi | +0.017 |
iet | +0.017 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.010 |
eighty | -0.010 |
pen | -0.009 |
cash | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
Judy | -0.001 |
arge | -0.001 |
Janet | -0.001 |
imi | -0.001 |
anne | -0.001 |
Token | K |
Token ID | 42 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
arge | +0.009 |
Judy | +0.009 |
Janet | +0.009 |
imi | +0.008 |
Bet | +0.008 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.011 |
eighty | -0.011 |
cash | -0.010 |
pen | -0.010 |
Token | ait |
Token ID | 4548 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.001 |
cash | +0.001 |
penn | +0.001 |
Neg logit contributions | |
Janet | -0.001 |
Judy | -0.001 |
Betty | -0.001 |
arge | -0.001 |
Bet | -0.001 |
Token | lyn |
Token ID | 6213 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
Evan | +0.080 |
cand | +0.077 |
eighty | +0.074 |
cash | +0.073 |
pen | +0.072 |
Neg logit contributions | |
Judy | -0.051 |
arge | -0.051 |
Janet | -0.051 |
imi | -0.050 |
Betty | -0.049 |
Token | had |
Token ID | 550 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Judy | +0.010 |
Janet | +0.009 |
arge | +0.009 |
anne | +0.009 |
Lynn | +0.009 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.007 |
eighty | -0.007 |
cash | -0.007 |
pen | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
Judy | +0.008 |
arge | +0.008 |
Janet | +0.008 |
imi | +0.008 |
Betty | +0.008 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
eighty | -0.005 |
cash | -0.005 |
pen | -0.004 |
Token | much |
Token ID | 881 |
Feature activation | +5.77e-01 |
Pos logit contributions | |
cash | +0.007 |
Evan | +0.007 |
cand | +0.007 |
eighty | +0.007 |
pen | +0.007 |
Neg logit contributions | |
Judy | -0.004 |
Janet | -0.004 |
arge | -0.004 |
Betty | -0.004 |
anne | -0.004 |
Token | fun |
Token ID | 1257 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
Judy | +0.010 |
arge | +0.010 |
Janet | +0.010 |
imi | +0.010 |
Betty | +0.010 |
Neg logit contributions | |
Evan | -0.019 |
cand | -0.018 |
eighty | -0.017 |
cash | -0.017 |
pen | -0.017 |
Token | agreed |
Token ID | 4987 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
Judy | +0.005 |
Janet | +0.005 |
Betty | +0.005 |
arge | +0.004 |
Lynn | +0.004 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
eighty | -0.004 |
pen | -0.004 |
cash | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
Evan | +0.008 |
eighty | +0.008 |
cand | +0.008 |
pen | +0.007 |
cash | +0.007 |
Neg logit contributions | |
Judy | -0.006 |
Maria | -0.006 |
Janet | -0.006 |
Betty | -0.006 |
anne | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
iet | +0.009 |
arge | +0.008 |
imi | +0.008 |
Janet | +0.008 |
anne | +0.008 |
Neg logit contributions | |
Evan | -0.006 |
Qu | -0.005 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
arge | +0.002 |
Janet | +0.002 |
Judy | +0.002 |
oky | +0.002 |
imi | +0.002 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.001 |
eighty | -0.001 |
pen | -0.001 |
himself | -0.001 |
Token | K |
Token ID | 42 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Judy | +0.010 |
arge | +0.010 |
Janet | +0.010 |
imi | +0.010 |
Betty | +0.010 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.010 |
eighty | -0.009 |
cash | -0.009 |
pen | -0.009 |
Token | ait |
Token ID | 4548 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
Evan | +0.005 |
eighty | +0.005 |
cand | +0.005 |
pen | +0.005 |
cash | +0.005 |
Neg logit contributions | |
Janet | -0.005 |
Judy | -0.005 |
Betty | -0.005 |
Bet | -0.004 |
arge | -0.004 |
Token | lyn |
Token ID | 6213 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Evan | +0.078 |
cand | +0.075 |
eighty | +0.073 |
cash | +0.071 |
pen | +0.069 |
Neg logit contributions | |
Judy | -0.053 |
arge | -0.052 |
Janet | -0.052 |
imi | -0.051 |
Betty | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Judy | +0.008 |
anne | +0.008 |
Janet | +0.008 |
arge | +0.008 |
Lynn | +0.008 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.006 |
eighty | -0.006 |
cash | -0.006 |
pen | -0.006 |
Token | Alex |
Token ID | 4422 |
Feature activation | -6.81e-03 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
eighty | +0.004 |
cash | +0.004 |
pen | +0.004 |
Neg logit contributions | |
Judy | -0.003 |
Janet | -0.003 |
arge | -0.003 |
imi | -0.003 |
Betty | -0.003 |
Token | showed |
Token ID | 3751 |
Feature activation | -4.99e-01 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
eighty | +0.000 |
cash | +0.000 |
pen | +0.000 |
Neg logit contributions | |
anne | -0.000 |
Judy | -0.000 |
Janet | -0.000 |
iet | -0.000 |
arge | -0.000 |
Token | that |
Token ID | 326 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
eighty | +0.013 |
Evan | +0.013 |
cand | +0.012 |
pen | +0.012 |
ninety | +0.012 |
Neg logit contributions | |
Judy | -0.012 |
Betty | -0.012 |
Janet | -0.012 |
imi | -0.012 |
arge | -0.012 |
Token | Ben |
Token ID | 3932 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.002 |
pen | +0.002 |
penn | +0.002 |
Neg logit contributions | |
Judy | -0.002 |
Janet | -0.002 |
arge | -0.002 |
Betty | -0.002 |
imi | -0.002 |
Token | say |
Token ID | 910 |
Feature activation | -8.01e-01 |
Pos logit contributions | |
Judy | +0.003 |
Janet | +0.002 |
Betty | +0.002 |
arge | +0.002 |
June | +0.002 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.003 |
eighty | -0.003 |
penn | -0.003 |
yle | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
Evan | +0.025 |
cand | +0.024 |
cash | +0.023 |
eighty | +0.023 |
pen | +0.022 |
Neg logit contributions | |
Judy | -0.015 |
Janet | -0.014 |
Maria | -0.014 |
anne | -0.014 |
Betty | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
imi | +0.003 |
iet | +0.003 |
arge | +0.003 |
zie | +0.003 |
Janet | +0.003 |
Neg logit contributions | |
Evan | -0.001 |
eighty | -0.001 |
cash | -0.001 |
Qu | -0.001 |
cand | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
Evan | +0.002 |
eighty | +0.002 |
himself | +0.002 |
cand | +0.002 |
cash | +0.002 |
Neg logit contributions | |
arge | -0.004 |
Janet | -0.004 |
Judy | -0.004 |
anne | -0.004 |
iet | -0.004 |
Token | Offic |
Token ID | 12710 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
Janet | +0.003 |
imi | +0.003 |
Judy | +0.003 |
arge | +0.003 |
anne | +0.003 |
Neg logit contributions | |
Evan | -0.004 |
eighty | -0.003 |
cash | -0.003 |
cand | -0.003 |
pen | -0.003 |
Token | er |
Token ID | 263 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Evan | +0.056 |
cand | +0.053 |
eighty | +0.051 |
cash | +0.049 |
pen | +0.048 |
Neg logit contributions | |
Judy | -0.075 |
arge | -0.074 |
Janet | -0.074 |
imi | -0.074 |
Betty | -0.072 |
Token | Mike |
Token ID | 4995 |
Feature activation | +8.23e-01 |
Pos logit contributions | |
Evan | +0.029 |
cand | +0.027 |
eighty | +0.027 |
cash | +0.027 |
pen | +0.025 |
Neg logit contributions | |
arge | -0.024 |
Judy | -0.024 |
Bet | -0.024 |
Janet | -0.024 |
imi | -0.024 |
Token | shows |
Token ID | 2523 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
imi | +0.019 |
Judy | +0.019 |
arge | +0.018 |
Lynn | +0.018 |
anne | +0.018 |
Neg logit contributions | |
Evan | -0.022 |
cand | -0.020 |
cash | -0.019 |
eighty | -0.019 |
yle | -0.019 |
Token | them |
Token ID | 606 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
Evan | +0.031 |
cand | +0.030 |
eighty | +0.030 |
pen | +0.028 |
cash | +0.027 |
Neg logit contributions | |
Judy | -0.034 |
Janet | -0.034 |
arge | -0.034 |
imi | -0.033 |
Betty | -0.033 |
Token | his |
Token ID | 465 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
Evan | +0.008 |
eighty | +0.008 |
cand | +0.008 |
pen | +0.007 |
cash | +0.007 |
Neg logit contributions | |
Judy | -0.009 |
Janet | -0.009 |
Betty | -0.008 |
arge | -0.008 |
Maria | -0.008 |
Token | The |
Token ID | 464 |
Feature activation | -5.15e-02 |
Pos logit contributions | |
Judy | +0.004 |
Janet | +0.004 |
arge | +0.004 |
imi | +0.004 |
Betty | +0.004 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.004 |
pen | -0.003 |
Token | little |
Token ID | 1310 |
Feature activation | -5.07e-03 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
Judy | -0.002 |
arge | -0.002 |
Janet | -0.002 |
imi | -0.002 |
Betty | -0.002 |
Token | girl |
Token ID | 2576 |
Feature activation | +9.08e-03 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
eighty | +0.000 |
cash | +0.000 |
pen | +0.000 |
Neg logit contributions | |
arge | -0.000 |
Judy | -0.000 |
Janet | -0.000 |
imi | -0.000 |
Bet | -0.000 |
Token | eagerly |
Token ID | 30130 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
Judy | +0.000 |
Janet | +0.000 |
arge | +0.000 |
Maria | +0.000 |
anne | +0.000 |
Neg logit contributions | |
Evan | -0.000 |
cand | -0.000 |
eighty | -0.000 |
cash | -0.000 |
pen | -0.000 |
Token | helped |
Token ID | 4193 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.009 |
eighty | +0.008 |
penn | +0.008 |
yle | +0.008 |
Neg logit contributions | |
Judy | -0.008 |
Janet | -0.008 |
Betty | -0.008 |
arge | -0.008 |
anne | -0.008 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
Evan | +0.010 |
eighty | +0.010 |
cand | +0.010 |
pen | +0.009 |
ninety | +0.009 |
Neg logit contributions | |
Judy | -0.010 |
Janet | -0.010 |
arge | -0.010 |
imi | -0.010 |
Betty | -0.010 |
Token | my |
Token ID | 1820 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
Evan | +0.067 |
cand | +0.066 |
cash | +0.063 |
eighty | +0.063 |
pen | +0.062 |
Neg logit contributions | |
Judy | -0.061 |
Bet | -0.060 |
arge | -0.060 |
Janet | -0.059 |
imi | -0.059 |
Token | open |
Token ID | 1280 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
Evan | +0.019 |
cand | +0.018 |
eighty | +0.017 |
cash | +0.017 |
pen | +0.016 |
Neg logit contributions | |
Judy | -0.026 |
arge | -0.026 |
Janet | -0.026 |
imi | -0.026 |
Betty | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | +8.68e-01 |
Pos logit contributions | |
arge | +0.004 |
Judy | +0.004 |
imi | +0.004 |
Janet | +0.004 |
Bet | +0.004 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.002 |
cash | -0.002 |
pen | -0.002 |
Token | box |
Token ID | 3091 |
Feature activation | +3.26e-03 |
Pos logit contributions | |
Judy | +0.018 |
arge | +0.018 |
Janet | +0.018 |
imi | +0.018 |
Bet | +0.017 |
Neg logit contributions | |
Evan | -0.026 |
cand | -0.025 |
eighty | -0.024 |
cash | -0.023 |
pen | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
imi | +0.000 |
Bet | +0.000 |
arge | +0.000 |
Janet | +0.000 |
Judy | +0.000 |
Neg logit contributions | |
Evan | -0.000 |
cand | -0.000 |
eighty | -0.000 |
pen | -0.000 |
cash | -0.000 |
Token | my |
Token ID | 1820 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
Evan | +0.015 |
cand | +0.014 |
eighty | +0.014 |
cash | +0.014 |
pen | +0.013 |
Neg logit contributions | |
Judy | -0.008 |
arge | -0.008 |
Janet | -0.008 |
imi | -0.008 |
Betty | -0.008 |
Token | see |
Token ID | 766 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
eighty | +0.004 |
cash | +0.003 |
penn | +0.003 |
Neg logit contributions | |
Judy | -0.006 |
Janet | -0.006 |
arge | -0.006 |
Betty | -0.006 |
Maria | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
Evan | +0.018 |
cand | +0.017 |
eighty | +0.016 |
cash | +0.016 |
pen | +0.015 |
Neg logit contributions | |
Judy | -0.028 |
arge | -0.028 |
Janet | -0.028 |
imi | -0.027 |
Betty | -0.027 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
eighty | +0.000 |
pen | +0.000 |
cash | +0.000 |
Neg logit contributions | |
arge | -0.000 |
Judy | -0.000 |
Janet | -0.000 |
imi | -0.000 |
Betty | -0.000 |
Token | in |
Token ID | 259 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
Evan | +0.035 |
goodbye | +0.032 |
eighty | +0.032 |
cand | +0.032 |
cash | +0.029 |
Neg logit contributions | |
imi | -0.028 |
arge | -0.028 |
oky | -0.027 |
iders | -0.026 |
iet | -0.026 |
Token | oc |
Token ID | 420 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
penn | +0.001 |
yle | +0.001 |
Neg logit contributions | |
arge | -0.002 |
Judy | -0.002 |
Betty | -0.002 |
Janet | -0.002 |
Bet | -0.002 |
Token | eros |
Token ID | 27498 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
Evan | +0.084 |
My | +0.073 |
rejuven | +0.073 |
marry | +0.072 |
eighty | +0.071 |
Neg logit contributions | |
arge | -0.045 |
oky | -0.043 |
imi | -0.041 |
uana | -0.038 |
Betty | -0.038 |
Token | up |
Token ID | 510 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Judy | +0.010 |
Janet | +0.010 |
Betty | +0.009 |
arge | +0.009 |
imi | +0.009 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.008 |
eighty | -0.008 |
cash | -0.008 |
penn | -0.008 |
Token | close |
Token ID | 1969 |
Feature activation | -3.99e-01 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
pen | +0.004 |
eighty | +0.004 |
penn | +0.004 |
Neg logit contributions | |
imi | -0.007 |
arge | -0.007 |
Janet | -0.007 |
Lynn | -0.007 |
Judy | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.008 |
eighty | +0.008 |
cash | +0.007 |
pen | +0.007 |
Neg logit contributions | |
arge | -0.011 |
imi | -0.011 |
Janet | -0.011 |
Judy | -0.011 |
Bet | -0.011 |
Token | Tim |
Token ID | 5045 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
cash | +0.004 |
eighty | +0.004 |
traded | +0.003 |
Neg logit contributions | |
iet | -0.007 |
imi | -0.007 |
arge | -0.007 |
anne | -0.007 |
Judy | -0.006 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.48e-03 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
cash | +0.003 |
penn | +0.003 |
eighty | +0.003 |
Neg logit contributions | |
Bet | -0.005 |
Judy | -0.005 |
Janet | -0.005 |
arge | -0.004 |
iet | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
arge | +0.000 |
iet | +0.000 |
imi | +0.000 |
Judy | +0.000 |
Bet | +0.000 |
Neg logit contributions | |
cand | -0.000 |
Evan | -0.000 |
eighty | -0.000 |
cash | -0.000 |
pen | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
Evan | +0.013 |
cand | +0.012 |
cash | +0.011 |
eighty | +0.011 |
pen | +0.011 |
Neg logit contributions | |
arge | -0.015 |
Judy | -0.015 |
Janet | -0.015 |
imi | -0.015 |
iet | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
Evan | +0.012 |
cand | +0.011 |
cash | +0.010 |
eighty | +0.010 |
pen | +0.009 |
Neg logit contributions | |
Janet | -0.019 |
Judy | -0.019 |
arge | -0.019 |
iet | -0.019 |
anne | -0.019 |
Token | S |
Token ID | 50 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Evan | +0.013 |
cand | +0.012 |
eighty | +0.012 |
pen | +0.011 |
penn | +0.011 |
Neg logit contributions | |
arge | -0.009 |
Judy | -0.009 |
imi | -0.009 |
Janet | -0.009 |
Bet | -0.009 |
Token | oph |
Token ID | 2522 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
Evan | +0.027 |
cand | +0.025 |
eighty | +0.025 |
cash | +0.024 |
pen | +0.023 |
Neg logit contributions | |
Judy | -0.025 |
arge | -0.024 |
Janet | -0.024 |
imi | -0.024 |
anne | -0.023 |
Token | ie |
Token ID | 494 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Evan | +0.075 |
cand | +0.073 |
eighty | +0.069 |
cash | +0.068 |
penn | +0.066 |
Neg logit contributions | |
Janet | -0.054 |
Judy | -0.054 |
arge | -0.054 |
Bet | -0.053 |
Betty | -0.052 |
Token | began |
Token ID | 2540 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
Judy | +0.006 |
arge | +0.006 |
Janet | +0.006 |
imi | +0.006 |
anne | +0.006 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.004 |
pen | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
Evan | +0.019 |
cand | +0.018 |
eighty | +0.018 |
cash | +0.017 |
pen | +0.016 |
Neg logit contributions | |
arge | -0.015 |
Judy | -0.015 |
Janet | -0.015 |
imi | -0.015 |
Lynn | -0.015 |
Token | feel |
Token ID | 1254 |
Feature activation | -8.30e-02 |
Pos logit contributions | |
Evan | +0.025 |
cand | +0.025 |
eighty | +0.023 |
penn | +0.022 |
pen | +0.022 |
Neg logit contributions | |
Judy | -0.033 |
arge | -0.032 |
Janet | -0.032 |
imi | -0.032 |
Betty | -0.032 |
Token | frustrated |
Token ID | 14718 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.002 |
ninety | +0.002 |
pen | +0.002 |
Neg logit contributions | |
Judy | -0.002 |
Betty | -0.002 |
Janet | -0.002 |
arge | -0.002 |
Lynn | -0.002 |
Token | than |
Token ID | 621 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
Evan | +0.005 |
cand | +0.005 |
himself | +0.004 |
penn | +0.004 |
eighty | +0.004 |
Neg logit contributions | |
Bet | -0.009 |
imi | -0.009 |
arge | -0.009 |
Janet | -0.009 |
Lynn | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -6.41e-01 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
eighty | +0.003 |
cash | +0.003 |
pen | +0.003 |
Neg logit contributions | |
arge | -0.006 |
Judy | -0.006 |
Janet | -0.006 |
imi | -0.006 |
Bet | -0.006 |
Token | park |
Token ID | 3952 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
Evan | +0.016 |
cand | +0.015 |
eighty | +0.014 |
cash | +0.014 |
penn | +0.013 |
Neg logit contributions | |
Judy | -0.017 |
Janet | -0.016 |
arge | -0.016 |
imi | -0.016 |
Betty | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
imi | +0.004 |
arge | +0.004 |
Judy | +0.004 |
Janet | +0.004 |
Bet | +0.004 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.003 |
cash | -0.003 |
eighty | -0.003 |
pen | -0.002 |
Token | K |
Token ID | 509 |
Feature activation | -3.55e-01 |
Pos logit contributions | |
arge | +0.007 |
imi | +0.007 |
Judy | +0.007 |
Janet | +0.007 |
iet | +0.007 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.008 |
cash | -0.007 |
eighty | -0.007 |
penn | -0.007 |
Token | ait |
Token ID | 4548 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.008 |
eighty | +0.008 |
cash | +0.008 |
penn | +0.008 |
Neg logit contributions | |
Janet | -0.009 |
Judy | -0.009 |
Betty | -0.008 |
Bet | -0.008 |
arge | -0.008 |
Token | lyn |
Token ID | 6213 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
Evan | +0.075 |
cand | +0.070 |
eighty | +0.069 |
cash | +0.067 |
pen | +0.065 |
Neg logit contributions | |
Janet | -0.055 |
Judy | -0.055 |
arge | -0.054 |
imi | -0.053 |
Betty | -0.053 |
Token | ran |
Token ID | 4966 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
Judy | +0.009 |
arge | +0.009 |
Janet | +0.009 |
anne | +0.009 |
imi | +0.008 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.007 |
eighty | -0.007 |
cash | -0.007 |
pen | -0.007 |
Token | over |
Token ID | 625 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.010 |
eighty | +0.009 |
cash | +0.009 |
pen | +0.009 |
Neg logit contributions | |
Judy | -0.011 |
Janet | -0.011 |
arge | -0.011 |
imi | -0.011 |
Betty | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
Evan | +0.025 |
cand | +0.023 |
eighty | +0.022 |
cash | +0.022 |
pen | +0.021 |
Neg logit contributions | |
arge | -0.032 |
imi | -0.032 |
Janet | -0.032 |
Judy | -0.032 |
anne | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.010 |
eighty | +0.009 |
cash | +0.009 |
pen | +0.008 |
Neg logit contributions | |
Judy | -0.016 |
Janet | -0.016 |
arge | -0.015 |
Betty | -0.015 |
imi | -0.015 |
Token | happy |
Token ID | 3772 |
Feature activation | -3.43e-01 |
Pos logit contributions | |
imi | +0.015 |
arge | +0.015 |
anne | +0.014 |
Janet | +0.014 |
Judy | +0.014 |
Neg logit contributions | |
Evan | -0.008 |
eighty | -0.008 |
cand | -0.008 |
cash | -0.007 |
penn | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
cand | +0.006 |
Evan | +0.005 |
eighty | +0.005 |
penn | +0.005 |
marry | +0.005 |
Neg logit contributions | |
Janet | -0.012 |
arge | -0.012 |
anne | -0.011 |
Judy | -0.011 |
Bet | -0.011 |
Token | see |
Token ID | 766 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
lights | +0.010 |
arge | +0.009 |
anne | +0.009 |
imi | +0.009 |
Janet | +0.009 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.004 |
marry | -0.004 |
eighty | -0.004 |
cash | -0.003 |
Token | our |
Token ID | 674 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Evan | +0.025 |
cand | +0.024 |
eighty | +0.022 |
cash | +0.021 |
penn | +0.021 |
Neg logit contributions | |
arge | -0.040 |
Janet | -0.040 |
Judy | -0.039 |
anne | -0.039 |
imi | -0.039 |
Token | big |
Token ID | 1263 |
Feature activation | -1.89e-02 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
cash | +0.003 |
eighty | +0.003 |
penn | +0.003 |
Neg logit contributions | |
Janet | -0.004 |
Judy | -0.004 |
arge | -0.004 |
imi | -0.004 |
anne | -0.004 |
Token | cuc |
Token ID | 38421 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
cand | +0.000 |
Evan | +0.000 |
cash | +0.000 |
penn | +0.000 |
eighty | +0.000 |
Neg logit contributions | |
arge | -0.001 |
Janet | -0.001 |
anne | -0.001 |
Bet | -0.000 |
Judy | -0.000 |
Token | umber |
Token ID | 4494 |
Feature activation | +3.90e-01 |
Pos logit contributions | |
Evan | +0.065 |
cand | +0.057 |
eighty | +0.055 |
goodbye | +0.055 |
hairc | +0.054 |
Neg logit contributions | |
arge | -0.065 |
imi | -0.064 |
Judy | -0.062 |
oky | -0.061 |
iet | -0.061 |
Token | ." |
Token ID | 526 |
Feature activation | -2.80e-01 |
Pos logit contributions | |
arge | +0.011 |
Judy | +0.011 |
Janet | +0.011 |
imi | +0.011 |
Bet | +0.011 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.008 |
eighty | -0.008 |
cash | -0.008 |
pen | -0.007 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
Evan | +0.005 |
cand | +0.005 |
cash | +0.005 |
Qu | +0.005 |
eighty | +0.004 |
Neg logit contributions | |
anne | -0.009 |
iders | -0.009 |
iet | -0.009 |
eways | -0.009 |
leys | -0.009 |
Token | says |
Token ID | 1139 |
Feature activation | -5.71e-01 |
Pos logit contributions | |
Judy | +0.010 |
arge | +0.010 |
Janet | +0.010 |
imi | +0.010 |
Betty | +0.010 |
Neg logit contributions | |
Evan | -0.018 |
cand | -0.017 |
eighty | -0.017 |
cash | -0.016 |
pen | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +8.78e-02 |
Pos logit contributions | |
Evan | +0.017 |
cand | +0.016 |
cash | +0.015 |
eighty | +0.015 |
pen | +0.015 |
Neg logit contributions | |
Judy | -0.012 |
anne | -0.011 |
Janet | -0.011 |
arge | -0.011 |
imi | -0.011 |
Token | â |
Token ID | 22940 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
eighty | +0.000 |
pen | +0.000 |
cash | +0.000 |
Neg logit contributions | |
arge | -0.001 |
imi | -0.001 |
Judy | -0.001 |
Janet | -0.001 |
Bet | -0.001 |
Token | € |
Token ID | 26391 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
Judy | +0.010 |
Janet | +0.010 |
arge | +0.010 |
anne | +0.010 |
imi | +0.009 |
Neg logit contributions | |
Evan | -0.014 |
cand | -0.014 |
eighty | -0.013 |
penn | -0.013 |
cash | -0.013 |
Token | � |
Token ID | 447 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
arge | +0.004 |
Judy | +0.004 |
imi | +0.004 |
Janet | +0.004 |
Betty | +0.004 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.003 |
eighty | -0.003 |
pen | -0.003 |
cash | -0.003 |
Token | � |
Token ID | 251 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
Evan | +0.027 |
cand | +0.025 |
pen | +0.024 |
cash | +0.024 |
eighty | +0.023 |
Neg logit contributions | |
arge | -0.023 |
Judy | -0.023 |
imi | -0.023 |
Janet | -0.023 |
Betty | -0.022 |
Token | S |
Token ID | 50 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
Evan | +0.013 |
cand | +0.013 |
eighty | +0.012 |
cash | +0.012 |
pen | +0.011 |
Neg logit contributions | |
arge | -0.016 |
Judy | -0.016 |
Janet | -0.016 |
imi | -0.016 |
anne | -0.016 |
Token | oph |
Token ID | 2522 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
Evan | +0.020 |
cand | +0.019 |
eighty | +0.018 |
cash | +0.018 |
pen | +0.017 |
Neg logit contributions | |
Janet | -0.023 |
Judy | -0.023 |
arge | -0.023 |
imi | -0.023 |
Betty | -0.022 |
Token | ie |
Token ID | 494 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
Evan | +0.074 |
cand | +0.071 |
eighty | +0.068 |
cash | +0.066 |
pen | +0.065 |
Neg logit contributions | |
Janet | -0.055 |
arge | -0.054 |
Judy | -0.054 |
Bet | -0.053 |
Betty | -0.052 |
Token | used |
Token ID | 973 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.002 |
cash | +0.002 |
pen | +0.002 |
Neg logit contributions | |
arge | -0.004 |
Judy | -0.004 |
Janet | -0.004 |
imi | -0.004 |
Bet | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Judy | +0.026 |
Janet | +0.026 |
arge | +0.026 |
imi | +0.025 |
Betty | +0.025 |
Neg logit contributions | |
Evan | -0.018 |
cand | -0.017 |
eighty | -0.016 |
cash | -0.016 |
pen | -0.015 |
Token | hands |
Token ID | 2832 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
arge | +0.016 |
Bet | +0.016 |
Janet | +0.016 |
Judy | +0.016 |
imi | +0.016 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.009 |
eighty | -0.009 |
penn | -0.008 |
cash | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
Evan | +0.006 |
cand | +0.006 |
eighty | +0.005 |
cash | +0.005 |
pen | +0.005 |
Neg logit contributions | |
arge | -0.007 |
Judy | -0.007 |
Janet | -0.007 |
imi | -0.007 |
Betty | -0.007 |
Token | But |
Token ID | 1537 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
Judy | +0.001 |
arge | +0.001 |
Janet | +0.001 |
imi | +0.001 |
Betty | +0.001 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.001 |
cash | -0.001 |
pen | -0.001 |
Token | then |
Token ID | 788 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
Evan | +0.005 |
cand | +0.005 |
eighty | +0.005 |
pen | +0.005 |
cash | +0.005 |
Neg logit contributions | |
Judy | -0.007 |
Janet | -0.007 |
arge | -0.007 |
imi | -0.007 |
Betty | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
Judy | +0.012 |
Betty | +0.012 |
Janet | +0.012 |
imi | +0.011 |
Maria | +0.011 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.007 |
eighty | -0.007 |
cash | -0.007 |
pen | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
Judy | +0.013 |
arge | +0.013 |
Janet | +0.013 |
imi | +0.013 |
Betty | +0.013 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.009 |
eighty | -0.008 |
cash | -0.008 |
pen | -0.008 |
Token | door |
Token ID | 3420 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Judy | +0.001 |
Janet | +0.001 |
Bet | +0.001 |
imi | +0.001 |
arge | +0.001 |
Neg logit contributions | |
cand | -0.001 |
cash | -0.001 |
Evan | -0.001 |
penn | -0.001 |
marry | -0.001 |
Token | fell |
Token ID | 3214 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
Judy | +0.019 |
arge | +0.019 |
imi | +0.018 |
Bet | +0.018 |
Janet | +0.018 |
Neg logit contributions | |
cand | -0.011 |
Evan | -0.011 |
cash | -0.010 |
traded | -0.009 |
pen | -0.009 |
Token | down |
Token ID | 866 |
Feature activation | +1.30e-01 |
Pos logit contributions | |
arge | +0.073 |
Judy | +0.073 |
anne | +0.070 |
imi | +0.069 |
Janet | +0.068 |
Neg logit contributions | |
Evan | -0.031 |
cand | -0.031 |
eighty | -0.028 |
himself | -0.027 |
goodbye | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
imi | +0.005 |
arge | +0.005 |
Judy | +0.005 |
anne | +0.005 |
iet | +0.005 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
himself | -0.002 |
cash | -0.002 |
marry | -0.001 |
Token | It |
Token ID | 632 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
eighty | +0.003 |
cash | +0.003 |
pen | +0.002 |
Neg logit contributions | |
Judy | -0.003 |
arge | -0.003 |
Janet | -0.003 |
imi | -0.003 |
Betty | -0.003 |
Token | made |
Token ID | 925 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.010 |
cash | +0.009 |
re | +0.009 |
marry | +0.009 |
Neg logit contributions | |
arge | -0.025 |
Judy | -0.025 |
Janet | -0.025 |
imi | -0.024 |
Bet | -0.024 |
Token | a |
Token ID | 257 |
Feature activation | -6.96e-02 |
Pos logit contributions | |
arge | +0.016 |
Janet | +0.016 |
Judy | +0.016 |
imi | +0.016 |
anne | +0.015 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.009 |
cash | -0.008 |
eighty | -0.008 |
penn | -0.008 |
Token | keep |
Token ID | 1394 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
eighty | +0.007 |
cand | +0.007 |
Evan | +0.007 |
penn | +0.007 |
ninety | +0.007 |
Neg logit contributions | |
Janet | -0.007 |
Betty | -0.007 |
Judy | -0.007 |
Maria | -0.007 |
Bet | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Janet | +0.007 |
Judy | +0.007 |
arge | +0.007 |
Betty | +0.007 |
imi | +0.007 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
eighty | -0.005 |
cash | -0.004 |
pen | -0.004 |
Token | bone |
Token ID | 9970 |
Feature activation | +2.26e-02 |
Pos logit contributions | |
Evan | +0.008 |
eighty | +0.007 |
yle | +0.007 |
cand | +0.007 |
marry | +0.007 |
Neg logit contributions | |
imi | -0.007 |
Betty | -0.006 |
Janet | -0.006 |
Bree | -0.006 |
Judy | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +4.44e-02 |
Pos logit contributions | |
Betty | +0.001 |
Janet | +0.001 |
Judy | +0.000 |
Maria | +0.000 |
imi | +0.000 |
Neg logit contributions | |
Evan | -0.001 |
eighty | -0.001 |
cand | -0.001 |
cash | -0.001 |
hairc | -0.001 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
arge | +0.001 |
Judy | +0.001 |
iet | +0.001 |
imi | +0.001 |
anne | +0.001 |
Neg logit contributions | |
Evan | -0.001 |
cash | -0.001 |
cand | -0.001 |
traded | -0.001 |
himself | -0.001 |
Token | wh |
Token ID | 348 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
Evan | +0.004 |
eighty | +0.004 |
cand | +0.003 |
penn | +0.003 |
yle | +0.003 |
Neg logit contributions | |
Judy | -0.004 |
Janet | -0.004 |
Betty | -0.004 |
Lynn | -0.004 |
imi | -0.004 |
Token | ined |
Token ID | 1389 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
Judy | +0.046 |
Betty | +0.045 |
arge | +0.044 |
Janet | +0.044 |
Bet | +0.043 |
Neg logit contributions | |
Evan | -0.058 |
cand | -0.055 |
eighty | -0.055 |
pen | -0.054 |
penn | -0.052 |
Token | and |
Token ID | 290 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
Judy | +0.037 |
Janet | +0.037 |
arge | +0.037 |
imi | +0.036 |
Betty | +0.036 |
Neg logit contributions | |
Evan | -0.028 |
cand | -0.026 |
eighty | -0.025 |
cash | -0.024 |
pen | -0.023 |
Token | bark |
Token ID | 21405 |
Feature activation | -3.46e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
eighty | +0.003 |
cash | +0.003 |
pen | +0.002 |
Neg logit contributions | |
arge | -0.004 |
Judy | -0.004 |
imi | -0.004 |
Janet | -0.004 |
anne | -0.004 |
Token | ed |
Token ID | 276 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
eighty | +0.009 |
Evan | +0.009 |
cash | +0.008 |
cand | +0.008 |
hairc | +0.008 |
Neg logit contributions | |
anne | -0.008 |
Betty | -0.008 |
Janet | -0.008 |
Judy | -0.008 |
Bet | -0.008 |
Token | until |
Token ID | 1566 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
Evan | +0.009 |
eighty | +0.009 |
cand | +0.009 |
yle | +0.008 |
cash | +0.008 |
Neg logit contributions | |
Judy | -0.009 |
Betty | -0.009 |
Janet | -0.009 |
Maria | -0.009 |
June | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
Evan | +0.025 |
cand | +0.024 |
eighty | +0.023 |
cash | +0.022 |
penn | +0.021 |
Neg logit contributions | |
Judy | -0.032 |
Janet | -0.032 |
arge | -0.032 |
Maria | -0.032 |
Betty | -0.031 |
Token | old |
Token ID | 1468 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Evan | +0.020 |
cand | +0.019 |
cash | +0.018 |
eighty | +0.018 |
pen | +0.018 |
Neg logit contributions | |
Janet | -0.014 |
Judy | -0.014 |
arge | -0.014 |
imi | -0.014 |
Betty | -0.014 |
Token | lady |
Token ID | 10846 |
Feature activation | -2.84e-01 |
Pos logit contributions | |
Evan | +0.029 |
cand | +0.028 |
eighty | +0.027 |
cash | +0.026 |
pen | +0.025 |
Neg logit contributions | |
Judy | -0.033 |
arge | -0.033 |
Janet | -0.033 |
imi | -0.033 |
Betty | -0.032 |
Token | like |
Token ID | 588 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
eighty | +0.004 |
cash | +0.003 |
pen | +0.003 |
Neg logit contributions | |
Judy | -0.010 |
arge | -0.010 |
Janet | -0.010 |
imi | -0.010 |
Betty | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
Judy | +0.004 |
Janet | +0.004 |
arge | +0.004 |
imi | +0.004 |
Betty | +0.004 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.002 |
cash | -0.002 |
pen | -0.002 |
Token | wh |
Token ID | 348 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
Evan | +0.016 |
cand | +0.014 |
eighty | +0.014 |
cash | +0.014 |
pen | +0.013 |
Neg logit contributions | |
Judy | -0.020 |
Janet | -0.020 |
arge | -0.020 |
imi | -0.020 |
Betty | -0.019 |
Token | irl |
Token ID | 1901 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
Betty | +0.048 |
Judy | +0.048 |
Janet | +0.047 |
June | +0.046 |
Bet | +0.045 |
Neg logit contributions | |
Evan | -0.060 |
pen | -0.058 |
eighty | -0.056 |
yle | -0.055 |
cand | -0.055 |
Token | ig |
Token ID | 328 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
Judy | +0.003 |
Janet | +0.003 |
arge | +0.003 |
anne | +0.003 |
imi | +0.003 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.003 |
eighty | -0.003 |
cash | -0.003 |
penn | -0.003 |
Token | ig |
Token ID | 328 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
Judy | +0.010 |
arge | +0.010 |
Janet | +0.010 |
imi | +0.010 |
Betty | +0.010 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.011 |
eighty | -0.011 |
pen | -0.011 |
marry | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
Judy | +0.010 |
arge | +0.010 |
Janet | +0.010 |
imi | +0.009 |
Betty | +0.009 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.012 |
eighty | -0.012 |
pen | -0.012 |
cash | -0.011 |
Token | His |
Token ID | 2399 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
Evan | +0.004 |
himself | +0.003 |
cash | +0.003 |
Qu | +0.003 |
pen | +0.003 |
Neg logit contributions | |
imi | -0.008 |
iet | -0.007 |
anne | -0.007 |
outage | -0.007 |
arge | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Janet | +0.013 |
Judy | +0.013 |
arge | +0.013 |
imi | +0.013 |
Bet | +0.012 |
Neg logit contributions | |
Evan | -0.013 |
cand | -0.012 |
eighty | -0.012 |
cash | -0.011 |
marry | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
imi | +0.003 |
Betty | +0.003 |
Janet | +0.003 |
Judy | +0.003 |
June | +0.003 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.002 |
cash | -0.002 |
yle | -0.002 |
Token | he |
Token ID | 339 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
arge | +0.011 |
Judy | +0.011 |
Janet | +0.011 |
imi | +0.011 |
anne | +0.011 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.009 |
eighty | -0.009 |
cash | -0.009 |
pen | -0.009 |
Token | dug |
Token ID | 18735 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
Evan | +0.005 |
cand | +0.005 |
eighty | +0.005 |
cash | +0.005 |
pen | +0.004 |
Neg logit contributions | |
Judy | -0.005 |
Janet | -0.005 |
arge | -0.005 |
imi | -0.005 |
Betty | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
Judy | +0.008 |
Betty | +0.008 |
iet | +0.008 |
Bet | +0.008 |
Janet | +0.008 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.007 |
eighty | -0.007 |
cash | -0.007 |
yle | -0.007 |
Token | very |
Token ID | 845 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
Janet | +0.005 |
arge | +0.005 |
Judy | +0.005 |
anne | +0.004 |
imi | +0.004 |
Neg logit contributions | |
cand | -0.006 |
Evan | -0.006 |
cash | -0.006 |
penn | -0.006 |
eighty | -0.006 |
Token | big |
Token ID | 1263 |
Feature activation | +9.39e-01 |
Pos logit contributions | |
Janet | +0.055 |
arge | +0.053 |
Bet | +0.053 |
Judy | +0.053 |
Lynn | +0.052 |
Neg logit contributions | |
Evan | -0.051 |
cand | -0.051 |
penn | -0.048 |
eighty | -0.047 |
cash | -0.046 |
Token | hole |
Token ID | 7604 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
arge | +0.016 |
Judy | +0.016 |
Janet | +0.016 |
imi | +0.016 |
anne | +0.015 |
Neg logit contributions | |
Evan | -0.031 |
cand | -0.031 |
eighty | -0.029 |
cash | -0.029 |
penn | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +3.99e-01 |
Pos logit contributions | |
Janet | +0.018 |
arge | +0.018 |
imi | +0.018 |
Judy | +0.018 |
Bet | +0.018 |
Neg logit contributions | |
Evan | -0.006 |
eighty | -0.005 |
cand | -0.005 |
himself | -0.005 |
pen | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -6.89e-03 |
Pos logit contributions | |
arge | +0.013 |
Judy | +0.012 |
Janet | +0.012 |
imi | +0.012 |
anne | +0.012 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.007 |
eighty | -0.007 |
cash | -0.006 |
pen | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
pen | +0.000 |
eighty | +0.000 |
himself | +0.000 |
Neg logit contributions | |
arge | -0.000 |
Janet | -0.000 |
Judy | -0.000 |
imi | -0.000 |
iet | -0.000 |
Token | hello |
Token ID | 23748 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
Judy | +0.018 |
Betty | +0.017 |
Janet | +0.017 |
June | +0.017 |
Bree | +0.017 |
Neg logit contributions | |
Evan | -0.014 |
pen | -0.014 |
cash | -0.014 |
cand | -0.013 |
yle | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.009 |
eighty | +0.009 |
cash | +0.009 |
pen | +0.009 |
Neg logit contributions | |
Judy | -0.008 |
Janet | -0.008 |
arge | -0.008 |
Betty | -0.008 |
imi | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
arge | +0.006 |
imi | +0.006 |
Janet | +0.006 |
Judy | +0.006 |
anne | +0.006 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.004 |
Qu | -0.003 |
Token | dog |
Token ID | 3290 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
Judy | +0.014 |
imi | +0.014 |
Janet | +0.014 |
arge | +0.014 |
Betty | +0.014 |
Neg logit contributions | |
Evan | -0.013 |
cand | -0.012 |
eighty | -0.012 |
pen | -0.012 |
cash | -0.012 |
Token | w |
Token ID | 266 |
Feature activation | +9.21e-01 |
Pos logit contributions | |
Evan | +0.000 |
yle | +0.000 |
pen | +0.000 |
cand | +0.000 |
eighty | +0.000 |
Neg logit contributions | |
imi | -0.000 |
Lynn | -0.000 |
iet | -0.000 |
Judy | -0.000 |
Betty | -0.000 |
Token | ags |
Token ID | 3775 |
Feature activation | +2.00e+00 |
Pos logit contributions | |
imi | +0.012 |
arge | +0.012 |
Judy | +0.012 |
Janet | +0.012 |
iet | +0.011 |
Neg logit contributions | |
Evan | -0.034 |
cand | -0.033 |
eighty | -0.032 |
cash | -0.032 |
pen | -0.031 |
Token | its |
Token ID | 663 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
arge | +0.063 |
imi | +0.063 |
Judy | +0.062 |
Janet | +0.062 |
Bet | +0.062 |
Neg logit contributions | |
Evan | -0.037 |
cand | -0.033 |
eighty | -0.033 |
cash | -0.030 |
himself | -0.030 |
Token | tail |
Token ID | 7894 |
Feature activation | -4.74e-01 |
Pos logit contributions | |
Evan | +0.043 |
cand | +0.041 |
eighty | +0.039 |
cash | +0.039 |
pen | +0.039 |
Neg logit contributions | |
Judy | -0.031 |
Janet | -0.031 |
arge | -0.031 |
imi | -0.030 |
Betty | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Evan | +0.014 |
cand | +0.013 |
yle | +0.012 |
cash | +0.012 |
penn | +0.012 |
Neg logit contributions | |
Judy | -0.009 |
anne | -0.009 |
imi | -0.009 |
iet | -0.009 |
Betty | -0.009 |
Token | l |
Token ID | 300 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
Judy | +0.010 |
Janet | +0.010 |
Betty | +0.010 |
imi | +0.010 |
Lynn | +0.010 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.006 |
pen | -0.006 |
eighty | -0.006 |
cash | -0.005 |
Token | icks |
Token ID | 3378 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
Evan | +0.018 |
cash | +0.017 |
cand | +0.017 |
hairc | +0.016 |
eighty | +0.016 |
Neg logit contributions | |
Judy | -0.007 |
imi | -0.007 |
arl | -0.006 |
oky | -0.006 |
arge | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | -4.01e-01 |
Pos logit contributions | |
Judy | +0.008 |
arge | +0.008 |
Janet | +0.008 |
imi | +0.008 |
anne | +0.008 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.006 |
eighty | -0.006 |
cash | -0.006 |
pen | -0.005 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.008 |
cash | +0.008 |
eighty | +0.008 |
marry | +0.007 |
Neg logit contributions | |
Bet | -0.012 |
Judy | -0.012 |
Janet | -0.012 |
arge | -0.011 |
anne | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -4.19e-02 |
Pos logit contributions | |
Evan | +0.025 |
cand | +0.025 |
eighty | +0.023 |
cash | +0.023 |
pen | +0.022 |
Neg logit contributions | |
arge | -0.038 |
Judy | -0.038 |
Janet | -0.038 |
Bet | -0.038 |
imi | -0.038 |
Token | Her |
Token ID | 2332 |
Feature activation | +5.22e-02 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
cash | +0.001 |
Qu | +0.001 |
marry | +0.001 |
Neg logit contributions | |
iet | -0.001 |
anne | -0.001 |
arge | -0.001 |
zie | -0.001 |
imi | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
Judy | +0.002 |
Janet | +0.002 |
Bet | +0.001 |
arge | +0.001 |
anne | +0.001 |
Neg logit contributions | |
cand | -0.001 |
Evan | -0.001 |
cash | -0.001 |
eighty | -0.001 |
penn | -0.001 |
Token | hugged |
Token ID | 41130 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
Evan | +0.009 |
penn | +0.008 |
eighty | +0.008 |
Mont | +0.007 |
cand | +0.007 |
Neg logit contributions | |
imi | -0.006 |
Lynn | -0.006 |
arge | -0.006 |
Janet | -0.006 |
Judy | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | -5.56e-01 |
Pos logit contributions | |
Judy | +0.024 |
Janet | +0.024 |
imi | +0.023 |
Betty | +0.023 |
arge | +0.023 |
Neg logit contributions | |
Evan | -0.023 |
cand | -0.022 |
eighty | -0.021 |
pen | -0.020 |
cash | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Evan | +0.015 |
cand | +0.014 |
pen | +0.013 |
penn | +0.013 |
eighty | +0.013 |
Neg logit contributions | |
Judy | -0.013 |
arge | -0.012 |
Janet | -0.012 |
imi | -0.012 |
iet | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.009 |
eighty | +0.008 |
pen | +0.008 |
cash | +0.008 |
Neg logit contributions | |
Judy | -0.007 |
Janet | -0.007 |
arge | -0.007 |
imi | -0.007 |
Betty | -0.007 |
Token | she |
Token ID | 673 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
imi | +0.007 |
Judy | +0.007 |
Betty | +0.006 |
Janet | +0.006 |
Maria | +0.006 |
Neg logit contributions | |
Evan | -0.007 |
pen | -0.007 |
cash | -0.007 |
eighty | -0.007 |
hop | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
arge | +0.013 |
imi | +0.013 |
Janet | +0.013 |
anne | +0.013 |
Judy | +0.013 |
Neg logit contributions | |
Evan | -0.013 |
eighty | -0.012 |
cand | -0.011 |
penn | -0.011 |
cash | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
Evan | +0.018 |
eighty | +0.017 |
cash | +0.016 |
yle | +0.016 |
cand | +0.016 |
Neg logit contributions | |
Judy | -0.016 |
Betty | -0.016 |
arge | -0.016 |
Janet | -0.015 |
Maria | -0.015 |
Token | could |
Token ID | 714 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
eighty | +0.004 |
cash | +0.004 |
penn | +0.004 |
Neg logit contributions | |
arge | -0.007 |
imi | -0.007 |
Janet | -0.007 |
Judy | -0.007 |
Bet | -0.007 |
Token | never |
Token ID | 1239 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Evan | +0.021 |
cand | +0.020 |
eighty | +0.020 |
cash | +0.019 |
marry | +0.018 |
Neg logit contributions | |
arge | -0.031 |
Janet | -0.031 |
imi | -0.031 |
Judy | -0.031 |
anne | -0.031 |
Token | get |
Token ID | 651 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Judy | +0.003 |
Betty | +0.003 |
Janet | +0.003 |
anne | +0.002 |
Maria | +0.002 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.002 |
eighty | -0.002 |
cash | -0.002 |
penn | -0.002 |
Token | enough |
Token ID | 1576 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
Judy | +0.008 |
Janet | +0.008 |
arge | +0.008 |
imi | +0.008 |
Betty | +0.008 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.006 |
eighty | -0.006 |
cash | -0.006 |
pen | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
arge | +0.003 |
Janet | +0.003 |
Judy | +0.003 |
imi | +0.003 |
Bet | +0.003 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.002 |
cash | -0.002 |
penn | -0.002 |
Token | eat |
Token ID | 4483 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
Judy | +0.014 |
arge | +0.014 |
Janet | +0.014 |
Betty | +0.014 |
imi | +0.013 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.008 |
eighty | -0.007 |
cash | -0.007 |
pen | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.77e-01 |
Pos logit contributions | |
arge | +0.024 |
Janet | +0.024 |
Judy | +0.024 |
imi | +0.024 |
anne | +0.023 |
Neg logit contributions | |
Evan | -0.018 |
cand | -0.017 |
eighty | -0.016 |
cash | -0.016 |
pen | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
iet | +0.009 |
arge | +0.009 |
lights | +0.009 |
Janet | +0.009 |
Judy | +0.009 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.004 |
cash | -0.004 |
eighty | -0.004 |
Qu | -0.003 |
Token | would |
Token ID | 561 |
Feature activation | -5.63e-01 |
Pos logit contributions | |
arge | +0.006 |
Judy | +0.006 |
anne | +0.006 |
imi | +0.006 |
Janet | +0.006 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.006 |
eighty | -0.006 |
pen | -0.006 |
cash | -0.005 |
Token | go |
Token ID | 467 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.010 |
eighty | +0.009 |
cash | +0.009 |
pen | +0.009 |
Neg logit contributions | |
Judy | -0.018 |
arge | -0.018 |
Janet | -0.018 |
imi | -0.017 |
Betty | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
arge | +0.019 |
imi | +0.019 |
Janet | +0.019 |
Judy | +0.019 |
anne | +0.019 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.010 |
himself | -0.009 |
pen | -0.009 |
eighty | -0.009 |
Token | |
Token ID | 220 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
Judy | +0.007 |
Janet | +0.007 |
arge | +0.007 |
Betty | +0.007 |
imi | +0.007 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
eighty | -0.004 |
cash | -0.004 |
penn | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
arge | +0.025 |
Janet | +0.024 |
iet | +0.024 |
Judy | +0.024 |
imi | +0.024 |
Neg logit contributions | |
Evan | -0.013 |
himself | -0.011 |
pen | -0.010 |
cand | -0.010 |
eighty | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
eighty | +0.003 |
pen | +0.003 |
cash | +0.003 |
Neg logit contributions | |
arge | -0.006 |
Judy | -0.006 |
Janet | -0.006 |
imi | -0.006 |
iet | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
Judy | +0.010 |
arge | +0.010 |
Janet | +0.010 |
imi | +0.009 |
Bet | +0.009 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.008 |
eighty | -0.008 |
cash | -0.008 |
penn | -0.007 |
Token | bear |
Token ID | 6842 |
Feature activation | +3.60e-01 |
Pos logit contributions | |
imi | +0.007 |
arge | +0.007 |
Judy | +0.006 |
Betty | +0.006 |
Janet | +0.006 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.005 |
eighty | -0.005 |
pen | -0.005 |
cash | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
arge | +0.011 |
Judy | +0.011 |
Janet | +0.011 |
imi | +0.011 |
Betty | +0.011 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.006 |
eighty | -0.006 |
cash | -0.006 |
pen | -0.006 |
Token | looking |
Token ID | 2045 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
Evan | +0.008 |
cand | +0.007 |
eighty | +0.007 |
cash | +0.007 |
pen | +0.006 |
Neg logit contributions | |
Judy | -0.009 |
arge | -0.009 |
Janet | -0.009 |
imi | -0.009 |
Betty | -0.009 |
Token | for |
Token ID | 329 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
eighty | +0.000 |
cash | +0.000 |
penn | +0.000 |
Neg logit contributions | |
arge | -0.001 |
Janet | -0.001 |
Judy | -0.001 |
imi | -0.001 |
Bet | -0.001 |
Token | honey |
Token ID | 12498 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
Evan | +0.011 |
eighty | +0.011 |
yle | +0.010 |
pen | +0.010 |
cand | +0.010 |
Neg logit contributions | |
Betty | -0.013 |
Judy | -0.013 |
Maria | -0.012 |
Janet | -0.012 |
Bree | -0.012 |
Token | near |
Token ID | 1474 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
arge | +0.007 |
Janet | +0.007 |
Judy | +0.007 |
imi | +0.007 |
anne | +0.007 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
eighty | -0.004 |
cash | -0.004 |
pen | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
cand | +0.002 |
Evan | +0.002 |
marry | +0.001 |
penn | +0.001 |
himself | +0.001 |
Neg logit contributions | |
Bet | -0.003 |
arge | -0.003 |
Janet | -0.003 |
imi | -0.003 |
Judy | -0.003 |
Token | So |
Token ID | 1406 |
Feature activation | +4.21e-01 |
Pos logit contributions | |
iet | +0.010 |
arge | +0.010 |
imi | +0.010 |
Janet | +0.010 |
Judy | +0.010 |
Neg logit contributions | |
Evan | -0.008 |
eighty | -0.006 |
cand | -0.006 |
cash | -0.006 |
Qu | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
arge | +0.013 |
imi | +0.013 |
Janet | +0.013 |
Judy | +0.013 |
anne | +0.013 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.007 |
eighty | -0.007 |
cash | -0.007 |
penn | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +1.20e-01 |
Pos logit contributions | |
arge | +0.007 |
Judy | +0.007 |
imi | +0.007 |
Janet | +0.007 |
anne | +0.007 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
eighty | -0.004 |
cash | -0.004 |
pen | -0.004 |
Token | family |
Token ID | 1641 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
Judy | +0.003 |
Janet | +0.003 |
arge | +0.003 |
imi | +0.003 |
Bet | +0.003 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.002 |
cash | -0.002 |
eighty | -0.002 |
penn | -0.002 |
Token | shared |
Token ID | 4888 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
Evan | +0.019 |
cand | +0.018 |
eighty | +0.017 |
cash | +0.017 |
pen | +0.016 |
Neg logit contributions | |
Judy | -0.023 |
Janet | -0.023 |
arge | -0.023 |
Betty | -0.022 |
anne | -0.022 |
Token | their |
Token ID | 511 |
Feature activation | +6.85e-01 |
Pos logit contributions | |
Judy | +0.018 |
arge | +0.018 |
Janet | +0.018 |
imi | +0.018 |
Betty | +0.017 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.011 |
eighty | -0.010 |
cash | -0.010 |
pen | -0.010 |
Token | spray |
Token ID | 11662 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
Judy | +0.018 |
arge | +0.018 |
Janet | +0.018 |
imi | +0.018 |
Betty | +0.017 |
Neg logit contributions | |
Evan | -0.016 |
eighty | -0.015 |
cand | -0.015 |
cash | -0.014 |
pen | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
arge | +0.005 |
Judy | +0.005 |
Janet | +0.005 |
imi | +0.005 |
anne | +0.005 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.003 |
cash | -0.003 |
eighty | -0.003 |
pen | -0.003 |
Token | gave |
Token ID | 2921 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
Judy | +0.007 |
Janet | +0.007 |
arge | +0.007 |
imi | +0.007 |
Betty | +0.007 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
eighty | -0.005 |
cash | -0.005 |
pen | -0.004 |
Token | some |
Token ID | 617 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Judy | +0.019 |
Janet | +0.018 |
arge | +0.018 |
Betty | +0.018 |
imi | +0.018 |
Neg logit contributions | |
Evan | -0.014 |
cand | -0.013 |
eighty | -0.012 |
cash | -0.012 |
pen | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
arge | -0.002 |
Judy | -0.002 |
Janet | -0.002 |
imi | -0.002 |
Bet | -0.002 |
Token | it |
Token ID | 340 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
arge | +0.007 |
imi | +0.007 |
Judy | +0.007 |
Janet | +0.007 |
anne | +0.007 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.004 |
pen | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | +8.51e-01 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.001 |
cash | +0.001 |
pen | +0.001 |
Neg logit contributions | |
Judy | -0.004 |
arge | -0.004 |
Janet | -0.004 |
imi | -0.004 |
Betty | -0.004 |
Token | easy |
Token ID | 2562 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
arge | +0.032 |
anne | +0.030 |
oky | +0.030 |
Judy | +0.030 |
iet | +0.030 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.011 |
eighty | -0.011 |
himself | -0.011 |
marry | -0.010 |
Token | ." |
Token ID | 526 |
Feature activation | +8.05e-02 |
Pos logit contributions | |
cand | +0.007 |
Evan | +0.006 |
himself | +0.006 |
hairc | +0.006 |
marry | +0.006 |
Neg logit contributions | |
Bet | -0.015 |
arge | -0.014 |
iet | -0.014 |
Janet | -0.014 |
imi | -0.014 |
Token | |
Token ID | 220 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
iet | +0.002 |
arge | +0.002 |
imi | +0.002 |
lights | +0.002 |
oky | +0.002 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.001 |
cash | -0.001 |
pen | -0.001 |
himself | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
iet | +0.036 |
arge | +0.036 |
Janet | +0.034 |
lights | +0.034 |
anne | +0.034 |
Neg logit contributions | |
Evan | -0.015 |
himself | -0.012 |
pen | -0.012 |
eighty | -0.011 |
Qu | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
lights | +0.005 |
arge | +0.004 |
iet | +0.004 |
oky | +0.004 |
imi | +0.004 |
Neg logit contributions | |
Evan | -0.002 |
himself | -0.002 |
pen | -0.002 |
cash | -0.002 |
eighty | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
arge | +0.014 |
imi | +0.014 |
Judy | +0.014 |
Janet | +0.014 |
lights | +0.014 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.010 |
cash | -0.010 |
eighty | -0.010 |
pen | -0.010 |
Token | little |
Token ID | 1310 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
Judy | +0.008 |
Janet | +0.008 |
arge | +0.008 |
anne | +0.008 |
imi | +0.008 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.006 |
cash | -0.005 |
eighty | -0.005 |
penn | -0.005 |
Token | boy |
Token ID | 2933 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
arge | +0.012 |
Judy | +0.012 |
Janet | +0.012 |
imi | +0.011 |
Bet | +0.011 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.008 |
eighty | -0.008 |
cash | -0.008 |
penn | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | +3.67e-01 |
Pos logit contributions | |
Evan | +0.003 |
cash | +0.002 |
eighty | +0.002 |
cand | +0.002 |
Qu | +0.002 |
Neg logit contributions | |
arge | -0.004 |
iet | -0.004 |
imi | -0.004 |
anne | -0.004 |
Janet | -0.004 |
Token | Those |
Token ID | 9627 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
Bet | +0.008 |
arge | +0.008 |
Judy | +0.008 |
oky | +0.008 |
iet | +0.007 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.010 |
eighty | -0.009 |
penn | -0.009 |
pen | -0.009 |
Token | are |
Token ID | 389 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
Evan | +0.013 |
eighty | +0.012 |
cand | +0.011 |
cash | +0.011 |
pen | +0.011 |
Neg logit contributions | |
Judy | -0.024 |
arge | -0.024 |
Janet | -0.024 |
imi | -0.024 |
Betty | -0.024 |
Token | Mom |
Token ID | 11254 |
Feature activation | +6.70e-02 |
Pos logit contributions | |
cand | +0.004 |
Evan | +0.004 |
eighty | +0.004 |
penn | +0.003 |
cash | +0.003 |
Neg logit contributions | |
anne | -0.005 |
Janet | -0.005 |
arge | -0.005 |
Judy | -0.005 |
iet | -0.005 |
Token | my |
Token ID | 1820 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
arge | +0.002 |
Janet | +0.002 |
Judy | +0.002 |
Bet | +0.002 |
iet | +0.002 |
Neg logit contributions | |
cand | -0.001 |
Evan | -0.001 |
eighty | -0.001 |
pen | -0.001 |
's | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
Judy | +0.005 |
arge | +0.005 |
Janet | +0.005 |
imi | +0.005 |
Bet | +0.005 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.004 |
eighty | -0.004 |
cash | -0.004 |
pen | -0.004 |
Token | flowers |
Token ID | 12734 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
cand | +0.012 |
marry | +0.011 |
penn | +0.011 |
re | +0.011 |
cash | +0.011 |
Neg logit contributions | |
Janet | -0.017 |
Maria | -0.017 |
Bet | -0.017 |
Judy | -0.017 |
Lynn | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
cand | +0.005 |
Evan | +0.005 |
eighty | +0.004 |
marry | +0.004 |
pen | +0.004 |
Neg logit contributions | |
Janet | -0.007 |
arge | -0.007 |
Judy | -0.007 |
Bet | -0.007 |
imi | -0.007 |
Token | You |
Token ID | 921 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Evan | +0.013 |
cand | +0.012 |
eighty | +0.012 |
cash | +0.011 |
marry | +0.011 |
Neg logit contributions | |
arge | -0.012 |
Janet | -0.012 |
Judy | -0.012 |
imi | -0.012 |
anne | -0.012 |
Token | can |
Token ID | 460 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.006 |
Neg logit contributions | |
Judy | -0.009 |
Janet | -0.009 |
arge | -0.009 |
imi | -0.009 |
Betty | -0.009 |
Token | 't |
Token ID | 470 |
Feature activation | +1.98e-01 |
Pos logit contributions | |
Evan | +0.026 |
cand | +0.024 |
eighty | +0.023 |
cash | +0.022 |
penn | +0.022 |
Neg logit contributions | |
imi | -0.034 |
Judy | -0.034 |
arge | -0.034 |
Janet | -0.033 |
Betty | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
arge | +0.000 |
Judy | +0.000 |
Janet | +0.000 |
imi | +0.000 |
anne | +0.000 |
Neg logit contributions | |
Evan | -0.000 |
cand | -0.000 |
eighty | -0.000 |
cash | -0.000 |
pen | -0.000 |
Token | be |
Token ID | 307 |
Feature activation | +5.96e-01 |
Pos logit contributions | |
Judy | +0.014 |
Janet | +0.014 |
imi | +0.014 |
Betty | +0.014 |
arge | +0.014 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.010 |
eighty | -0.009 |
yle | -0.009 |
penn | -0.009 |
Token | honest |
Token ID | 5508 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
Judy | +0.017 |
Janet | +0.017 |
arge | +0.016 |
Betty | +0.016 |
imi | +0.016 |
Neg logit contributions | |
Evan | -0.013 |
cand | -0.012 |
eighty | -0.012 |
cash | -0.011 |
pen | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
Evan | +0.016 |
cand | +0.015 |
eighty | +0.015 |
cash | +0.014 |
pen | +0.014 |
Neg logit contributions | |
Judy | -0.021 |
arge | -0.021 |
Janet | -0.021 |
imi | -0.021 |
Betty | -0.021 |
Token | kind |
Token ID | 1611 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Judy | +0.001 |
Janet | +0.001 |
arge | +0.001 |
Betty | +0.001 |
imi | +0.001 |
Neg logit contributions | |
Evan | -0.000 |
cand | -0.000 |
eighty | -0.000 |
pen | -0.000 |
cash | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +3.70e-03 |
Pos logit contributions | |
Evan | +0.014 |
cand | +0.014 |
eighty | +0.013 |
cash | +0.013 |
pen | +0.012 |
Neg logit contributions | |
Judy | -0.015 |
arge | -0.015 |
Janet | -0.015 |
imi | -0.015 |
Betty | -0.015 |
Token | Do |
Token ID | 2141 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
Judy | +0.000 |
Janet | +0.000 |
arge | +0.000 |
imi | +0.000 |
Betty | +0.000 |
Neg logit contributions | |
Evan | -0.000 |
cand | -0.000 |
eighty | -0.000 |
cash | -0.000 |
pen | -0.000 |
Token | you |
Token ID | 345 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
imi | +0.005 |
Janet | +0.004 |
Judy | +0.004 |
arge | +0.004 |
Betty | +0.004 |
Neg logit contributions | |
Evan | -0.004 |
eighty | -0.004 |
pen | -0.004 |
cand | -0.004 |
cash | -0.004 |
Token | understand |
Token ID | 1833 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
Judy | +0.011 |
Janet | +0.011 |
arge | +0.011 |
imi | +0.010 |
Betty | +0.010 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.005 |
eighty | -0.004 |
cash | -0.004 |
pen | -0.004 |
Token | ?" |
Token ID | 1701 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
Evan | +0.021 |
cand | +0.021 |
cash | +0.020 |
eighty | +0.020 |
marry | +0.020 |
Neg logit contributions | |
anne | -0.012 |
Bet | -0.012 |
Judy | -0.012 |
Janet | -0.011 |
arge | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.83e-01 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
eighty | +0.000 |
pen | +0.000 |
cash | +0.000 |
Neg logit contributions | |
Judy | -0.000 |
Janet | -0.000 |
arge | -0.000 |
imi | -0.000 |
Betty | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
Judy | +0.032 |
arge | +0.032 |
Janet | +0.032 |
imi | +0.031 |
Betty | +0.031 |
Neg logit contributions | |
Evan | -0.019 |
cand | -0.018 |
eighty | -0.017 |
cash | -0.016 |
pen | -0.016 |
Token | stop |
Token ID | 2245 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
imi | +0.007 |
Judy | +0.007 |
Janet | +0.007 |
arge | +0.006 |
Betty | +0.006 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.006 |
pen | -0.006 |
eighty | -0.006 |
cash | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.006 |
Neg logit contributions | |
anne | -0.009 |
Bet | -0.009 |
Judy | -0.009 |
arge | -0.009 |
Janet | -0.009 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
Evan | +0.000 |
cand | +0.000 |
eighty | +0.000 |
pen | +0.000 |
cash | +0.000 |
Neg logit contributions | |
Judy | -0.000 |
arge | -0.000 |
Janet | -0.000 |
Bet | -0.000 |
anne | -0.000 |
Token | Sara |
Token ID | 24799 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
pen | +0.015 |
eighty | +0.015 |
cand | +0.014 |
Evan | +0.014 |
ninety | +0.013 |
Neg logit contributions | |
Judy | -0.014 |
Betty | -0.013 |
arge | -0.013 |
imi | -0.013 |
Lynn | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
Judy | +0.016 |
arge | +0.016 |
Janet | +0.016 |
imi | +0.016 |
Betty | +0.016 |
Neg logit contributions | |
Evan | -0.020 |
cand | -0.019 |
eighty | -0.019 |
cash | -0.018 |
pen | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.009 |
eighty | +0.009 |
cash | +0.009 |
ninety | +0.008 |
Neg logit contributions | |
Judy | -0.007 |
Maria | -0.007 |
Janet | -0.006 |
anne | -0.006 |
Betty | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
Evan | +0.006 |
cand | +0.006 |
eighty | +0.006 |
cash | +0.006 |
pen | +0.005 |
Neg logit contributions | |
arge | -0.006 |
Janet | -0.006 |
imi | -0.006 |
Judy | -0.006 |
anne | -0.006 |
Token | You |
Token ID | 1639 |
Feature activation | -2.88e-02 |
Pos logit contributions | |
arge | +0.007 |
Bet | +0.006 |
oky | +0.006 |
iet | +0.006 |
Judy | +0.006 |
Neg logit contributions | |
Evan | -0.010 |
cand | -0.010 |
penn | -0.009 |
eighty | -0.009 |
cash | -0.008 |
Token | are |
Token ID | 389 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
Evan | +0.001 |
cand | +0.001 |
eighty | +0.001 |
cash | +0.001 |
ninety | +0.001 |
Neg logit contributions | |
Janet | -0.001 |
Judy | -0.001 |
imi | -0.001 |
arge | -0.001 |
Betty | -0.001 |
Token | making |
Token ID | 1642 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
Janet | +0.008 |
arge | +0.008 |
Judy | +0.008 |
Betty | +0.008 |
June | +0.008 |
Neg logit contributions | |
Evan | -0.011 |
cand | -0.010 |
eighty | -0.010 |
pen | -0.010 |
hop | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
Judy | +0.011 |
Janet | +0.010 |
arge | +0.010 |
imi | +0.010 |
Betty | +0.010 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.011 |
cash | -0.010 |
eighty | -0.010 |
pen | -0.010 |
Token | thanked |
Token ID | 26280 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
Judy | +0.004 |
Janet | +0.004 |
Betty | +0.003 |
Lynn | +0.003 |
Bree | +0.003 |
Neg logit contributions | |
Evan | -0.004 |
pen | -0.003 |
eighty | -0.003 |
cand | -0.003 |
yle | -0.003 |
Token | Mama |
Token ID | 40084 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
Judy | +0.019 |
Janet | +0.019 |
arge | +0.019 |
imi | +0.018 |
Betty | +0.018 |
Neg logit contributions | |
Evan | -0.014 |
cand | -0.013 |
eighty | -0.013 |
cash | -0.012 |
pen | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
Evan | +0.027 |
cand | +0.026 |
eighty | +0.025 |
cash | +0.024 |
pen | +0.023 |
Neg logit contributions | |
Judy | -0.033 |
arge | -0.033 |
Janet | -0.033 |
imi | -0.032 |
Bet | -0.031 |
Token | They |
Token ID | 1119 |
Feature activation | +3.45e-01 |
Pos logit contributions | |
anne | +0.010 |
iet | +0.010 |
arge | +0.009 |
outage | +0.009 |
iders | +0.009 |
Neg logit contributions | |
Evan | -0.005 |
Qu | -0.004 |
Pe | -0.004 |
cash | -0.004 |
eighty | -0.004 |
Token | put |
Token ID | 1234 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
Janet | +0.009 |
Judy | +0.009 |
Bet | +0.008 |
iet | +0.008 |
Betty | +0.008 |
Neg logit contributions | |
Evan | -0.008 |
hairc | -0.008 |
eighty | -0.007 |
cand | -0.007 |
yle | -0.007 |
Token | their |
Token ID | 511 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Evan | +0.009 |
cand | +0.008 |
eighty | +0.008 |
pen | +0.007 |
cash | +0.007 |
Neg logit contributions | |
Judy | -0.013 |
Janet | -0.013 |
arge | -0.013 |
Betty | -0.013 |
imi | -0.013 |
Token | pieces |
Token ID | 5207 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
imi | +0.007 |
arge | +0.007 |
Judy | +0.007 |
Janet | +0.007 |
Betty | +0.007 |
Neg logit contributions | |
Evan | -0.011 |
pen | -0.009 |
etr | -0.009 |
eighty | -0.009 |
hop | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
Evan | +0.008 |
cash | +0.007 |
cand | +0.007 |
eighty | +0.007 |
pen | +0.007 |
Neg logit contributions | |
Judy | -0.008 |
Janet | -0.008 |
lights | -0.008 |
iet | -0.008 |
Betty | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Judy | +0.016 |
Betty | +0.015 |
Maria | +0.015 |
imi | +0.015 |
Janet | +0.015 |
Neg logit contributions | |
Evan | -0.020 |
eighty | -0.017 |
pen | -0.017 |
etr | -0.017 |
yle | -0.017 |
Token | magnet |
Token ID | 19972 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
imi | +0.003 |
window | +0.003 |
vine | +0.003 |
hose | +0.003 |
blender | +0.003 |
Neg logit contributions | |
Evan | -0.004 |
hop | -0.003 |
yle | -0.003 |
pen | -0.003 |
Mont | -0.003 |
Token | Max |
Token ID | 5436 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
Judy | +0.014 |
Janet | +0.014 |
arge | +0.014 |
imi | +0.014 |
Betty | +0.014 |
Neg logit contributions | |
Evan | -0.012 |
cand | -0.012 |
eighty | -0.011 |
cash | -0.011 |
penn | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
June | +0.003 |
imi | +0.003 |
Betty | +0.003 |
Judy | +0.003 |
Lynn | +0.003 |
Neg logit contributions | |
Evan | -0.006 |
yle | -0.005 |
cand | -0.005 |
cash | -0.005 |
marry | -0.005 |
Token | play |
Token ID | 711 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.006 |
eighty | +0.006 |
pen | +0.006 |
cash | +0.006 |
Neg logit contributions | |
Judy | -0.009 |
Janet | -0.009 |
arge | -0.009 |
imi | -0.009 |
Betty | -0.009 |
Token | with |
Token ID | 351 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
Evan | +0.007 |
cand | +0.006 |
eighty | +0.006 |
penn | +0.006 |
cash | +0.006 |
Neg logit contributions | |
Judy | -0.012 |
Janet | -0.012 |
June | -0.012 |
Betty | -0.011 |
Lynn | -0.011 |
Token | him |
Token ID | 683 |
Feature activation | -4.21e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.002 |
eighty | +0.002 |
cash | +0.002 |
penn | +0.002 |
Neg logit contributions | |
Judy | -0.006 |
Janet | -0.006 |
arge | -0.006 |
imi | -0.006 |
Betty | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
Evan | +0.012 |
eighty | +0.011 |
cand | +0.011 |
cash | +0.011 |
pen | +0.010 |
Neg logit contributions | |
imi | -0.008 |
Betty | -0.008 |
Judy | -0.008 |
Janet | -0.008 |
June | -0.008 |
Token | They |
Token ID | 1119 |
Feature activation | +5.94e-02 |
Pos logit contributions | |
arge | +0.003 |
imi | +0.003 |
iet | +0.003 |
anne | +0.003 |
Judy | +0.003 |
Neg logit contributions | |
Evan | -0.002 |
Qu | -0.002 |
eighty | -0.002 |
cand | -0.002 |
himself | -0.002 |
Token | wait |
Token ID | 4043 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
Judy | +0.002 |
Janet | +0.002 |
Bet | +0.002 |
Betty | +0.002 |
arge | +0.002 |
Neg logit contributions | |
Evan | -0.001 |
cand | -0.001 |
eighty | -0.001 |
cash | -0.001 |
pen | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
Evan | +0.014 |
eighty | +0.013 |
cand | +0.013 |
goodbye | +0.012 |
cash | +0.012 |
Neg logit contributions | |
Janet | -0.023 |
Bet | -0.022 |
Judy | -0.022 |
imi | -0.022 |
arge | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
Evan | +0.008 |
cand | +0.007 |
eighty | +0.007 |
cash | +0.007 |
pen | +0.007 |
Neg logit contributions | |
Judy | -0.011 |
arge | -0.011 |
Janet | -0.011 |
imi | -0.011 |
Betty | -0.011 |
Token | woman |
Token ID | 2415 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
Judy | +0.008 |
Janet | +0.008 |
arge | +0.008 |
imi | +0.008 |
Betty | +0.008 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.007 |
cash | -0.007 |
eighty | -0.006 |
penn | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
Judy | +0.002 |
Betty | +0.002 |
Janet | +0.002 |
Maria | +0.002 |
June | +0.002 |
Neg logit contributions | |
Evan | -0.002 |
pen | -0.002 |
cash | -0.002 |
cand | -0.002 |
eighty | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.009 |
eighty | +0.009 |
cash | +0.009 |
ninety | +0.008 |
Neg logit contributions | |
arge | -0.012 |
imi | -0.012 |
Judy | -0.011 |
Janet | -0.011 |
iet | -0.011 |
Token | That |
Token ID | 2504 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
Judy | +0.006 |
imi | +0.006 |
arge | +0.006 |
Janet | +0.006 |
Betty | +0.006 |
Neg logit contributions | |
Evan | -0.006 |
cand | -0.006 |
eighty | -0.006 |
cash | -0.006 |
pen | -0.005 |
Token | is |
Token ID | 318 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
Evan | +0.005 |
cand | +0.005 |
eighty | +0.005 |
cash | +0.005 |
pen | +0.004 |
Neg logit contributions | |
Janet | -0.007 |
Judy | -0.007 |
arge | -0.007 |
imi | -0.007 |
Betty | -0.007 |
Token | an |
Token ID | 281 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
Evan | +0.004 |
cand | +0.004 |
eighty | +0.004 |
marry | +0.003 |
re | +0.003 |
Neg logit contributions | |
anne | -0.012 |
arge | -0.012 |
imi | -0.012 |
iet | -0.012 |
Bet | -0.011 |
Token | aer |
Token ID | 9551 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
Evan | +0.010 |
cand | +0.010 |
pen | +0.009 |
cash | +0.009 |
eighty | +0.009 |
Neg logit contributions | |
arge | -0.012 |
Janet | -0.012 |
Judy | -0.012 |
imi | -0.011 |
Betty | -0.011 |
Token | opl |
Token ID | 20106 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Evan | +0.041 |
cand | +0.039 |
eighty | +0.038 |
pen | +0.037 |
cash | +0.037 |
Neg logit contributions | |
Judy | -0.030 |
Janet | -0.030 |
arge | -0.029 |
imi | -0.029 |
Betty | -0.029 |
Token | ane |
Token ID | 1531 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
Evan | +0.032 |
cand | +0.031 |
cash | +0.029 |
eighty | +0.028 |
penn | +0.027 |
Neg logit contributions | |
arge | -0.030 |
Janet | -0.030 |
imi | -0.029 |
Judy | -0.029 |
oky | -0.028 |
Token | ! |
Token ID | 0 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
arge | +0.014 |
Judy | +0.013 |
Janet | +0.013 |
imi | +0.013 |
Bet | +0.013 |
Neg logit contributions | |
Evan | -0.009 |
cand | -0.009 |
eighty | -0.008 |
marry | -0.008 |
pen | -0.008 |
Token | It |
Token ID | 632 |
Feature activation | -7.79e-01 |
Pos logit contributions | |
Evan | +0.006 |
cand | +0.005 |
eighty | +0.005 |
cash | +0.005 |
pen | +0.005 |
Neg logit contributions | |
arge | -0.007 |
Judy | -0.007 |
imi | -0.007 |
Janet | -0.007 |
anne | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
Evan | +0.015 |
cand | +0.014 |
cash | +0.013 |
eighty | +0.013 |
pen | +0.013 |
Neg logit contributions | |
Judy | -0.024 |
Janet | -0.024 |
arge | -0.023 |
imi | -0.023 |
Betty | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
arge | +0.018 |
lights | +0.018 |
leys | +0.017 |
oky | +0.017 |
iet | +0.017 |
Neg logit contributions | |
Evan | -0.005 |
cand | -0.004 |
pen | -0.004 |
eighty | -0.004 |
cash | -0.003 |
Token | I |
Token ID | 314 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
Judy | +0.010 |
Janet | +0.010 |
imi | +0.010 |
Betty | +0.010 |
arge | +0.010 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.008 |
eighty | -0.008 |
cash | -0.007 |
pen | -0.007 |
Token | 'm |
Token ID | 1101 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
arge | +0.032 |
Judy | +0.032 |
Janet | +0.032 |
imi | +0.031 |
anne | +0.031 |
Neg logit contributions | |
Evan | -0.021 |
cand | -0.019 |
eighty | -0.018 |
pen | -0.018 |
cash | -0.017 |
Token | scared |
Token ID | 12008 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
arge | +0.014 |
anne | +0.014 |
lights | +0.014 |
iet | +0.014 |
imi | +0.014 |
Neg logit contributions | |
Evan | -0.013 |
eighty | -0.012 |
cand | -0.012 |
Qu | -0.011 |
re | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Janet | +0.018 |
Judy | +0.018 |
arge | +0.018 |
anne | +0.018 |
Bet | +0.018 |
Neg logit contributions | |
Evan | -0.007 |
himself | -0.006 |
cand | -0.006 |
re | -0.006 |
Qu | -0.005 |
Token | that |
Token ID | 326 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.002 |
cash | +0.002 |
penn | +0.002 |
Neg logit contributions | |
anne | -0.004 |
arge | -0.004 |
Janet | -0.004 |
Judy | -0.004 |
iet | -0.004 |
Token | gate |
Token ID | 8946 |
Feature activation | +2.22e-02 |
Pos logit contributions | |
Evan | +0.032 |
's | +0.031 |
hairc | +0.030 |
re | +0.029 |
goodbye | +0.029 |
Neg logit contributions | |
anne | -0.035 |
Janet | -0.035 |
arl | -0.034 |
Bet | -0.034 |
lights | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -8.60e-02 |
Pos logit contributions | |
arge | +0.001 |
Jud | +0.001 |
Judy | +0.001 |
Bet | +0.001 |
Rachel | +0.001 |
Neg logit contributions | |
cand | -0.000 |
Evan | -0.000 |
's | -0.000 |
himself | -0.000 |
re | -0.000 |
Token | Can |
Token ID | 1680 |
Feature activation | +7.23e-02 |
Pos logit contributions | |
Evan | +0.002 |
eighty | +0.001 |
cash | +0.001 |
cand | +0.001 |
Qu | +0.001 |
Neg logit contributions | |
arge | -0.003 |
iet | -0.003 |
Judy | -0.003 |
anne | -0.003 |
imi | -0.003 |
Token | you |
Token ID | 345 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
imi | +0.002 |
Janet | +0.002 |
Betty | +0.002 |
Judy | +0.002 |
June | +0.002 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.002 |
pen | -0.002 |
cash | -0.002 |
Token | help |
Token ID | 1037 |
Feature activation | -4.57e-01 |
Pos logit contributions | |
Judy | +0.007 |
Janet | +0.007 |
imi | +0.007 |
arge | +0.007 |
Betty | +0.007 |
Neg logit contributions | |
Evan | -0.004 |
cand | -0.004 |
eighty | -0.003 |
cash | -0.003 |
penn | -0.003 |
Token | ay |
Token ID | 323 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
Evan | +0.012 |
cand | +0.011 |
eighty | +0.011 |
cash | +0.011 |
pen | +0.011 |
Neg logit contributions | |
arge | -0.006 |
imi | -0.006 |
Janet | -0.006 |
Judy | -0.006 |
Betty | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
Evan | +0.020 |
cand | +0.019 |
eighty | +0.018 |
cash | +0.018 |
pen | +0.017 |
Neg logit contributions | |
Judy | -0.014 |
Janet | -0.014 |
arge | -0.014 |
imi | -0.014 |
Betty | -0.013 |
Token | let |
Token ID | 1309 |
Feature activation | -2.53e-01 |
Pos logit contributions | |
Judy | +0.009 |
Janet | +0.009 |
arge | +0.009 |
imi | +0.009 |
Betty | +0.009 |
Neg logit contributions | |
Evan | -0.007 |
cand | -0.006 |
eighty | -0.006 |
cash | -0.006 |
pen | -0.006 |
Token | â |
Token ID | 22940 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
eighty | +0.003 |
cash | +0.003 |
pen | +0.003 |
Neg logit contributions | |
Judy | -0.009 |
Janet | -0.009 |
imi | -0.009 |
arge | -0.009 |
Betty | -0.009 |
Token | € |
Token ID | 26391 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
Janet | +0.009 |
Judy | +0.009 |
arge | +0.009 |
anne | +0.009 |
imi | +0.009 |
Neg logit contributions | |
cand | -0.012 |
Evan | -0.011 |
eighty | -0.011 |
penn | -0.011 |
cash | -0.011 |
Token | ™ |
Token ID | 8151 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
Judy | +0.011 |
arge | +0.011 |
Janet | +0.011 |
imi | +0.011 |
Betty | +0.010 |
Neg logit contributions | |
Evan | -0.011 |
cand | -0.010 |
eighty | -0.010 |
cash | -0.009 |
pen | -0.009 |
Token | s |
Token ID | 82 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
Evan | +0.040 |
cand | +0.038 |
eighty | +0.036 |
cash | +0.035 |
pen | +0.035 |
Neg logit contributions | |
Judy | -0.040 |
Janet | -0.040 |
arge | -0.040 |
imi | -0.039 |
Betty | -0.038 |
Token | buy |
Token ID | 2822 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
Evan | +0.008 |
cand | +0.007 |
eighty | +0.007 |
cash | +0.007 |
pen | +0.006 |
Neg logit contributions | |
Judy | -0.015 |
Janet | -0.015 |
arge | -0.015 |
imi | -0.015 |
Betty | -0.014 |
Token | it |
Token ID | 340 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
Judy | +0.005 |
arge | +0.005 |
Janet | +0.005 |
Betty | +0.005 |
imi | +0.005 |
Neg logit contributions | |
Evan | -0.004 |
eighty | -0.004 |
pen | -0.004 |
cand | -0.004 |
etr | -0.004 |
Token | ! |
Token ID | 0 |
Feature activation | +4.41e-01 |
Pos logit contributions | |
arge | +0.009 |
Judy | +0.009 |
Janet | +0.009 |
imi | +0.009 |
Bet | +0.009 |
Neg logit contributions | |
Evan | -0.008 |
cand | -0.007 |
eighty | -0.007 |
cash | -0.007 |
penn | -0.006 |
Token | â |
Token ID | 22940 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
arge | +0.013 |
imi | +0.013 |
iet | +0.013 |
Judy | +0.013 |
anne | +0.013 |
Neg logit contributions | |
Evan | -0.010 |
eighty | -0.008 |
cand | -0.008 |
cash | -0.008 |
pen | -0.007 |
Token | lived |
Token ID | 5615 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
imi | +0.001 |
Maria | +0.001 |
Judy | +0.001 |
Betty | +0.001 |
Janet | +0.001 |
Neg logit contributions | |
eighty | -0.002 |
cash | -0.002 |
cand | -0.002 |
Evan | -0.001 |
penn | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
cand | +0.004 |
Evan | +0.003 |
cash | +0.003 |
hairc | +0.003 |
penn | +0.003 |
Neg logit contributions | |
Bet | -0.003 |
Judy | -0.003 |
Betty | -0.003 |
imi | -0.003 |
Maria | -0.003 |
Token | little |
Token ID | 1310 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
Evan | +0.011 |
cand | +0.011 |
eighty | +0.010 |
cash | +0.010 |
pen | +0.010 |
Neg logit contributions | |
Judy | -0.013 |
arge | -0.013 |
imi | -0.013 |
Janet | -0.013 |
Betty | -0.013 |
Token | girl |
Token ID | 2576 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
imi | +0.016 |
Judy | +0.016 |
arge | +0.016 |
Janet | +0.016 |
Betty | +0.016 |
Neg logit contributions | |
Evan | -0.015 |
cand | -0.014 |
eighty | -0.014 |
cash | -0.013 |
pen | -0.013 |
Token | named |
Token ID | 3706 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Judy | +0.002 |
arge | +0.002 |
Janet | +0.002 |
imi | +0.002 |
Betty | +0.002 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.001 |
cash | -0.001 |
pen | -0.001 |
Token | Gab |
Token ID | 12300 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
lights | +0.004 |
arge | +0.004 |
iet | +0.004 |
puters | +0.004 |
Janet | +0.004 |
Neg logit contributions | |
Evan | -0.003 |
cand | -0.002 |
Qu | -0.002 |
marry | -0.002 |
cash | -0.002 |
Token | by |
Token ID | 1525 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
Evan | +0.038 |
cand | +0.035 |
cash | +0.033 |
eighty | +0.033 |
penn | +0.032 |
Neg logit contributions | |
imi | -0.031 |
arge | -0.030 |
Judy | -0.030 |
iet | -0.030 |
Janet | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -9.39e-02 |
Pos logit contributions | |
Judy | +0.002 |
arge | +0.002 |
Janet | +0.002 |
imi | +0.002 |
Betty | +0.002 |
Neg logit contributions | |
Evan | -0.002 |
cand | -0.002 |
eighty | -0.002 |
cash | -0.002 |
pen | -0.002 |
Token | She |
Token ID | 1375 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
etr | +0.003 |
hairc | +0.003 |
pen | +0.003 |
Neg logit contributions | |
Judy | -0.002 |
Janet | -0.002 |
Betty | -0.002 |
Bet | -0.002 |
Donna | -0.002 |
Token | woke |
Token ID | 19092 |
Feature activation | +4.94e-01 |
Pos logit contributions | |
Evan | +0.001 |
cash | +0.001 |
eighty | +0.001 |
cand | +0.001 |
pen | +0.001 |
Neg logit contributions | |
imi | -0.000 |
iet | -0.000 |
arge | -0.000 |
anne | -0.000 |
Janet | -0.000 |
Token | up |
Token ID | 510 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
imi | +0.011 |
arge | +0.011 |
Judy | +0.011 |
Janet | +0.011 |
Betty | +0.011 |
Neg logit contributions | |
Evan | -0.013 |
cand | -0.013 |
eighty | -0.013 |
cash | -0.012 |
pen | -0.012 |
Token | Ben |
Token ID | 3932 |
Feature activation | +6.39e-01 |
Pos logit contributions | |
Judy | +0.017 |
Betty | +0.016 |
Janet | +0.016 |
Maria | +0.015 |
June | +0.015 |
Neg logit contributions | |
cand | -0.016 |
Evan | -0.016 |
pen | -0.016 |
cash | -0.015 |
eighty | -0.015 |
Token | were |
Token ID | 547 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
Judy | +0.015 |
iet | +0.014 |
Janet | +0.014 |
Betty | +0.013 |
Bet | +0.013 |
Neg logit contributions | |
cand | -0.015 |
Evan | -0.015 |
cash | -0.015 |
hairc | -0.015 |
penn | -0.015 |
Token | twins |
Token ID | 20345 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
Evan | +0.005 |
cand | +0.004 |
eighty | +0.004 |
cash | +0.004 |
penn | +0.004 |
Neg logit contributions | |
Judy | -0.007 |
Janet | -0.007 |
arge | -0.007 |
imi | -0.007 |
anne | -0.007 |
Token | who |
Token ID | 508 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
Evan | +0.002 |
cand | +0.002 |
eighty | +0.002 |
ninety | +0.002 |
cash | +0.002 |
Neg logit contributions | |
arge | -0.001 |
anne | -0.001 |
imi | -0.001 |
Maria | -0.001 |
Judy | -0.001 |
Token | loved |
Token ID | 6151 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
anne | +0.013 |
Judy | +0.013 |
Janet | +0.013 |
arge | +0.013 |
Betty | +0.012 |
Neg logit contributions | |
eighty | -0.014 |
cand | -0.014 |
Evan | -0.014 |
penn | -0.013 |
cash | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
arge | +0.034 |
Judy | +0.034 |
Janet | +0.034 |
Betty | +0.033 |
imi | +0.033 |
Neg logit contributions | |
Evan | -0.037 |
eighty | -0.034 |
pen | -0.033 |
cand | -0.033 |
cash | -0.032 |
Token | play |
Token ID | 711 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
Evan | +0.025 |
cand | +0.023 |
eighty | +0.022 |
cash | +0.021 |
pen | +0.020 |
Neg logit contributions | |
arge | -0.046 |
Judy | -0.046 |
imi | -0.045 |
Janet | -0.045 |
Bet | -0.045 |
Token | with |
Token ID | 351 |
Feature activation | -5.96e-02 |
Pos logit contributions | |
Evan | +0.007 |
eighty | +0.007 |
cand | +0.007 |
ninety | +0.007 |
seventy | +0.006 |
Neg logit contributions | |
imi | -0.009 |
Janet | -0.009 |
iet | -0.008 |
arge | -0.008 |
Judy | -0.008 |
Token | their |
Token ID | 511 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
Evan | +0.002 |
eighty | +0.002 |
cand | +0.001 |
pen | +0.001 |
cash | +0.001 |
Neg logit contributions | |
imi | -0.001 |
arge | -0.001 |
Janet | -0.001 |
Judy | -0.001 |
Betty | -0.001 |
Token | toys |
Token ID | 14958 |
Feature activation | +4.35e-01 |
Pos logit contributions | |
Evan | +0.003 |
cand | +0.003 |
cash | +0.003 |
eighty | +0.003 |
penn | +0.002 |
Neg logit contributions | |
Judy | -0.004 |
Janet | -0.004 |
arge | -0.004 |
imi | -0.004 |
Bet | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
arge | +0.010 |
imi | +0.010 |
Janet | +0.010 |
Judy | +0.010 |
Betty | +0.010 |
Neg logit contributions | |
Evan | -0.011 |
eighty | -0.010 |
cand | -0.010 |
cash | -0.010 |
pen | -0.010 |