Token | not |
Token ID | 407 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
ained | +0.031 |
ount | +0.028 |
ectar | +0.028 |
ala | +0.027 |
perspective | +0.027 |
Neg logit contributions | |
hands | -0.020 |
paws | -0.018 |
help | -0.017 |
drive | -0.016 |
Daddy | -0.016 |
Token | ride |
Token ID | 6594 |
Feature activation | -6.23e-03 |
Pos logit contributions | |
ained | +0.057 |
Ag | +0.051 |
THE | +0.051 |
Prin | +0.050 |
ectar | +0.050 |
Neg logit contributions | |
hands | -0.028 |
sle | -0.026 |
paws | -0.026 |
fingers | -0.024 |
cheeks | -0.023 |
Token | his |
Token ID | 465 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
hands | +0.007 |
paws | +0.007 |
sle | +0.007 |
fingers | +0.006 |
apr | +0.006 |
Neg logit contributions | |
ained | -0.013 |
ectar | -0.012 |
Ag | -0.012 |
perspective | -0.012 |
Prin | -0.012 |
Token | bike |
Token ID | 7161 |
Feature activation | -1.39e-03 |
Pos logit contributions | |
ained | +0.009 |
THE | +0.008 |
Ag | +0.008 |
ust | +0.008 |
perspective | +0.008 |
Neg logit contributions | |
sle | -0.005 |
hands | -0.005 |
paws | -0.005 |
apr | -0.005 |
pans | -0.005 |
Token | at |
Token ID | 379 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
hands | +0.002 |
drive | +0.002 |
paws | +0.002 |
sle | +0.002 |
load | +0.002 |
Neg logit contributions | |
ectar | -0.003 |
ained | -0.002 |
Ag | -0.002 |
Kay | -0.002 |
eway | -0.002 |
Token | such |
Token ID | 884 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
ained | +0.025 |
Ag | +0.022 |
THE | +0.022 |
ectar | +0.022 |
Prin | +0.022 |
Neg logit contributions | |
hands | -0.016 |
sle | -0.016 |
paws | -0.015 |
fingers | -0.014 |
apr | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +9.10e-03 |
Pos logit contributions | |
ained | +0.235 |
ount | +0.221 |
ectar | +0.217 |
inas | +0.215 |
Ag | +0.213 |
Neg logit contributions | |
hands | -0.067 |
paws | -0.059 |
fingers | -0.048 |
Daddy | -0.044 |
sle | -0.041 |
Token | high |
Token ID | 1029 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
ained | +0.020 |
ectar | +0.018 |
ala | +0.017 |
ount | +0.017 |
Ag | +0.017 |
Neg logit contributions | |
hands | -0.010 |
sle | -0.010 |
paws | -0.009 |
fingers | -0.008 |
load | -0.008 |
Token | speed |
Token ID | 2866 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
ained | +0.005 |
Ag | +0.005 |
ectar | +0.004 |
Kay | +0.004 |
THE | +0.004 |
Neg logit contributions | |
hands | -0.003 |
sle | -0.003 |
paws | -0.003 |
fingers | -0.003 |
load | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +6.18e-04 |
Pos logit contributions | |
ectar | +0.011 |
Kay | +0.011 |
Ag | +0.010 |
ained | +0.010 |
Acc | +0.010 |
Neg logit contributions | |
hands | -0.005 |
load | -0.004 |
drive | -0.004 |
sle | -0.004 |
paws | -0.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
ained | +0.001 |
THE | +0.001 |
Ag | +0.001 |
ectar | +0.001 |
Prin | +0.001 |
Neg logit contributions | |
sle | -0.001 |
hands | -0.001 |
paws | -0.001 |
pans | -0.001 |
apr | -0.001 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
ained | +0.052 |
perspective | +0.047 |
ust | +0.046 |
fault | +0.045 |
eway | +0.045 |
Neg logit contributions | |
hands | -0.032 |
paws | -0.029 |
sle | -0.028 |
Daddy | -0.027 |
cheeks | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +8.51e-03 |
Pos logit contributions | |
hands | +0.012 |
sle | +0.012 |
paws | +0.011 |
fingers | +0.010 |
apr | +0.010 |
Neg logit contributions | |
ained | -0.023 |
Ag | -0.020 |
THE | -0.020 |
ust | -0.020 |
ectar | -0.020 |
Token | frog |
Token ID | 21264 |
Feature activation | +1.56e-02 |
Pos logit contributions | |
ained | +0.015 |
Ag | +0.013 |
THE | +0.013 |
ust | +0.013 |
ectar | +0.013 |
Neg logit contributions | |
hands | -0.012 |
sle | -0.012 |
paws | -0.011 |
fingers | -0.011 |
pans | -0.010 |
Token | again |
Token ID | 757 |
Feature activation | +3.60e-02 |
Pos logit contributions | |
ained | +0.036 |
Ag | +0.032 |
Prin | +0.031 |
Kay | +0.030 |
Fighting | +0.030 |
Neg logit contributions | |
hands | -0.018 |
sle | -0.016 |
paws | -0.016 |
cub | -0.014 |
nose | -0.014 |
Token | for |
Token ID | 329 |
Feature activation | +4.85e-02 |
Pos logit contributions | |
ained | +0.091 |
Ag | +0.080 |
Prin | +0.078 |
ount | +0.078 |
fault | +0.078 |
Neg logit contributions | |
hands | -0.035 |
paws | -0.030 |
fingers | -0.028 |
Daddy | -0.028 |
sle | -0.028 |
Token | such |
Token ID | 884 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
ained | +0.098 |
ust | +0.090 |
perspective | +0.086 |
ount | +0.085 |
Ag | +0.085 |
Neg logit contributions | |
hands | -0.060 |
sle | -0.058 |
paws | -0.053 |
Daddy | -0.050 |
help | -0.049 |
Token | an |
Token ID | 281 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
ained | +0.240 |
inas | +0.228 |
ount | +0.227 |
ill | +0.224 |
ub | +0.224 |
Neg logit contributions | |
hands | -0.047 |
paws | -0.037 |
help | -0.028 |
apr | -0.026 |
fingers | -0.026 |
Token | amazing |
Token ID | 4998 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
ained | +0.038 |
ust | +0.035 |
THE | +0.035 |
ectar | +0.032 |
Ag | +0.032 |
Neg logit contributions | |
hands | -0.041 |
sle | -0.040 |
pans | -0.039 |
paws | -0.039 |
fingers | -0.037 |
Token | experience |
Token ID | 1998 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
ained | +0.049 |
perspective | +0.043 |
THE | +0.043 |
Ag | +0.042 |
ectar | +0.042 |
Neg logit contributions | |
hands | -0.052 |
sle | -0.052 |
pans | -0.050 |
paws | -0.049 |
forks | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
ained | +0.070 |
Prin | +0.063 |
Ag | +0.060 |
inas | +0.059 |
ust | +0.059 |
Neg logit contributions | |
hands | -0.026 |
sle | -0.021 |
Daddy | -0.020 |
paws | -0.020 |
fingers | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
ained | +0.032 |
ust | +0.028 |
Ag | +0.028 |
Prin | +0.028 |
perspective | +0.028 |
Neg logit contributions | |
hands | -0.024 |
sle | -0.023 |
paws | -0.022 |
Daddy | -0.021 |
fingers | -0.020 |
Token | of |
Token ID | 286 |
Feature activation | +3.41e-02 |
Pos logit contributions | |
ained | +0.045 |
Prin | +0.039 |
ust | +0.037 |
Ag | +0.037 |
Kay | +0.037 |
Neg logit contributions | |
hands | -0.032 |
paws | -0.030 |
Daddy | -0.028 |
sle | -0.028 |
fingers | -0.027 |
Token | himself |
Token ID | 2241 |
Feature activation | -2.06e-03 |
Pos logit contributions | |
ained | +0.074 |
Prin | +0.067 |
perspective | +0.066 |
ectar | +0.066 |
ust | +0.065 |
Neg logit contributions | |
hands | -0.039 |
paws | -0.034 |
Daddy | -0.033 |
sle | -0.032 |
fingers | -0.030 |
Token | for |
Token ID | 329 |
Feature activation | +3.63e-02 |
Pos logit contributions | |
hands | +0.003 |
sle | +0.002 |
paws | +0.002 |
fingers | +0.002 |
Daddy | +0.002 |
Neg logit contributions | |
ained | -0.004 |
Ag | -0.004 |
Prin | -0.004 |
ectar | -0.004 |
Kay | -0.004 |
Token | going |
Token ID | 1016 |
Feature activation | -4.81e-03 |
Pos logit contributions | |
ained | +0.065 |
Prin | +0.056 |
ectar | +0.056 |
Ag | +0.056 |
THE | +0.055 |
Neg logit contributions | |
hands | -0.053 |
sle | -0.051 |
paws | -0.049 |
fingers | -0.046 |
apr | -0.046 |
Token | on |
Token ID | 319 |
Feature activation | +8.75e-03 |
Pos logit contributions | |
hands | +0.006 |
sle | +0.006 |
paws | +0.006 |
load | +0.005 |
fingers | +0.005 |
Neg logit contributions | |
ained | -0.009 |
Prin | -0.009 |
ectar | -0.009 |
ust | -0.009 |
ala | -0.008 |
Token | such |
Token ID | 884 |
Feature activation | +8.85e-02 |
Pos logit contributions | |
ained | +0.020 |
ectar | +0.019 |
ust | +0.019 |
Prin | +0.019 |
ala | +0.019 |
Neg logit contributions | |
hands | -0.008 |
sle | -0.008 |
paws | -0.007 |
apr | -0.006 |
Daddy | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +1.01e-02 |
Pos logit contributions | |
ained | +0.251 |
ount | +0.236 |
ectar | +0.233 |
inas | +0.231 |
ill | +0.230 |
Neg logit contributions | |
hands | -0.037 |
paws | -0.028 |
sle | -0.022 |
little | -0.021 |
Daddy | -0.021 |
Token | big |
Token ID | 1263 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
ained | +0.018 |
Ag | +0.016 |
THE | +0.016 |
ust | +0.016 |
Prin | +0.016 |
Neg logit contributions | |
hands | -0.014 |
sle | -0.014 |
paws | -0.013 |
fingers | -0.012 |
apr | -0.012 |
Token | journey |
Token ID | 7002 |
Feature activation | -5.29e-04 |
Pos logit contributions | |
perspective | +0.014 |
ained | +0.014 |
THE | +0.013 |
fault | +0.012 |
Ag | +0.012 |
Neg logit contributions | |
pans | -0.015 |
hands | -0.014 |
forks | -0.014 |
apr | -0.014 |
sle | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +4.53e-04 |
Pos logit contributions | |
hands | +0.001 |
sle | +0.001 |
paws | +0.000 |
load | +0.000 |
Daddy | +0.000 |
Neg logit contributions | |
ained | -0.001 |
ectar | -0.001 |
Prin | -0.001 |
Ag | -0.001 |
ust | -0.001 |
Token | helping |
Token ID | 5742 |
Feature activation | -1.34e-03 |
Pos logit contributions | |
ained | +0.001 |
ala | +0.001 |
ust | +0.001 |
Prin | +0.001 |
ount | +0.001 |
Neg logit contributions | |
hands | -0.001 |
paws | -0.001 |
Daddy | -0.000 |
sle | -0.000 |
help | -0.000 |
Token | congratulated |
Token ID | 47630 |
Feature activation | -1.75e-03 |
Pos logit contributions | |
ained | +0.018 |
ectar | +0.015 |
Ag | +0.015 |
fault | +0.015 |
perspective | +0.015 |
Neg logit contributions | |
hands | -0.010 |
sle | -0.009 |
paws | -0.009 |
Daddy | -0.009 |
fingers | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
hands | +0.002 |
sle | +0.001 |
paws | +0.001 |
Daddy | +0.001 |
fingers | +0.001 |
Neg logit contributions | |
ained | -0.004 |
ectar | -0.004 |
THE | -0.004 |
Prin | -0.004 |
Ag | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
sle | +0.017 |
hands | +0.017 |
paws | +0.016 |
apr | +0.015 |
fingers | +0.015 |
Neg logit contributions | |
ained | -0.019 |
Ag | -0.017 |
THE | -0.017 |
Prin | -0.017 |
Kay | -0.016 |
Token | boy |
Token ID | 2933 |
Feature activation | +6.79e-03 |
Pos logit contributions | |
hands | +0.022 |
sle | +0.021 |
paws | +0.020 |
fingers | +0.019 |
Daddy | +0.018 |
Neg logit contributions | |
ained | -0.035 |
ectar | -0.031 |
THE | -0.031 |
ust | -0.030 |
Prin | -0.030 |
Token | on |
Token ID | 319 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
ained | +0.014 |
Ag | +0.013 |
Prin | +0.013 |
perspective | +0.012 |
ust | +0.012 |
Neg logit contributions | |
hands | -0.009 |
sle | -0.008 |
paws | -0.008 |
fingers | -0.007 |
cub | -0.007 |
Token | such |
Token ID | 884 |
Feature activation | +8.72e-02 |
Pos logit contributions | |
ained | +0.028 |
ust | +0.025 |
ectar | +0.025 |
Prin | +0.025 |
Ag | +0.024 |
Neg logit contributions | |
hands | -0.013 |
sle | -0.012 |
paws | -0.011 |
Daddy | -0.010 |
apr | -0.010 |
Token | an |
Token ID | 281 |
Feature activation | +3.90e-03 |
Pos logit contributions | |
ained | +0.236 |
ectar | +0.218 |
ill | +0.215 |
ount | +0.213 |
inas | +0.213 |
Neg logit contributions | |
hands | -0.052 |
paws | -0.040 |
apr | -0.038 |
sle | -0.036 |
Daddy | -0.034 |
Token | important |
Token ID | 1593 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
ained | +0.006 |
THE | +0.005 |
ust | +0.005 |
Ag | +0.005 |
Kay | +0.005 |
Neg logit contributions | |
hands | -0.007 |
paws | -0.006 |
sle | -0.006 |
pans | -0.006 |
fingers | -0.006 |
Token | event |
Token ID | 1785 |
Feature activation | +3.75e-02 |
Pos logit contributions | |
ained | +0.068 |
ectar | +0.058 |
THE | +0.058 |
Ag | +0.058 |
Prin | +0.057 |
Neg logit contributions | |
hands | -0.048 |
sle | -0.047 |
paws | -0.043 |
fingers | -0.041 |
apr | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-03 |
Pos logit contributions | |
ained | +0.084 |
Prin | +0.077 |
ectar | +0.076 |
ust | +0.073 |
Ag | +0.072 |
Neg logit contributions | |
hands | -0.040 |
sle | -0.037 |
Daddy | -0.034 |
drive | -0.034 |
paws | -0.033 |
Token | He |
Token ID | 679 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
ained | +0.003 |
Ag | +0.002 |
THE | +0.002 |
ectar | +0.002 |
Prin | +0.002 |
Neg logit contributions | |
hands | -0.002 |
sle | -0.002 |
paws | -0.002 |
fingers | -0.002 |
apr | -0.002 |
Token | proud |
Token ID | 6613 |
Feature activation | +3.28e-02 |
Pos logit contributions | |
ained | +0.004 |
perspective | +0.004 |
THE | +0.004 |
ectar | +0.004 |
Ag | +0.004 |
Neg logit contributions | |
hands | -0.004 |
sle | -0.003 |
paws | -0.003 |
pans | -0.003 |
Daddy | -0.003 |
Token | of |
Token ID | 286 |
Feature activation | +3.80e-02 |
Pos logit contributions | |
ained | +0.066 |
Prin | +0.059 |
Ag | +0.057 |
Kay | +0.057 |
ount | +0.055 |
Neg logit contributions | |
hands | -0.046 |
paws | -0.041 |
Daddy | -0.040 |
sle | -0.039 |
fingers | -0.039 |
Token | himself |
Token ID | 2241 |
Feature activation | -1.11e-03 |
Pos logit contributions | |
ained | +0.087 |
Prin | +0.081 |
Ag | +0.079 |
ectar | +0.077 |
ount | +0.077 |
Neg logit contributions | |
hands | -0.039 |
paws | -0.033 |
Daddy | -0.032 |
sle | -0.030 |
forks | -0.029 |
Token | for |
Token ID | 329 |
Feature activation | +3.76e-02 |
Pos logit contributions | |
hands | +0.001 |
paws | +0.001 |
sle | +0.001 |
fingers | +0.001 |
Daddy | +0.001 |
Neg logit contributions | |
ained | -0.002 |
Ag | -0.002 |
Prin | -0.002 |
Kay | -0.002 |
ectar | -0.002 |
Token | doing |
Token ID | 1804 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
ained | +0.073 |
Ag | +0.064 |
THE | +0.064 |
ectar | +0.063 |
Prin | +0.063 |
Neg logit contributions | |
hands | -0.048 |
sle | -0.047 |
paws | -0.044 |
fingers | -0.041 |
apr | -0.041 |
Token | such |
Token ID | 884 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
ained | +0.115 |
ala | +0.107 |
ectar | +0.106 |
Ag | +0.103 |
Prin | +0.103 |
Neg logit contributions | |
hands | -0.054 |
paws | -0.044 |
Daddy | -0.044 |
apr | -0.043 |
sle | -0.041 |
Token | an |
Token ID | 281 |
Feature activation | +1.91e-02 |
Pos logit contributions | |
ained | +0.237 |
ount | +0.218 |
ill | +0.217 |
inas | +0.217 |
ala | +0.216 |
Neg logit contributions | |
hands | -0.047 |
paws | -0.038 |
Daddy | -0.032 |
help | -0.028 |
fingers | -0.027 |
Token | excellent |
Token ID | 6275 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
ained | +0.028 |
ust | +0.025 |
THE | +0.025 |
Ag | +0.024 |
perspective | +0.023 |
Neg logit contributions | |
hands | -0.033 |
sle | -0.033 |
paws | -0.032 |
fingers | -0.030 |
pans | -0.030 |
Token | job |
Token ID | 1693 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
ained | +0.066 |
THE | +0.057 |
Ag | +0.057 |
Prin | +0.056 |
perspective | +0.056 |
Neg logit contributions | |
hands | -0.055 |
sle | -0.055 |
paws | -0.051 |
apr | -0.048 |
fingers | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
ained | +0.044 |
Prin | +0.041 |
Ag | +0.039 |
Kay | +0.039 |
ectar | +0.038 |
Neg logit contributions | |
hands | -0.022 |
sle | -0.019 |
Daddy | -0.019 |
paws | -0.018 |
fingers | -0.018 |
Token | With |
Token ID | 2080 |
Feature activation | +7.72e-03 |
Pos logit contributions | |
ained | +0.011 |
Ag | +0.010 |
ectar | +0.010 |
ala | +0.010 |
Prin | +0.010 |
Neg logit contributions | |
hands | -0.007 |
paws | -0.006 |
Daddy | -0.006 |
sle | -0.006 |
fingers | -0.005 |
Token | heard |
Token ID | 2982 |
Feature activation | -9.80e-03 |
Pos logit contributions | |
sle | +0.000 |
hands | +0.000 |
paws | +0.000 |
apr | +0.000 |
fingers | +0.000 |
Neg logit contributions | |
ained | -0.000 |
Prin | -0.000 |
Ag | -0.000 |
THE | -0.000 |
ust | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +9.85e-03 |
Pos logit contributions | |
hands | +0.010 |
sle | +0.010 |
paws | +0.009 |
apr | +0.009 |
fingers | +0.009 |
Neg logit contributions | |
ained | -0.021 |
Prin | -0.018 |
THE | -0.018 |
Ag | -0.018 |
ectar | -0.018 |
Token | noise |
Token ID | 7838 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
ained | +0.018 |
Ag | +0.017 |
Prin | +0.017 |
THE | +0.017 |
ust | +0.017 |
Neg logit contributions | |
hands | -0.012 |
sle | -0.012 |
paws | -0.011 |
apr | -0.011 |
fingers | -0.010 |
Token | in |
Token ID | 287 |
Feature activation | -1.62e-02 |
Pos logit contributions | |
hands | +0.009 |
sle | +0.009 |
paws | +0.009 |
apr | +0.008 |
fingers | +0.008 |
Neg logit contributions | |
ained | -0.010 |
Ag | -0.009 |
THE | -0.008 |
ectar | -0.008 |
Prin | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
hands | +0.020 |
sle | +0.020 |
paws | +0.019 |
apr | +0.018 |
fingers | +0.018 |
Neg logit contributions | |
ained | -0.030 |
THE | -0.027 |
perspective | -0.026 |
Kay | -0.026 |
Ag | -0.026 |
Token | tre |
Token ID | 2054 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
ained | +0.035 |
THE | +0.032 |
Prin | +0.032 |
perspective | +0.030 |
Ag | +0.029 |
Neg logit contributions | |
hands | -0.033 |
sle | -0.032 |
paws | -0.030 |
apr | -0.030 |
fingers | -0.030 |
Token | et |
Token ID | 316 |
Feature activation | +8.88e-03 |
Pos logit contributions | |
ained | +0.141 |
Ag | +0.135 |
THE | +0.130 |
ectar | +0.128 |
Prin | +0.127 |
Neg logit contributions | |
hands | -0.120 |
sle | -0.118 |
paws | -0.110 |
apr | -0.109 |
fingers | -0.106 |
Token | ops |
Token ID | 2840 |
Feature activation | +6.52e-03 |
Pos logit contributions | |
Ag | +0.018 |
ained | +0.018 |
ectar | +0.017 |
ust | +0.017 |
Kay | +0.017 |
Neg logit contributions | |
hands | -0.010 |
sle | -0.010 |
paws | -0.010 |
nose | -0.009 |
cub | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -9.06e-03 |
Pos logit contributions | |
ained | +0.013 |
Ag | +0.012 |
Kay | +0.012 |
Prin | +0.012 |
known | +0.011 |
Neg logit contributions | |
hands | -0.008 |
sle | -0.008 |
paws | -0.007 |
fingers | -0.007 |
nose | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | -1.77e-03 |
Pos logit contributions | |
sle | +0.014 |
hands | +0.014 |
paws | +0.013 |
apr | +0.013 |
pans | +0.013 |
Neg logit contributions | |
ained | -0.014 |
Prin | -0.012 |
Ag | -0.012 |
ectar | -0.012 |
THE | -0.012 |
Token | looked |
Token ID | 3114 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
apr | +0.003 |
hands | +0.003 |
sle | +0.003 |
plates | +0.002 |
forks | +0.002 |
Neg logit contributions | |
Prin | -0.003 |
ained | -0.003 |
ust | -0.002 |
Ag | -0.002 |
Kay | -0.002 |
Token | he |
Token ID | 339 |
Feature activation | +5.44e-03 |
Pos logit contributions | |
ained | +0.032 |
Ag | +0.028 |
THE | +0.028 |
Prin | +0.028 |
ectar | +0.028 |
Neg logit contributions | |
hands | -0.020 |
sle | -0.019 |
paws | -0.018 |
fingers | -0.017 |
apr | -0.016 |
Token | had |
Token ID | 550 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
ained | +0.009 |
Ag | +0.008 |
THE | +0.008 |
Prin | +0.008 |
ust | +0.008 |
Neg logit contributions | |
hands | -0.008 |
sle | -0.008 |
paws | -0.007 |
fingers | -0.007 |
apr | -0.007 |
Token | never |
Token ID | 1239 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
ained | +0.042 |
ectar | +0.038 |
Prin | +0.037 |
inas | +0.037 |
ust | +0.036 |
Neg logit contributions | |
hands | -0.021 |
paws | -0.017 |
sle | -0.017 |
fingers | -0.015 |
white | -0.015 |
Token | gone |
Token ID | 3750 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
ained | +0.033 |
THE | +0.030 |
Ag | +0.030 |
ectar | +0.030 |
Kay | +0.029 |
Neg logit contributions | |
hands | -0.027 |
paws | -0.025 |
sle | -0.024 |
fingers | -0.024 |
load | -0.022 |
Token | on |
Token ID | 319 |
Feature activation | +8.79e-03 |
Pos logit contributions | |
ained | +0.037 |
Prin | +0.036 |
ulture | +0.036 |
Ag | +0.035 |
ust | +0.034 |
Neg logit contributions | |
hands | -0.019 |
sle | -0.017 |
paws | -0.017 |
eyes | -0.015 |
brown | -0.015 |
Token | such |
Token ID | 884 |
Feature activation | +8.46e-02 |
Pos logit contributions | |
ained | +0.020 |
ust | +0.019 |
ectar | +0.019 |
Ag | +0.018 |
THE | +0.018 |
Neg logit contributions | |
hands | -0.008 |
sle | -0.008 |
paws | -0.007 |
fingers | -0.007 |
plates | -0.006 |
Token | an |
Token ID | 281 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
ained | +0.228 |
ectar | +0.211 |
inas | +0.207 |
ount | +0.205 |
ying | +0.203 |
Neg logit contributions | |
hands | -0.059 |
paws | -0.048 |
fingers | -0.042 |
sle | -0.040 |
apr | -0.035 |
Token | adventure |
Token ID | 8855 |
Feature activation | -1.05e-04 |
Pos logit contributions | |
ained | +0.030 |
ust | +0.027 |
THE | +0.027 |
perspective | +0.027 |
Ag | +0.026 |
Neg logit contributions | |
hands | -0.025 |
paws | -0.023 |
pans | -0.023 |
sle | -0.023 |
apr | -0.022 |
Token | before |
Token ID | 878 |
Feature activation | +7.01e-03 |
Pos logit contributions | |
hands | +0.000 |
sle | +0.000 |
paws | +0.000 |
Daddy | +0.000 |
load | +0.000 |
Neg logit contributions | |
ained | -0.000 |
Ag | -0.000 |
Prin | -0.000 |
Kay | -0.000 |
ectar | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +4.74e-03 |
Pos logit contributions | |
ained | +0.013 |
Prin | +0.011 |
ust | +0.011 |
Ag | +0.011 |
ectar | +0.011 |
Neg logit contributions | |
hands | -0.010 |
sle | -0.010 |
paws | -0.009 |
fingers | -0.009 |
Daddy | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +4.25e-03 |
Pos logit contributions | |
ained | +0.007 |
THE | +0.006 |
Ag | +0.006 |
ectar | +0.006 |
Prin | +0.006 |
Neg logit contributions | |
sle | -0.008 |
hands | -0.008 |
pans | -0.007 |
paws | -0.007 |
fingers | -0.007 |
Token | boy |
Token ID | 2933 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
hands | +0.000 |
sle | +0.000 |
paws | +0.000 |
apr | +0.000 |
fingers | +0.000 |
Neg logit contributions | |
ained | -0.000 |
THE | -0.000 |
Prin | -0.000 |
perspective | -0.000 |
ectar | -0.000 |
Token | thanked |
Token ID | 26280 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
ained | +0.029 |
Ag | +0.025 |
ectar | +0.024 |
THE | +0.024 |
Prin | +0.024 |
Neg logit contributions | |
hands | -0.021 |
sle | -0.020 |
paws | -0.020 |
fingers | -0.018 |
apr | -0.018 |
Token | his |
Token ID | 465 |
Feature activation | +6.74e-04 |
Pos logit contributions | |
hands | +0.021 |
sle | +0.020 |
paws | +0.019 |
fingers | +0.018 |
pans | +0.018 |
Neg logit contributions | |
ained | -0.030 |
THE | -0.028 |
Prin | -0.027 |
Ag | -0.027 |
Kay | -0.027 |
Token | companion |
Token ID | 15185 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
ained | +0.001 |
THE | +0.001 |
fault | +0.001 |
Kay | +0.001 |
perspective | +0.001 |
Neg logit contributions | |
hands | -0.001 |
sle | -0.001 |
forks | -0.001 |
pans | -0.001 |
Daddy | -0.001 |
Token | for |
Token ID | 329 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
hands | +0.020 |
sle | +0.019 |
paws | +0.018 |
fingers | +0.017 |
Daddy | +0.016 |
Neg logit contributions | |
ained | -0.033 |
Ag | -0.029 |
ectar | -0.028 |
Prin | -0.028 |
ust | -0.028 |
Token | such |
Token ID | 884 |
Feature activation | +8.43e-02 |
Pos logit contributions | |
ained | +0.071 |
ust | +0.063 |
Ag | +0.062 |
Prin | +0.062 |
ectar | +0.061 |
Neg logit contributions | |
hands | -0.042 |
sle | -0.041 |
paws | -0.037 |
apr | -0.034 |
Daddy | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
ained | +0.222 |
inas | +0.203 |
ount | +0.202 |
ala | +0.200 |
ectar | +0.199 |
Neg logit contributions | |
hands | -0.052 |
paws | -0.044 |
sle | -0.043 |
Daddy | -0.034 |
apr | -0.033 |
Token | great |
Token ID | 1049 |
Feature activation | +3.82e-02 |
Pos logit contributions | |
ained | +0.021 |
THE | +0.019 |
Ag | +0.019 |
ectar | +0.019 |
ust | +0.019 |
Neg logit contributions | |
hands | -0.016 |
sle | -0.015 |
paws | -0.014 |
fingers | -0.014 |
apr | -0.014 |
Token | search |
Token ID | 2989 |
Feature activation | -4.41e-03 |
Pos logit contributions | |
ained | +0.073 |
Ag | +0.064 |
THE | +0.063 |
ectar | +0.063 |
Prin | +0.063 |
Neg logit contributions | |
hands | -0.050 |
sle | -0.049 |
paws | -0.046 |
fingers | -0.043 |
apr | -0.043 |
Token | as |
Token ID | 355 |
Feature activation | -5.47e-03 |
Pos logit contributions | |
hands | +0.006 |
sle | +0.006 |
paws | +0.005 |
Daddy | +0.005 |
fingers | +0.005 |
Neg logit contributions | |
ained | -0.009 |
Prin | -0.008 |
Ag | -0.008 |
Kay | -0.007 |
ectar | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | +3.86e-03 |
Pos logit contributions | |
hands | +0.007 |
sle | +0.007 |
paws | +0.006 |
fingers | +0.006 |
apr | +0.006 |
Neg logit contributions | |
ained | -0.011 |
Ag | -0.009 |
THE | -0.009 |
Prin | -0.009 |
ectar | -0.009 |
Token | been |
Token ID | 587 |
Feature activation | +1.16e-02 |
Pos logit contributions | |
ained | +0.064 |
ectar | +0.057 |
ala | +0.055 |
perspective | +0.055 |
ust | +0.055 |
Neg logit contributions | |
hands | -0.058 |
paws | -0.053 |
sle | -0.051 |
apr | -0.050 |
fingers | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
ained | +0.020 |
perspective | +0.018 |
ust | +0.018 |
ectar | +0.018 |
Prin | +0.017 |
Neg logit contributions | |
hands | -0.017 |
paws | -0.016 |
sle | -0.015 |
apr | -0.014 |
pans | -0.014 |
Token | one |
Token ID | 530 |
Feature activation | -5.14e-04 |
Pos logit contributions | |
ained | +0.066 |
ectar | +0.059 |
Ag | +0.058 |
ala | +0.057 |
Prin | +0.057 |
Neg logit contributions | |
hands | -0.038 |
sle | -0.036 |
paws | -0.034 |
fingers | -0.031 |
Daddy | -0.031 |
Token | to |
Token ID | 284 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
hands | +0.001 |
paws | +0.001 |
sle | +0.001 |
fingers | +0.001 |
Daddy | +0.001 |
Neg logit contributions | |
ained | -0.001 |
Ag | -0.001 |
Prin | -0.001 |
Kay | -0.001 |
ount | -0.001 |
Token | start |
Token ID | 923 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
ained | +0.025 |
ectar | +0.022 |
ust | +0.022 |
Prin | +0.022 |
ala | +0.022 |
Neg logit contributions | |
hands | -0.010 |
help | -0.009 |
paws | -0.009 |
load | -0.009 |
drive | -0.008 |
Token | such |
Token ID | 884 |
Feature activation | +8.39e-02 |
Pos logit contributions | |
ained | +0.028 |
Prin | +0.027 |
Ag | +0.027 |
ount | +0.026 |
Acc | +0.026 |
Neg logit contributions | |
hands | -0.015 |
paws | -0.012 |
fingers | -0.010 |
Daddy | -0.010 |
load | -0.010 |
Token | an |
Token ID | 281 |
Feature activation | +1.69e-02 |
Pos logit contributions | |
ained | +0.239 |
ount | +0.230 |
inas | +0.228 |
ala | +0.225 |
ill | +0.224 |
Neg logit contributions | |
hands | -0.033 |
paws | -0.018 |
help | -0.018 |
Daddy | -0.014 |
little | -0.013 |
Token | awesome |
Token ID | 7427 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
ained | +0.029 |
THE | +0.025 |
ust | +0.025 |
Ag | +0.025 |
ectar | +0.024 |
Neg logit contributions | |
hands | -0.025 |
sle | -0.025 |
paws | -0.024 |
fingers | -0.023 |
pans | -0.022 |
Token | game |
Token ID | 983 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
ained | +0.042 |
Ag | +0.036 |
ectar | +0.036 |
Prin | +0.036 |
THE | +0.036 |
Neg logit contributions | |
hands | -0.034 |
sle | -0.033 |
paws | -0.032 |
fingers | -0.029 |
apr | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +6.78e-03 |
Pos logit contributions | |
ained | +0.063 |
Prin | +0.060 |
Acc | +0.057 |
Kay | +0.056 |
ust | +0.055 |
Neg logit contributions | |
hands | -0.025 |
paws | -0.020 |
Daddy | -0.020 |
help | -0.019 |
sle | -0.018 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
ained | +0.013 |
ust | +0.012 |
Ag | +0.011 |
perspective | +0.011 |
Prin | +0.011 |
Neg logit contributions | |
hands | -0.009 |
sle | -0.008 |
paws | -0.008 |
Daddy | -0.008 |
fingers | -0.007 |
Token | proud |
Token ID | 6613 |
Feature activation | +2.39e-02 |
Pos logit contributions | |
ained | +0.001 |
ulture | +0.001 |
ectar | +0.001 |
Prin | +0.001 |
perspective | +0.001 |
Neg logit contributions | |
hands | -0.001 |
paws | -0.001 |
white | -0.001 |
brown | -0.001 |
load | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
ained | +0.052 |
Prin | +0.046 |
Ag | +0.044 |
ount | +0.044 |
Kay | +0.044 |
Neg logit contributions | |
hands | -0.030 |
paws | -0.028 |
Daddy | -0.026 |
fingers | -0.026 |
eyes | -0.025 |
Token | herself |
Token ID | 5223 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ained | +0.069 |
ount | +0.062 |
Prin | +0.061 |
Ag | +0.059 |
ust | +0.059 |
Neg logit contributions | |
hands | -0.062 |
Daddy | -0.054 |
paws | -0.054 |
help | -0.054 |
fingers | -0.053 |
Token | for |
Token ID | 329 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
ained | +0.027 |
Prin | +0.025 |
Ag | +0.024 |
Kay | +0.024 |
ount | +0.024 |
Neg logit contributions | |
hands | -0.011 |
paws | -0.009 |
sle | -0.008 |
fingers | -0.008 |
Daddy | -0.008 |
Token | doing |
Token ID | 1804 |
Feature activation | +4.79e-02 |
Pos logit contributions | |
ained | +0.066 |
ectar | +0.058 |
Prin | +0.057 |
ount | +0.057 |
ust | +0.057 |
Neg logit contributions | |
hands | -0.046 |
paws | -0.041 |
sle | -0.040 |
fingers | -0.039 |
apr | -0.038 |
Token | such |
Token ID | 884 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
ained | +0.114 |
ount | +0.106 |
ectar | +0.106 |
ulture | +0.103 |
ust | +0.102 |
Neg logit contributions | |
hands | -0.049 |
paws | -0.038 |
Daddy | -0.036 |
eyes | -0.036 |
fingers | -0.036 |
Token | a |
Token ID | 257 |
Feature activation | +7.36e-03 |
Pos logit contributions | |
ained | +0.253 |
ount | +0.241 |
ill | +0.234 |
inas | +0.232 |
ub | +0.231 |
Neg logit contributions | |
hands | -0.030 |
paws | -0.022 |
little | -0.015 |
help | -0.013 |
three | -0.011 |
Token | big |
Token ID | 1263 |
Feature activation | +7.08e-03 |
Pos logit contributions | |
ained | +0.016 |
ectar | +0.014 |
ala | +0.013 |
ount | +0.013 |
Ag | +0.013 |
Neg logit contributions | |
hands | -0.008 |
sle | -0.008 |
paws | -0.008 |
pans | -0.007 |
apr | -0.007 |
Token | task |
Token ID | 4876 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
ained | +0.011 |
perspective | +0.010 |
THE | +0.010 |
fault | +0.010 |
Ag | +0.010 |
Neg logit contributions | |
sle | -0.010 |
hands | -0.010 |
paws | -0.010 |
pans | -0.009 |
fingers | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
ained | +0.076 |
Acc | +0.070 |
Prin | +0.069 |
ectar | +0.068 |
Ag | +0.068 |
Neg logit contributions | |
hands | -0.025 |
Daddy | -0.022 |
help | -0.021 |
paws | -0.021 |
plates | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +9.01e-03 |
Pos logit contributions | |
ained | +0.018 |
ust | +0.017 |
Ag | +0.017 |
ier | +0.016 |
ectar | +0.016 |
Neg logit contributions | |
hands | -0.013 |
paws | -0.012 |
Daddy | -0.011 |
sle | -0.011 |
fingers | -0.010 |
Token | good |
Token ID | 922 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
ained | +0.029 |
ala | +0.025 |
Prin | +0.025 |
ectar | +0.025 |
perspective | +0.025 |
Neg logit contributions | |
hands | -0.021 |
paws | -0.019 |
sle | -0.018 |
Daddy | -0.018 |
fingers | -0.018 |
Token | about |
Token ID | 546 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
ained | +0.089 |
Prin | +0.084 |
Kay | +0.079 |
ust | +0.078 |
ectar | +0.077 |
Neg logit contributions | |
hands | -0.051 |
paws | -0.045 |
sle | -0.045 |
Daddy | -0.043 |
fingers | -0.042 |
Token | himself |
Token ID | 2241 |
Feature activation | -2.14e-03 |
Pos logit contributions | |
ained | +0.061 |
Prin | +0.054 |
ectar | +0.052 |
THE | +0.052 |
ust | +0.052 |
Neg logit contributions | |
hands | -0.036 |
sle | -0.033 |
paws | -0.031 |
Daddy | -0.031 |
fingers | -0.030 |
Token | for |
Token ID | 329 |
Feature activation | +3.39e-02 |
Pos logit contributions | |
hands | +0.002 |
paws | +0.002 |
sle | +0.002 |
fingers | +0.002 |
Daddy | +0.002 |
Neg logit contributions | |
ained | -0.005 |
Prin | -0.004 |
Ag | -0.004 |
Kay | -0.004 |
ectar | -0.004 |
Token | mastering |
Token ID | 45116 |
Feature activation | +5.10e-02 |
Pos logit contributions | |
ained | +0.065 |
Prin | +0.056 |
ust | +0.056 |
Ag | +0.056 |
ectar | +0.056 |
Neg logit contributions | |
hands | -0.047 |
sle | -0.044 |
paws | -0.042 |
fingers | -0.040 |
Daddy | -0.040 |
Token | such |
Token ID | 884 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
ained | +0.111 |
Prin | +0.100 |
ectar | +0.099 |
THE | +0.099 |
ust | +0.098 |
Neg logit contributions | |
hands | -0.055 |
sle | -0.051 |
paws | -0.048 |
fingers | -0.045 |
Daddy | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | +6.87e-03 |
Pos logit contributions | |
ained | +0.248 |
ount | +0.243 |
ectar | +0.232 |
ulture | +0.231 |
ying | +0.230 |
Neg logit contributions | |
hands | -0.032 |
paws | -0.023 |
little | -0.020 |
white | -0.015 |
three | -0.013 |
Token | difficult |
Token ID | 2408 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
ained | +0.013 |
Ag | +0.011 |
ectar | +0.011 |
THE | +0.011 |
Prin | +0.011 |
Neg logit contributions | |
hands | -0.009 |
sle | -0.009 |
paws | -0.008 |
fingers | -0.008 |
apr | -0.008 |
Token | thing |
Token ID | 1517 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
ained | +0.057 |
Ag | +0.050 |
THE | +0.050 |
ectar | +0.049 |
Prin | +0.049 |
Neg logit contributions | |
hands | -0.046 |
sle | -0.045 |
paws | -0.043 |
fingers | -0.040 |
apr | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -2.06e-03 |
Pos logit contributions | |
ained | +0.067 |
Prin | +0.061 |
Ag | +0.059 |
Kay | +0.058 |
ectar | +0.057 |
Neg logit contributions | |
hands | -0.034 |
sle | -0.032 |
paws | -0.030 |
Daddy | -0.029 |
fingers | -0.028 |
Token | Even |
Token ID | 3412 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
sle | +0.003 |
hands | +0.003 |
paws | +0.003 |
apr | +0.003 |
pans | +0.003 |
Neg logit contributions | |
ained | -0.003 |
THE | -0.003 |
Ag | -0.003 |
ectar | -0.003 |
ust | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +3.60e-03 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.011 |
paws | +0.010 |
apr | +0.009 |
fingers | +0.009 |
Neg logit contributions | |
ained | -0.022 |
Ag | -0.020 |
THE | -0.020 |
ectar | -0.020 |
Prin | -0.020 |
Token | place |
Token ID | 1295 |
Feature activation | +1.66e-02 |
Pos logit contributions | |
ained | +0.007 |
THE | +0.006 |
ectar | +0.006 |
Prin | +0.006 |
Ag | +0.006 |
Neg logit contributions | |
hands | -0.004 |
sle | -0.004 |
paws | -0.004 |
apr | -0.004 |
fingers | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
ained | +0.032 |
Ag | +0.030 |
Prin | +0.030 |
Kay | +0.029 |
ust | +0.028 |
Neg logit contributions | |
hands | -0.022 |
sle | -0.021 |
paws | -0.019 |
Daddy | -0.018 |
fingers | -0.018 |
Token | rest |
Token ID | 1334 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
ained | +0.043 |
Ag | +0.038 |
THE | +0.037 |
ust | +0.037 |
Prin | +0.037 |
Neg logit contributions | |
hands | -0.024 |
sle | -0.023 |
paws | -0.022 |
fingers | -0.020 |
apr | -0.020 |
Token | on |
Token ID | 319 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
Ag | +0.035 |
ained | +0.035 |
Kay | +0.034 |
Prin | +0.033 |
ount | +0.032 |
Neg logit contributions | |
hands | -0.021 |
sle | -0.018 |
paws | -0.018 |
Daddy | -0.017 |
pans | -0.017 |
Token | such |
Token ID | 884 |
Feature activation | +8.36e-02 |
Pos logit contributions | |
ained | +0.024 |
THE | +0.021 |
Ag | +0.021 |
ectar | +0.021 |
Prin | +0.021 |
Neg logit contributions | |
hands | -0.014 |
sle | -0.013 |
paws | -0.013 |
fingers | -0.012 |
apr | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
ained | +0.221 |
inas | +0.205 |
ount | +0.203 |
ying | +0.201 |
Ag | +0.199 |
Neg logit contributions | |
hands | -0.052 |
paws | -0.045 |
sle | -0.044 |
fingers | -0.034 |
fiery | -0.033 |
Token | hot |
Token ID | 3024 |
Feature activation | +1.02e-03 |
Pos logit contributions | |
ained | +0.027 |
THE | +0.024 |
Ag | +0.024 |
Prin | +0.024 |
ectar | +0.024 |
Neg logit contributions | |
hands | -0.018 |
sle | -0.017 |
paws | -0.017 |
apr | -0.016 |
fingers | -0.016 |
Token | summer |
Token ID | 3931 |
Feature activation | +1.38e-03 |
Pos logit contributions | |
ained | +0.001 |
perspective | +0.001 |
THE | +0.001 |
ectar | +0.001 |
pour | +0.001 |
Neg logit contributions | |
hands | -0.002 |
sle | -0.002 |
apr | -0.002 |
forks | -0.002 |
paws | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | +7.68e-03 |
Pos logit contributions | |
ained | +0.002 |
THE | +0.002 |
ectar | +0.002 |
Prin | +0.002 |
Ag | +0.002 |
Neg logit contributions | |
hands | -0.002 |
sle | -0.002 |
paws | -0.002 |
fingers | -0.002 |
apr | -0.002 |
Token | ." |
Token ID | 526 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
ained | +0.014 |
Ag | +0.013 |
Kay | +0.013 |
THE | +0.013 |
Prin | +0.013 |
Neg logit contributions | |
hands | -0.010 |
sle | -0.010 |
paws | -0.009 |
fingers | -0.009 |
Daddy | -0.009 |
Token | why |
Token ID | 1521 |
Feature activation | +6.27e-03 |
Pos logit contributions | |
hands | +0.051 |
sle | +0.048 |
paws | +0.046 |
Daddy | +0.044 |
fingers | +0.044 |
Neg logit contributions | |
ained | -0.065 |
Ag | -0.056 |
THE | -0.056 |
Prin | -0.056 |
ectar | -0.055 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ained | +0.012 |
Prin | +0.012 |
perspective | +0.011 |
Ag | +0.011 |
ust | +0.011 |
Neg logit contributions | |
hands | -0.008 |
Daddy | -0.008 |
Dad | -0.007 |
Mom | -0.007 |
paws | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
hands | +0.017 |
sle | +0.016 |
paws | +0.015 |
load | +0.015 |
Daddy | +0.014 |
Neg logit contributions | |
ained | -0.030 |
Ag | -0.028 |
ectar | -0.028 |
perspective | -0.028 |
THE | -0.027 |
Token | Jen |
Token ID | 13364 |
Feature activation | -1.95e-03 |
Pos logit contributions | |
hands | +0.053 |
sle | +0.050 |
paws | +0.049 |
fingers | +0.048 |
apr | +0.047 |
Neg logit contributions | |
ained | -0.039 |
THE | -0.032 |
Prin | -0.032 |
Ag | -0.032 |
ectar | -0.032 |
Token | did |
Token ID | 750 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
hands | +0.003 |
paws | +0.002 |
sle | +0.002 |
cheeks | +0.002 |
fingers | +0.002 |
Neg logit contributions | |
ained | -0.004 |
Ag | -0.003 |
ectar | -0.003 |
THE | -0.003 |
perspective | -0.003 |
Token | such |
Token ID | 884 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
ained | +0.059 |
ectar | +0.055 |
Prin | +0.053 |
perspective | +0.053 |
Ag | +0.052 |
Neg logit contributions | |
hands | -0.039 |
help | -0.035 |
Daddy | -0.034 |
load | -0.033 |
paws | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ained | +0.182 |
Ag | +0.161 |
THE | +0.161 |
ectar | +0.160 |
Prin | +0.159 |
Neg logit contributions | |
hands | -0.086 |
sle | -0.085 |
paws | -0.078 |
fingers | -0.072 |
apr | -0.071 |
Token | silly |
Token ID | 14397 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
ained | +0.034 |
Ag | +0.029 |
THE | +0.029 |
ectar | +0.029 |
Prin | +0.028 |
Neg logit contributions | |
hands | -0.030 |
sle | -0.030 |
paws | -0.028 |
fingers | -0.027 |
apr | -0.027 |
Token | thing |
Token ID | 1517 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ained | +0.038 |
Prin | +0.035 |
THE | +0.034 |
Ag | +0.034 |
ectar | +0.033 |
Neg logit contributions | |
hands | -0.032 |
sle | -0.030 |
paws | -0.029 |
fingers | -0.027 |
cheeks | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
ained | +0.037 |
Prin | +0.035 |
perspective | +0.035 |
Kay | +0.035 |
Ag | +0.035 |
Neg logit contributions | |
hands | -0.015 |
sle | -0.014 |
Daddy | -0.014 |
plates | -0.013 |
forks | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-03 |
Pos logit contributions | |
ained | +0.015 |
perspective | +0.014 |
THE | +0.013 |
ust | +0.013 |
ectar | +0.013 |
Neg logit contributions | |
hands | -0.008 |
Daddy | -0.008 |
Dad | -0.008 |
paws | -0.007 |
sle | -0.007 |
Token | thanked |
Token ID | 26280 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
ained | +0.024 |
perspective | +0.021 |
ectar | +0.021 |
ust | +0.020 |
Prin | +0.020 |
Neg logit contributions | |
hands | -0.015 |
sle | -0.014 |
paws | -0.014 |
Daddy | -0.012 |
fingers | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | -3.33e-03 |
Pos logit contributions | |
hands | +0.035 |
sle | +0.033 |
Daddy | +0.033 |
paws | +0.031 |
fingers | +0.030 |
Neg logit contributions | |
ained | -0.049 |
ust | -0.040 |
Ag | -0.040 |
ectar | -0.040 |
THE | -0.039 |
Token | for |
Token ID | 329 |
Feature activation | +3.44e-02 |
Pos logit contributions | |
hands | +0.004 |
sle | +0.004 |
Daddy | +0.004 |
paws | +0.004 |
fingers | +0.003 |
Neg logit contributions | |
ained | -0.008 |
Ag | -0.007 |
Prin | -0.006 |
perspective | -0.006 |
Kay | -0.006 |
Token | going |
Token ID | 1016 |
Feature activation | -6.30e-03 |
Pos logit contributions | |
ained | +0.073 |
ust | +0.064 |
perspective | +0.062 |
ectar | +0.061 |
Prin | +0.061 |
Neg logit contributions | |
hands | -0.043 |
sle | -0.039 |
Daddy | -0.036 |
paws | -0.036 |
help | -0.035 |
Token | on |
Token ID | 319 |
Feature activation | +6.45e-03 |
Pos logit contributions | |
hands | +0.008 |
sle | +0.007 |
paws | +0.007 |
load | +0.006 |
front | +0.006 |
Neg logit contributions | |
ained | -0.013 |
ust | -0.012 |
Prin | -0.012 |
ectar | -0.012 |
perspective | -0.012 |
Token | such |
Token ID | 884 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
ained | +0.015 |
ust | +0.014 |
ub | +0.013 |
itates | +0.013 |
ying | +0.013 |
Neg logit contributions | |
hands | -0.007 |
Daddy | -0.006 |
sle | -0.006 |
paws | -0.006 |
front | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +2.09e-03 |
Pos logit contributions | |
ained | +0.249 |
ount | +0.233 |
inas | +0.228 |
ectar | +0.228 |
ub | +0.226 |
Neg logit contributions | |
hands | -0.031 |
paws | -0.018 |
little | -0.018 |
white | -0.015 |
Daddy | -0.015 |
Token | wonderful |
Token ID | 7932 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
ained | +0.004 |
Ag | +0.004 |
THE | +0.004 |
ectar | +0.004 |
Prin | +0.004 |
Neg logit contributions | |
hands | -0.002 |
sle | -0.002 |
paws | -0.002 |
fingers | -0.002 |
apr | -0.002 |
Token | adventure |
Token ID | 8855 |
Feature activation | -7.81e-03 |
Pos logit contributions | |
ained | +0.029 |
Ag | +0.025 |
THE | +0.025 |
ust | +0.025 |
ectar | +0.025 |
Neg logit contributions | |
hands | -0.021 |
sle | -0.020 |
paws | -0.019 |
fingers | -0.018 |
apr | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -7.48e-04 |
Pos logit contributions | |
hands | +0.009 |
sle | +0.008 |
paws | +0.007 |
Daddy | +0.007 |
fingers | +0.007 |
Neg logit contributions | |
ained | -0.017 |
Prin | -0.015 |
Ag | -0.015 |
ectar | -0.015 |
ust | -0.014 |
Token | The |
Token ID | 383 |
Feature activation | -8.08e-03 |
Pos logit contributions | |
hands | +0.001 |
paws | +0.001 |
Daddy | +0.001 |
sle | +0.001 |
fingers | +0.001 |
Neg logit contributions | |
ained | -0.002 |
ust | -0.001 |
ier | -0.001 |
Ag | -0.001 |
perspective | -0.001 |
Token | an |
Token ID | 281 |
Feature activation | +3.32e-03 |
Pos logit contributions | |
sle | +0.011 |
hands | +0.011 |
paws | +0.010 |
fingers | +0.010 |
pans | +0.010 |
Neg logit contributions | |
ained | -0.023 |
THE | -0.021 |
Ag | -0.021 |
ectar | -0.021 |
Prin | -0.021 |
Token | old |
Token ID | 1468 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
ained | +0.006 |
ust | +0.005 |
ectar | +0.005 |
perspective | +0.005 |
THE | +0.005 |
Neg logit contributions | |
hands | -0.004 |
sle | -0.004 |
paws | -0.004 |
apr | -0.004 |
cheeks | -0.004 |
Token | man |
Token ID | 582 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
ained | +0.038 |
Ag | +0.033 |
THE | +0.033 |
ust | +0.033 |
ectar | +0.032 |
Neg logit contributions | |
hands | -0.025 |
sle | -0.025 |
paws | -0.023 |
fingers | -0.022 |
pans | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +2.15e-03 |
Pos logit contributions | |
ained | +0.057 |
Ag | +0.054 |
ust | +0.052 |
Prin | +0.052 |
fault | +0.051 |
Neg logit contributions | |
hands | -0.026 |
sle | -0.023 |
paws | -0.021 |
load | -0.020 |
drive | -0.020 |
Token | He |
Token ID | 679 |
Feature activation | -2.08e-03 |
Pos logit contributions | |
ained | +0.003 |
Prin | +0.003 |
Ag | +0.003 |
ectar | +0.003 |
THE | +0.003 |
Neg logit contributions | |
sle | -0.003 |
hands | -0.003 |
paws | -0.003 |
apr | -0.003 |
pans | -0.003 |
Token | tre |
Token ID | 2054 |
Feature activation | +8.32e-02 |
Pos logit contributions | |
hands | +0.003 |
sle | +0.003 |
paws | +0.002 |
apr | +0.002 |
Daddy | +0.002 |
Neg logit contributions | |
ained | -0.004 |
ectar | -0.004 |
THE | -0.004 |
perspective | -0.004 |
Ag | -0.004 |
Token | asured |
Token ID | 34006 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
ained | +0.114 |
Ag | +0.099 |
THE | +0.099 |
Prin | +0.096 |
ectar | +0.096 |
Neg logit contributions | |
hands | -0.148 |
sle | -0.143 |
paws | -0.138 |
apr | -0.133 |
fingers | -0.133 |
Token | it |
Token ID | 340 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
ained | +0.048 |
Ag | +0.044 |
ectar | +0.043 |
THE | +0.043 |
Prin | +0.043 |
Neg logit contributions | |
hands | -0.026 |
sle | -0.023 |
paws | -0.023 |
fingers | -0.022 |
apr | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +3.71e-02 |
Pos logit contributions | |
ained | +0.018 |
Ag | +0.018 |
Kay | +0.017 |
ount | +0.016 |
ala | +0.016 |
Neg logit contributions | |
hands | -0.012 |
paws | -0.011 |
sle | -0.011 |
fingers | -0.010 |
Daddy | -0.010 |
Token | for |
Token ID | 329 |
Feature activation | +2.19e-02 |
Pos logit contributions | |
ained | +0.075 |
THE | +0.070 |
Ag | +0.068 |
ust | +0.068 |
ala | +0.068 |
Neg logit contributions | |
hands | -0.049 |
paws | -0.045 |
sle | -0.043 |
fingers | -0.043 |
Daddy | -0.041 |
Token | it |
Token ID | 340 |
Feature activation | +4.82e-03 |
Pos logit contributions | |
ained | +0.043 |
Ag | +0.038 |
THE | +0.038 |
ectar | +0.037 |
ust | +0.037 |
Neg logit contributions | |
hands | -0.028 |
sle | -0.027 |
paws | -0.026 |
fingers | -0.024 |
apr | -0.024 |
Token | with |
Token ID | 351 |
Feature activation | +3.38e-03 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.010 |
paws | +0.010 |
Daddy | +0.010 |
fingers | +0.009 |
Neg logit contributions | |
ained | -0.018 |
Prin | -0.016 |
Ag | -0.016 |
ust | -0.015 |
perspective | -0.015 |
Token | him |
Token ID | 683 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
ained | +0.006 |
THE | +0.005 |
Ag | +0.005 |
Prin | +0.005 |
ectar | +0.005 |
Neg logit contributions | |
sle | -0.005 |
hands | -0.004 |
paws | -0.004 |
pans | -0.004 |
fingers | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +2.23e-02 |
Pos logit contributions | |
hands | +0.024 |
paws | +0.022 |
sle | +0.020 |
fingers | +0.019 |
Daddy | +0.019 |
Neg logit contributions | |
ained | -0.038 |
Ag | -0.034 |
Prin | -0.033 |
Kay | -0.033 |
ala | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
ained | +0.045 |
ust | +0.039 |
Prin | +0.039 |
ala | +0.039 |
ectar | +0.038 |
Neg logit contributions | |
hands | -0.032 |
sle | -0.030 |
paws | -0.029 |
Daddy | -0.027 |
fingers | -0.027 |
Token | he |
Token ID | 339 |
Feature activation | +7.77e-03 |
Pos logit contributions | |
ained | +0.012 |
Ag | +0.011 |
ectar | +0.011 |
ala | +0.011 |
ount | +0.010 |
Neg logit contributions | |
hands | -0.008 |
paws | -0.007 |
sle | -0.007 |
Daddy | -0.007 |
fingers | -0.007 |
Token | tre |
Token ID | 2054 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
ained | +0.015 |
Ag | +0.013 |
ectar | +0.012 |
perspective | +0.012 |
ust | +0.012 |
Neg logit contributions | |
hands | -0.011 |
sle | -0.011 |
paws | -0.010 |
fingers | -0.009 |
apr | -0.009 |
Token | asured |
Token ID | 34006 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
ained | +0.116 |
Ag | +0.101 |
THE | +0.100 |
Prin | +0.100 |
ectar | +0.098 |
Neg logit contributions | |
hands | -0.146 |
sle | -0.141 |
paws | -0.136 |
apr | -0.131 |
fingers | -0.131 |
Token | it |
Token ID | 340 |
Feature activation | +4.29e-03 |
Pos logit contributions | |
ained | +0.039 |
Prin | +0.034 |
ust | +0.034 |
ectar | +0.034 |
Ag | +0.033 |
Neg logit contributions | |
hands | -0.028 |
paws | -0.024 |
sle | -0.024 |
fingers | -0.023 |
Daddy | -0.023 |
Token | always |
Token ID | 1464 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ained | +0.008 |
Ag | +0.008 |
Kay | +0.007 |
ectar | +0.007 |
ount | +0.007 |
Neg logit contributions | |
hands | -0.006 |
paws | -0.005 |
sle | -0.005 |
fingers | -0.005 |
Daddy | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +8.53e-04 |
Pos logit contributions | |
ained | +0.027 |
Ag | +0.023 |
THE | +0.023 |
ectar | +0.023 |
Prin | +0.023 |
Neg logit contributions | |
hands | -0.021 |
sle | -0.020 |
paws | -0.019 |
fingers | -0.018 |
apr | -0.018 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.07e-02 |
Pos logit contributions | |
ained | +0.001 |
THE | +0.001 |
Prin | +0.001 |
Ag | +0.001 |
ectar | +0.001 |
Neg logit contributions | |
sle | -0.001 |
hands | -0.001 |
paws | -0.001 |
apr | -0.001 |
pans | -0.001 |
Token | proud |
Token ID | 6613 |
Feature activation | +2.77e-02 |
Pos logit contributions | |
ained | +0.016 |
perspective | +0.015 |
eway | +0.015 |
Ag | +0.015 |
ust | +0.014 |
Neg logit contributions | |
hands | -0.010 |
paws | -0.009 |
Daddy | -0.008 |
fingers | -0.008 |
sle | -0.008 |
Token | of |
Token ID | 286 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
ained | +0.054 |
Prin | +0.047 |
Ag | +0.046 |
eway | +0.046 |
ount | +0.045 |
Neg logit contributions | |
hands | -0.039 |
paws | -0.036 |
Daddy | -0.035 |
fingers | -0.033 |
sle | -0.033 |
Token | herself |
Token ID | 5223 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ained | +0.069 |
Prin | +0.060 |
Ag | +0.059 |
ount | +0.059 |
ust | +0.059 |
Neg logit contributions | |
hands | -0.070 |
paws | -0.063 |
Daddy | -0.063 |
fingers | -0.061 |
sle | -0.061 |
Token | for |
Token ID | 329 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
ained | +0.032 |
Ag | +0.028 |
Prin | +0.028 |
THE | +0.028 |
ectar | +0.028 |
Neg logit contributions | |
hands | -0.021 |
sle | -0.020 |
paws | -0.019 |
fingers | -0.018 |
apr | -0.018 |
Token | doing |
Token ID | 1804 |
Feature activation | +4.69e-02 |
Pos logit contributions | |
ained | +0.065 |
Ag | +0.056 |
THE | +0.056 |
Prin | +0.055 |
ectar | +0.055 |
Neg logit contributions | |
hands | -0.051 |
sle | -0.049 |
paws | -0.047 |
fingers | -0.045 |
apr | -0.044 |
Token | such |
Token ID | 884 |
Feature activation | +8.28e-02 |
Pos logit contributions | |
ained | +0.104 |
ust | +0.093 |
ount | +0.093 |
perspective | +0.091 |
ala | +0.090 |
Neg logit contributions | |
hands | -0.054 |
apr | -0.046 |
paws | -0.044 |
Daddy | -0.044 |
fingers | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | +8.40e-03 |
Pos logit contributions | |
ained | +0.220 |
ount | +0.201 |
inas | +0.200 |
ill | +0.198 |
ala | +0.196 |
Neg logit contributions | |
hands | -0.053 |
paws | -0.043 |
Daddy | -0.036 |
fingers | -0.035 |
apr | -0.034 |
Token | good |
Token ID | 922 |
Feature activation | +4.13e-02 |
Pos logit contributions | |
ained | +0.016 |
Ag | +0.014 |
THE | +0.014 |
ectar | +0.014 |
Prin | +0.014 |
Neg logit contributions | |
hands | -0.011 |
sle | -0.011 |
paws | -0.010 |
fingers | -0.009 |
apr | -0.009 |
Token | job |
Token ID | 1693 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
ained | +0.075 |
Ag | +0.065 |
THE | +0.065 |
ectar | +0.064 |
Prin | +0.064 |
Neg logit contributions | |
hands | -0.058 |
sle | -0.056 |
paws | -0.054 |
fingers | -0.051 |
apr | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e-02 |
Pos logit contributions | |
ained | +0.045 |
Prin | +0.040 |
Acc | +0.039 |
Ag | +0.038 |
ulture | +0.038 |
Neg logit contributions | |
hands | -0.019 |
Daddy | -0.016 |
fingers | -0.015 |
sle | -0.015 |
t | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
ained | +0.023 |
THE | +0.019 |
Ag | +0.019 |
ectar | +0.019 |
Prin | +0.019 |
Neg logit contributions | |
sle | -0.027 |
hands | -0.027 |
paws | -0.026 |
apr | -0.025 |
pans | -0.025 |
Token | to |
Token ID | 284 |
Feature activation | +3.27e-02 |
Pos logit contributions | |
ained | +0.041 |
Prin | +0.038 |
Ag | +0.037 |
Kay | +0.037 |
ount | +0.036 |
Neg logit contributions | |
hands | -0.025 |
paws | -0.023 |
fingers | -0.021 |
sle | -0.021 |
Daddy | -0.020 |
Token | have |
Token ID | 423 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
ained | +0.065 |
Ag | +0.057 |
THE | +0.056 |
ectar | +0.056 |
Prin | +0.056 |
Neg logit contributions | |
hands | -0.041 |
sle | -0.040 |
paws | -0.037 |
fingers | -0.035 |
apr | -0.034 |
Token | been |
Token ID | 587 |
Feature activation | +1.15e-02 |
Pos logit contributions | |
ained | +0.081 |
THE | +0.070 |
ectar | +0.070 |
Ag | +0.070 |
Prin | +0.069 |
Neg logit contributions | |
hands | -0.059 |
sle | -0.055 |
paws | -0.055 |
fingers | -0.050 |
apr | -0.049 |
Token | saved |
Token ID | 7448 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
ained | +0.022 |
THE | +0.019 |
Ag | +0.019 |
perspective | +0.019 |
ust | +0.019 |
Neg logit contributions | |
hands | -0.015 |
sle | -0.014 |
paws | -0.014 |
fingers | -0.013 |
pans | -0.012 |
Token | by |
Token ID | 416 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
ained | +0.027 |
Ag | +0.024 |
THE | +0.024 |
inas | +0.023 |
Kay | +0.023 |
Neg logit contributions | |
hands | -0.019 |
paws | -0.017 |
sle | -0.017 |
fingers | -0.016 |
cub | -0.016 |
Token | such |
Token ID | 884 |
Feature activation | +8.25e-02 |
Pos logit contributions | |
ained | +0.036 |
Ag | +0.033 |
THE | +0.032 |
ust | +0.032 |
Prin | +0.032 |
Neg logit contributions | |
hands | -0.017 |
paws | -0.015 |
sle | -0.015 |
fingers | -0.014 |
eyes | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +8.59e-03 |
Pos logit contributions | |
ained | +0.229 |
ount | +0.218 |
ill | +0.217 |
inas | +0.216 |
ying | +0.212 |
Neg logit contributions | |
hands | -0.042 |
paws | -0.037 |
fiery | -0.024 |
brown | -0.024 |
white | -0.023 |
Token | kind |
Token ID | 1611 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
ained | +0.020 |
ala | +0.017 |
ill | +0.017 |
ectar | +0.017 |
inas | +0.017 |
Neg logit contributions | |
sle | -0.009 |
hands | -0.008 |
paws | -0.008 |
load | -0.007 |
cub | -0.007 |
Token | bird |
Token ID | 6512 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
ained | +0.063 |
THE | +0.055 |
Ag | +0.054 |
Acc | +0.053 |
Prin | +0.052 |
Neg logit contributions | |
hands | -0.032 |
paws | -0.031 |
sle | -0.031 |
cub | -0.027 |
little | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +8.98e-03 |
Pos logit contributions | |
ained | +0.087 |
Ag | +0.080 |
Kay | +0.079 |
Prin | +0.076 |
pour | +0.074 |
Neg logit contributions | |
hands | -0.035 |
sle | -0.033 |
paws | -0.033 |
cub | -0.031 |
help | -0.028 |
Token | From |
Token ID | 3574 |
Feature activation | +3.56e-02 |
Pos logit contributions | |
ained | +0.017 |
Ag | +0.015 |
THE | +0.015 |
ectar | +0.015 |
ust | +0.015 |
Neg logit contributions | |
hands | -0.012 |
sle | -0.011 |
paws | -0.011 |
Daddy | -0.010 |
fingers | -0.010 |
Token | have |
Token ID | 423 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
ained | +0.064 |
ust | +0.058 |
perspective | +0.056 |
Prin | +0.056 |
ectar | +0.056 |
Neg logit contributions | |
hands | -0.028 |
sle | -0.025 |
paws | -0.025 |
help | -0.023 |
Daddy | -0.023 |
Token | spent |
Token ID | 3377 |
Feature activation | +5.67e-02 |
Pos logit contributions | |
ained | +0.073 |
perspective | +0.065 |
ectar | +0.065 |
ust | +0.064 |
ount | +0.063 |
Neg logit contributions | |
hands | -0.057 |
paws | -0.051 |
sle | -0.048 |
apr | -0.048 |
fingers | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
ained | +0.121 |
ust | +0.117 |
ount | +0.115 |
inas | +0.113 |
ala | +0.112 |
Neg logit contributions | |
hands | -0.065 |
paws | -0.053 |
apr | -0.049 |
fingers | -0.046 |
white | -0.045 |
Token | afternoon |
Token ID | 6672 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
ained | +0.037 |
Ag | +0.033 |
THE | +0.033 |
Prin | +0.032 |
Kay | +0.031 |
Neg logit contributions | |
sle | -0.032 |
hands | -0.032 |
paws | -0.030 |
fingers | -0.030 |
forks | -0.029 |
Token | in |
Token ID | 287 |
Feature activation | +5.25e-03 |
Pos logit contributions | |
hands | +0.014 |
sle | +0.013 |
paws | +0.013 |
fingers | +0.012 |
pans | +0.011 |
Neg logit contributions | |
ained | -0.024 |
ust | -0.021 |
Prin | -0.021 |
ala | -0.020 |
Kay | -0.020 |
Token | such |
Token ID | 884 |
Feature activation | +8.24e-02 |
Pos logit contributions | |
ained | +0.013 |
ust | +0.012 |
ying | +0.011 |
ount | +0.011 |
inas | +0.011 |
Neg logit contributions | |
hands | -0.005 |
sle | -0.004 |
Daddy | -0.004 |
paws | -0.004 |
front | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +3.17e-03 |
Pos logit contributions | |
ained | +0.232 |
inas | +0.217 |
ying | +0.216 |
ount | +0.216 |
ub | +0.211 |
Neg logit contributions | |
hands | -0.040 |
paws | -0.028 |
apr | -0.023 |
white | -0.022 |
fiery | -0.021 |
Token | calm |
Token ID | 9480 |
Feature activation | -4.87e-04 |
Pos logit contributions | |
ained | +0.007 |
ectar | +0.006 |
ala | +0.006 |
ust | +0.006 |
ying | +0.005 |
Neg logit contributions | |
sle | -0.004 |
hands | -0.004 |
paws | -0.003 |
pans | -0.003 |
Daddy | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -8.25e-03 |
Pos logit contributions | |
hands | +0.001 |
sle | +0.001 |
paws | +0.001 |
Daddy | +0.000 |
white | +0.000 |
Neg logit contributions | |
ained | -0.001 |
ust | -0.001 |
Prin | -0.001 |
THE | -0.001 |
Acc | -0.001 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +8.67e-03 |
Pos logit contributions | |
hands | +0.010 |
sle | +0.009 |
paws | +0.008 |
Daddy | +0.008 |
white | +0.008 |
Neg logit contributions | |
ained | -0.017 |
ust | -0.016 |
ala | -0.016 |
Prin | -0.015 |
ount | -0.015 |
Token | way |
Token ID | 835 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
ained | +0.019 |
ust | +0.018 |
itates | +0.017 |
ount | +0.017 |
ying | +0.016 |
Neg logit contributions | |
hands | -0.011 |
paws | -0.010 |
sle | -0.009 |
white | -0.009 |
orange | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
ained | +0.014 |
ulture | +0.012 |
Fighting | +0.012 |
Prin | +0.012 |
ust | +0.012 |
Neg logit contributions | |
hands | -0.005 |
white | -0.004 |
sle | -0.004 |
brown | -0.004 |
big | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.29e-02 |
Pos logit contributions | |
ained | +0.060 |
ust | +0.054 |
Prin | +0.052 |
ala | +0.052 |
ectar | +0.051 |
Neg logit contributions | |
hands | -0.038 |
sle | -0.038 |
paws | -0.033 |
white | -0.032 |
Daddy | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
ained | +0.052 |
Prin | +0.048 |
ust | +0.046 |
ount | +0.045 |
Ag | +0.045 |
Neg logit contributions | |
hands | -0.026 |
sle | -0.024 |
paws | -0.022 |
eyes | -0.022 |
Daddy | -0.022 |
Token | be |
Token ID | 307 |
Feature activation | +2.45e-02 |
Pos logit contributions | |
ained | +0.068 |
ust | +0.061 |
ectar | +0.060 |
perspective | +0.059 |
Prin | +0.059 |
Neg logit contributions | |
hands | -0.024 |
sle | -0.023 |
help | -0.021 |
paws | -0.021 |
load | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | +7.59e-03 |
Pos logit contributions | |
ained | +0.046 |
perspective | +0.042 |
fault | +0.041 |
ust | +0.041 |
Prin | +0.040 |
Neg logit contributions | |
hands | -0.032 |
sle | -0.030 |
paws | -0.029 |
white | -0.026 |
Daddy | -0.026 |
Token | such |
Token ID | 884 |
Feature activation | +8.23e-02 |
Pos logit contributions | |
ained | +0.019 |
ust | +0.017 |
ulture | +0.017 |
ectar | +0.017 |
itates | +0.017 |
Neg logit contributions | |
hands | -0.006 |
sle | -0.006 |
paws | -0.005 |
Daddy | -0.005 |
white | -0.005 |
Token | an |
Token ID | 281 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
ained | +0.246 |
ount | +0.233 |
inas | +0.233 |
ying | +0.229 |
ub | +0.228 |
Neg logit contributions | |
hands | -0.028 |
paws | -0.018 |
little | -0.018 |
help | -0.012 |
white | -0.011 |
Token | adventure |
Token ID | 8855 |
Feature activation | +1.31e-03 |
Pos logit contributions | |
ained | +0.021 |
THE | +0.019 |
ust | +0.019 |
Ag | +0.018 |
perspective | +0.018 |
Neg logit contributions | |
hands | -0.020 |
paws | -0.019 |
sle | -0.019 |
fingers | -0.019 |
pans | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +7.57e-03 |
Pos logit contributions | |
ained | +0.003 |
Prin | +0.003 |
Ag | +0.003 |
ectar | +0.002 |
inas | +0.002 |
Neg logit contributions | |
hands | -0.001 |
sle | -0.001 |
paws | -0.001 |
Daddy | -0.001 |
fingers | -0.001 |
Token | What |
Token ID | 1867 |
Feature activation | +8.52e-03 |
Pos logit contributions | |
ained | +0.013 |
Ag | +0.012 |
ust | +0.012 |
Prin | +0.011 |
ectar | +0.011 |
Neg logit contributions | |
hands | -0.011 |
sle | -0.010 |
paws | -0.010 |
Daddy | -0.009 |
fingers | -0.009 |
Token | would |
Token ID | 561 |
Feature activation | -9.95e-03 |
Pos logit contributions | |
ained | +0.021 |
ount | +0.019 |
Ag | +0.019 |
inas | +0.018 |
THE | +0.018 |
Neg logit contributions | |
hands | -0.007 |
Daddy | -0.006 |
paws | -0.006 |
sle | -0.006 |
grand | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
hands | +0.038 |
sle | +0.035 |
Daddy | +0.033 |
paws | +0.032 |
fingers | +0.031 |
Neg logit contributions | |
ained | -0.070 |
Ag | -0.065 |
Prin | -0.064 |
THE | -0.062 |
Kay | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
ained | +0.026 |
ust | +0.023 |
perspective | +0.022 |
Prin | +0.022 |
ectar | +0.022 |
Neg logit contributions | |
hands | -0.015 |
sle | -0.013 |
paws | -0.013 |
Daddy | -0.013 |
fingers | -0.012 |
Token | Grand |
Token ID | 5675 |
Feature activation | -4.04e-02 |
Pos logit contributions | |
hands | +0.028 |
sle | +0.025 |
Daddy | +0.024 |
paws | +0.024 |
fingers | +0.023 |
Neg logit contributions | |
ained | -0.045 |
perspective | -0.039 |
Ag | -0.039 |
ectar | -0.039 |
THE | -0.039 |
Token | ma |
Token ID | 2611 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
sle | +0.044 |
paws | +0.044 |
hands | +0.044 |
pans | +0.038 |
fingers | +0.038 |
Neg logit contributions | |
ained | -0.081 |
THE | -0.073 |
Kay | -0.073 |
ust | -0.073 |
ala | -0.072 |
Token | hugged |
Token ID | 41130 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
hands | +0.029 |
sle | +0.027 |
paws | +0.026 |
Daddy | +0.025 |
fingers | +0.024 |
Neg logit contributions | |
ained | -0.047 |
Ag | -0.042 |
ectar | -0.041 |
perspective | -0.040 |
Prin | -0.040 |
Token | Little |
Token ID | 7703 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
hands | +0.055 |
sle | +0.051 |
Daddy | +0.048 |
paws | +0.047 |
apr | +0.046 |
Neg logit contributions | |
ained | -0.098 |
ectar | -0.086 |
Ag | -0.085 |
THE | -0.085 |
ust | -0.085 |
Token | Billy |
Token ID | 15890 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
hands | +0.098 |
sle | +0.097 |
paws | +0.091 |
fingers | +0.084 |
apr | +0.084 |
Neg logit contributions | |
ained | -0.154 |
Ag | -0.136 |
THE | -0.135 |
Prin | -0.134 |
ectar | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | -2.34e-02 |
Pos logit contributions | |
hands | +0.056 |
sle | +0.052 |
paws | +0.050 |
fingers | +0.046 |
Daddy | +0.046 |
Neg logit contributions | |
ained | -0.080 |
Ag | -0.073 |
Prin | -0.070 |
Kay | -0.069 |
ectar | -0.069 |
Token | " |
Token ID | 366 |
Feature activation | -8.38e-03 |
Pos logit contributions | |
hands | +0.029 |
sle | +0.028 |
paws | +0.026 |
fingers | +0.024 |
apr | +0.024 |
Neg logit contributions | |
ained | -0.046 |
Ag | -0.041 |
THE | -0.041 |
ectar | -0.040 |
Prin | -0.040 |
Token | We |
Token ID | 1135 |
Feature activation | -1.93e-02 |
Pos logit contributions | |
sle | +0.012 |
hands | +0.012 |
apr | +0.012 |
Daddy | +0.012 |
pans | +0.011 |
Neg logit contributions | |
ained | -0.014 |
fault | -0.012 |
ying | -0.012 |
ectar | -0.012 |
eway | -0.011 |
Token | 'll |
Token ID | 1183 |
Feature activation | -3.31e-02 |
Pos logit contributions | |
hands | +0.025 |
paws | +0.022 |
sle | +0.021 |
help | +0.021 |
Daddy | +0.021 |
Neg logit contributions | |
ained | -0.038 |
Ag | -0.034 |
ectar | -0.034 |
Kay | -0.033 |
eway | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -7.92e-03 |
Pos logit contributions | |
ained | +0.008 |
Ag | +0.008 |
Prin | +0.008 |
perspective | +0.008 |
ust | +0.008 |
Neg logit contributions | |
hands | -0.004 |
sle | -0.004 |
paws | -0.004 |
load | -0.004 |
orange | -0.004 |
Token | named |
Token ID | 3706 |
Feature activation | -3.73e-04 |
Pos logit contributions | |
hands | +0.009 |
paws | +0.008 |
fingers | +0.008 |
sle | +0.008 |
pans | +0.008 |
Neg logit contributions | |
ained | -0.017 |
ust | -0.016 |
ectar | -0.016 |
THE | -0.015 |
ala | -0.015 |
Token | it |
Token ID | 340 |
Feature activation | -3.08e-02 |
Pos logit contributions | |
sle | +0.001 |
hands | +0.001 |
paws | +0.001 |
pans | +0.001 |
apr | +0.000 |
Neg logit contributions | |
ained | -0.001 |
Prin | -0.001 |
Kay | -0.001 |
Ag | -0.001 |
THE | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | -5.76e-03 |
Pos logit contributions | |
hands | +0.036 |
paws | +0.033 |
sle | +0.032 |
fingers | +0.030 |
load | +0.029 |
Neg logit contributions | |
ained | -0.065 |
Ag | -0.060 |
ectar | -0.059 |
perspective | -0.059 |
ust | -0.059 |
Token | The |
Token ID | 464 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
hands | +0.008 |
sle | +0.008 |
paws | +0.008 |
apr | +0.008 |
fingers | +0.008 |
Neg logit contributions | |
ained | -0.010 |
Ag | -0.008 |
ectar | -0.008 |
fault | -0.008 |
perspective | -0.008 |
Token | Big |
Token ID | 4403 |
Feature activation | -7.67e-02 |
Pos logit contributions | |
sle | +0.020 |
hands | +0.020 |
paws | +0.019 |
apr | +0.018 |
fingers | +0.017 |
Neg logit contributions | |
ained | -0.036 |
THE | -0.032 |
perspective | -0.032 |
Prin | -0.032 |
ust | -0.031 |
Token | Tower |
Token ID | 8765 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
sle | +0.091 |
hands | +0.088 |
apr | +0.082 |
paws | +0.079 |
pans | +0.079 |
Neg logit contributions | |
ained | -0.137 |
bows | -0.126 |
fault | -0.122 |
inas | -0.119 |
olving | -0.119 |
Token | ". |
Token ID | 1911 |
Feature activation | -2.62e-03 |
Pos logit contributions | |
hands | +0.027 |
sle | +0.025 |
paws | +0.024 |
fingers | +0.022 |
apr | +0.022 |
Neg logit contributions | |
ained | -0.041 |
Ag | -0.038 |
ectar | -0.037 |
ust | -0.037 |
THE | -0.037 |
Token | She |
Token ID | 1375 |
Feature activation | +1.90e-04 |
Pos logit contributions | |
hands | +0.003 |
paws | +0.003 |
Daddy | +0.003 |
sle | +0.003 |
fingers | +0.003 |
Neg logit contributions | |
ained | -0.005 |
ust | -0.005 |
ier | -0.005 |
THE | -0.005 |
ectar | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ained | +0.000 |
ectar | +0.000 |
Ag | +0.000 |
THE | +0.000 |
ust | +0.000 |
Neg logit contributions | |
hands | -0.000 |
sle | -0.000 |
paws | -0.000 |
fingers | -0.000 |
apr | -0.000 |
Token | very |
Token ID | 845 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
hands | +0.017 |
paws | +0.014 |
white | +0.014 |
sle | +0.014 |
Daddy | +0.014 |
Neg logit contributions | |
ained | -0.031 |
perspective | -0.031 |
ust | -0.030 |
Ag | -0.030 |
Prin | -0.030 |
Token | shop |
Token ID | 6128 |
Feature activation | -6.98e-03 |
Pos logit contributions | |
hands | +0.004 |
sle | +0.004 |
paws | +0.004 |
plates | +0.004 |
forks | +0.004 |
Neg logit contributions | |
ained | -0.008 |
ust | -0.007 |
Ag | -0.007 |
ectar | -0.007 |
Prin | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
hands | +0.007 |
sle | +0.006 |
paws | +0.006 |
Daddy | +0.006 |
fingers | +0.006 |
Neg logit contributions | |
ained | -0.016 |
THE | -0.014 |
Prin | -0.014 |
ectar | -0.014 |
Ag | -0.014 |
Token | Little |
Token ID | 7703 |
Feature activation | -6.82e-02 |
Pos logit contributions | |
hands | +0.018 |
sle | +0.018 |
paws | +0.017 |
apr | +0.016 |
fingers | +0.015 |
Neg logit contributions | |
ained | -0.038 |
Ag | -0.033 |
THE | -0.033 |
ectar | -0.033 |
Prin | -0.033 |
Token | Jake |
Token ID | 14757 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
sle | +0.083 |
hands | +0.079 |
paws | +0.074 |
apr | +0.069 |
fingers | +0.068 |
Neg logit contributions | |
ained | -0.132 |
Ag | -0.117 |
THE | -0.116 |
ust | -0.113 |
ill | -0.113 |
Token | asked |
Token ID | 1965 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
hands | +0.034 |
sle | +0.032 |
paws | +0.031 |
fingers | +0.029 |
Daddy | +0.028 |
Neg logit contributions | |
ained | -0.053 |
ectar | -0.047 |
Ag | -0.046 |
THE | -0.046 |
ust | -0.045 |
Token | Big |
Token ID | 4403 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
hands | +0.038 |
sle | +0.037 |
paws | +0.034 |
fingers | +0.032 |
apr | +0.032 |
Neg logit contributions | |
ained | -0.068 |
Ag | -0.060 |
THE | -0.059 |
ectar | -0.059 |
Prin | -0.059 |
Token | John |
Token ID | 1757 |
Feature activation | -4.07e-02 |
Pos logit contributions | |
sle | +0.087 |
hands | +0.086 |
paws | +0.078 |
apr | +0.073 |
fingers | +0.073 |
Neg logit contributions | |
ained | -0.148 |
Ag | -0.133 |
THE | -0.130 |
inas | -0.130 |
Prin | -0.130 |
Token | for |
Token ID | 329 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
hands | +0.049 |
sle | +0.044 |
Daddy | +0.043 |
paws | +0.043 |
load | +0.041 |
Neg logit contributions | |
ained | -0.089 |
Ag | -0.080 |
Prin | -0.077 |
ectar | -0.075 |
THE | -0.075 |
Token | a |
Token ID | 257 |
Feature activation | -3.16e-03 |
Pos logit contributions | |
ained | +0.027 |
THE | +0.024 |
Ag | +0.024 |
ectar | +0.024 |
Prin | +0.024 |
Neg logit contributions | |
hands | -0.014 |
sle | -0.013 |
paws | -0.013 |
fingers | -0.012 |
apr | -0.012 |
Token | coffee |
Token ID | 6891 |
Feature activation | -8.90e-03 |
Pos logit contributions | |
sle | +0.004 |
hands | +0.004 |
paws | +0.004 |
pans | +0.003 |
fingers | +0.003 |
Neg logit contributions | |
ained | -0.005 |
Ag | -0.005 |
perspective | -0.005 |
THE | -0.005 |
ust | -0.005 |
Token | : |
Token ID | 25 |
Feature activation | +5.14e-03 |
Pos logit contributions | |
hands | +0.010 |
sle | +0.010 |
plates | +0.009 |
Daddy | +0.009 |
paws | +0.009 |
Neg logit contributions | |
ained | -0.019 |
Prin | -0.017 |
Ag | -0.016 |
ust | -0.016 |
Kay | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -9.28e-03 |
Pos logit contributions | |
sle | +0.016 |
hands | +0.016 |
paws | +0.015 |
fingers | +0.015 |
apr | +0.014 |
Neg logit contributions | |
ained | -0.017 |
THE | -0.014 |
Ag | -0.014 |
ectar | -0.014 |
ust | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
hands | +0.017 |
sle | +0.017 |
fingers | +0.016 |
paws | +0.016 |
cheeks | +0.016 |
Neg logit contributions | |
ained | -0.013 |
THE | -0.013 |
Ag | -0.011 |
Prin | -0.011 |
ectar | -0.010 |
Token | Mom |
Token ID | 29252 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
hands | +0.025 |
sle | +0.025 |
paws | +0.024 |
fingers | +0.023 |
apr | +0.022 |
Neg logit contributions | |
ained | -0.020 |
THE | -0.017 |
Ag | -0.017 |
Prin | -0.016 |
ectar | -0.016 |
Token | my |
Token ID | 1820 |
Feature activation | -1.39e-02 |
Pos logit contributions | |
sle | +0.033 |
hands | +0.033 |
paws | +0.031 |
apr | +0.030 |
fingers | +0.030 |
Neg logit contributions | |
ained | -0.035 |
THE | -0.030 |
Ag | -0.029 |
Prin | -0.029 |
ust | -0.029 |
Token | hugged |
Token ID | 41130 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
hands | +0.020 |
sle | +0.020 |
paws | +0.018 |
fingers | +0.018 |
apr | +0.017 |
Neg logit contributions | |
ained | -0.024 |
THE | -0.021 |
Ag | -0.021 |
Prin | -0.021 |
Kay | -0.021 |
Token | Little |
Token ID | 7703 |
Feature activation | -7.58e-02 |
Pos logit contributions | |
sle | +0.048 |
paws | +0.045 |
hands | +0.044 |
pans | +0.043 |
fingers | +0.041 |
Neg logit contributions | |
ained | -0.065 |
THE | -0.060 |
Prin | -0.058 |
Ag | -0.057 |
Kay | -0.057 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
sle | +0.096 |
hands | +0.087 |
paws | +0.087 |
fingers | +0.078 |
apr | +0.077 |
Neg logit contributions | |
ained | -0.140 |
Ag | -0.126 |
THE | -0.126 |
it | -0.121 |
Kay | -0.120 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e-02 |
Pos logit contributions | |
sle | +0.033 |
hands | +0.032 |
paws | +0.030 |
apr | +0.030 |
pans | +0.030 |
Neg logit contributions | |
ained | -0.038 |
THE | -0.034 |
ectar | -0.032 |
ust | -0.032 |
Prin | -0.032 |
Token | said |
Token ID | 531 |
Feature activation | +8.96e-03 |
Pos logit contributions | |
sle | +0.016 |
hands | +0.015 |
paws | +0.015 |
fingers | +0.014 |
apr | +0.014 |
Neg logit contributions | |
ained | -0.016 |
THE | -0.015 |
Ag | -0.015 |
Kay | -0.014 |
Prin | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
ained | +0.020 |
Ag | +0.017 |
Prin | +0.017 |
ectar | +0.017 |
perspective | +0.017 |
Neg logit contributions | |
hands | -0.010 |
sle | -0.009 |
paws | -0.008 |
Daddy | -0.008 |
fingers | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | +6.74e-03 |
Pos logit contributions | |
ained | +0.039 |
Ag | +0.034 |
THE | +0.034 |
ectar | +0.034 |
Prin | +0.034 |
Neg logit contributions | |
hands | -0.029 |
sle | -0.028 |
paws | -0.027 |
fingers | -0.025 |
apr | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
hands | +0.010 |
sle | +0.009 |
paws | +0.009 |
Daddy | +0.008 |
apr | +0.008 |
Neg logit contributions | |
ained | -0.013 |
Ag | -0.012 |
perspective | -0.012 |
THE | -0.012 |
ectar | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | -1.46e-02 |
Pos logit contributions | |
hands | +0.012 |
sle | +0.011 |
paws | +0.011 |
apr | +0.010 |
Daddy | +0.010 |
Neg logit contributions | |
ained | -0.021 |
perspective | -0.019 |
ier | -0.019 |
fault | -0.019 |
ust | -0.019 |
Token | When |
Token ID | 2215 |
Feature activation | -4.35e-02 |
Pos logit contributions | |
apr | +0.018 |
hands | +0.018 |
Daddy | +0.016 |
little | +0.016 |
paws | +0.016 |
Neg logit contributions | |
fault | -0.026 |
ained | -0.025 |
ier | -0.024 |
ectar | -0.023 |
bows | -0.023 |
Token | it |
Token ID | 340 |
Feature activation | -3.92e-02 |
Pos logit contributions | |
hands | +0.058 |
Daddy | +0.055 |
paws | +0.050 |
sle | +0.049 |
plates | +0.047 |
Neg logit contributions | |
ained | -0.087 |
ust | -0.078 |
ount | -0.077 |
ectar | -0.077 |
ala | -0.076 |
Token | was |
Token ID | 373 |
Feature activation | -4.60e-02 |
Pos logit contributions | |
hands | +0.051 |
sle | +0.049 |
paws | +0.047 |
fingers | +0.043 |
Daddy | +0.043 |
Neg logit contributions | |
ained | -0.073 |
ectar | -0.065 |
perspective | -0.064 |
Ag | -0.064 |
ust | -0.063 |
Token | time |
Token ID | 640 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
sle | +0.073 |
hands | +0.073 |
paws | +0.069 |
fingers | +0.066 |
pans | +0.066 |
Neg logit contributions | |
ained | -0.077 |
THE | -0.064 |
Prin | -0.063 |
Ag | -0.062 |
ust | -0.062 |
Token | to |
Token ID | 284 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
hands | +0.109 |
sle | +0.101 |
paws | +0.097 |
Daddy | +0.093 |
fingers | +0.092 |
Neg logit contributions | |
ained | -0.137 |
Ag | -0.120 |
Prin | -0.120 |
ust | -0.119 |
ectar | -0.119 |
Token | go |
Token ID | 467 |
Feature activation | -5.40e-02 |
Pos logit contributions | |
hands | +0.040 |
sle | +0.039 |
paws | +0.036 |
fingers | +0.033 |
apr | +0.033 |
Neg logit contributions | |
ained | -0.088 |
THE | -0.079 |
Ag | -0.078 |
Prin | -0.077 |
ectar | -0.077 |
Token | home |
Token ID | 1363 |
Feature activation | -3.35e-02 |
Pos logit contributions | |
hands | +0.079 |
sle | +0.077 |
paws | +0.072 |
Daddy | +0.069 |
fingers | +0.065 |
Neg logit contributions | |
ained | -0.097 |
ust | -0.086 |
Prin | -0.084 |
ectar | -0.083 |
Ag | -0.083 |
Token | , |
Token ID | 11 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
hands | +0.029 |
sle | +0.026 |
Daddy | +0.024 |
paws | +0.024 |
fingers | +0.021 |
Neg logit contributions | |
ained | -0.082 |
Prin | -0.073 |
THE | -0.073 |
ust | -0.073 |
Ag | -0.073 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.55e-02 |
Pos logit contributions | |
Daddy | +0.011 |
hands | +0.011 |
Mom | +0.010 |
mom | +0.009 |
daddy | +0.009 |
Neg logit contributions | |
ained | -0.025 |
ount | -0.022 |
iddle | -0.022 |
ust | -0.022 |
ulture | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | -3.50e-03 |
Pos logit contributions | |
ained | +0.021 |
ust | +0.018 |
Ag | +0.018 |
THE | +0.018 |
ectar | +0.018 |
Neg logit contributions | |
hands | -0.013 |
sle | -0.012 |
paws | -0.011 |
fingers | -0.011 |
apr | -0.011 |
Token | door |
Token ID | 3420 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
hands | +0.004 |
sle | +0.004 |
paws | +0.003 |
fingers | +0.003 |
apr | +0.003 |
Neg logit contributions | |
ained | -0.008 |
Ag | -0.007 |
ectar | -0.007 |
THE | -0.007 |
ust | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
hands | +0.014 |
paws | +0.011 |
sle | +0.011 |
fingers | +0.011 |
Daddy | +0.010 |
Neg logit contributions | |
ained | -0.027 |
Ag | -0.026 |
ectar | -0.024 |
Prin | -0.024 |
Kay | -0.024 |
Token | Tom |
Token ID | 4186 |
Feature activation | -7.88e-03 |
Pos logit contributions | |
ained | +0.004 |
ust | +0.003 |
ectar | +0.003 |
THE | +0.003 |
perspective | +0.003 |
Neg logit contributions | |
hands | -0.003 |
sle | -0.003 |
paws | -0.003 |
Daddy | -0.003 |
fingers | -0.002 |
Token | hugged |
Token ID | 41130 |
Feature activation | -3.43e-02 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.010 |
paws | +0.010 |
fingers | +0.009 |
apr | +0.009 |
Neg logit contributions | |
ained | -0.015 |
Ag | -0.013 |
ectar | -0.013 |
THE | -0.013 |
ust | -0.012 |
Token | Big |
Token ID | 4403 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
hands | +0.040 |
sle | +0.039 |
paws | +0.036 |
Daddy | +0.034 |
fingers | +0.033 |
Neg logit contributions | |
ained | -0.072 |
ectar | -0.065 |
ust | -0.064 |
Ag | -0.063 |
THE | -0.063 |
Token | Red |
Token ID | 2297 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
sle | +0.096 |
apr | +0.094 |
hands | +0.093 |
pans | +0.089 |
forks | +0.088 |
Neg logit contributions | |
ained | -0.133 |
bows | -0.116 |
Ag | -0.114 |
fault | -0.112 |
inas | -0.110 |
Token | and |
Token ID | 290 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
hands | +0.019 |
sle | +0.018 |
paws | +0.017 |
fingers | +0.016 |
forks | +0.016 |
Neg logit contributions | |
ained | -0.026 |
Ag | -0.023 |
Prin | -0.023 |
ectar | -0.022 |
THE | -0.022 |
Token | played |
Token ID | 2826 |
Feature activation | +6.34e-03 |
Pos logit contributions | |
sle | +0.026 |
hands | +0.025 |
paws | +0.023 |
apr | +0.023 |
fingers | +0.023 |
Neg logit contributions | |
ained | -0.035 |
Ag | -0.031 |
Prin | -0.030 |
THE | -0.030 |
ectar | -0.029 |
Token | with |
Token ID | 351 |
Feature activation | -9.14e-03 |
Pos logit contributions | |
ained | +0.015 |
ust | +0.014 |
inas | +0.014 |
perspective | +0.014 |
Kay | +0.013 |
Neg logit contributions | |
hands | -0.007 |
help | -0.006 |
paws | -0.006 |
t | -0.005 |
load | -0.005 |
Token | him |
Token ID | 683 |
Feature activation | -1.80e-02 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.011 |
paws | +0.010 |
fingers | +0.010 |
apr | +0.010 |
Neg logit contributions | |
ained | -0.018 |
Ag | -0.016 |
THE | -0.016 |
Prin | -0.016 |
ectar | -0.016 |
Token | excited |
Token ID | 6568 |
Feature activation | +8.64e-03 |
Pos logit contributions | |
hands | +0.014 |
sle | +0.013 |
paws | +0.013 |
fingers | +0.012 |
pans | +0.012 |
Neg logit contributions | |
ained | -0.019 |
THE | -0.017 |
Prin | -0.016 |
Ag | -0.016 |
perspective | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -5.03e-03 |
Pos logit contributions | |
ained | +0.019 |
Prin | +0.017 |
THE | +0.017 |
ectar | +0.016 |
Ag | +0.016 |
Neg logit contributions | |
hands | -0.010 |
Daddy | -0.008 |
paws | -0.008 |
fingers | -0.008 |
sle | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
hands | +0.008 |
sle | +0.008 |
paws | +0.008 |
fingers | +0.007 |
Daddy | +0.007 |
Neg logit contributions | |
ained | -0.008 |
Ag | -0.007 |
THE | -0.007 |
ust | -0.007 |
ectar | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.87e-02 |
Pos logit contributions | |
hands | +0.015 |
Daddy | +0.014 |
sle | +0.013 |
paws | +0.013 |
apr | +0.012 |
Neg logit contributions | |
ained | -0.032 |
fault | -0.028 |
ier | -0.028 |
inas | -0.028 |
bows | -0.027 |
Token | " |
Token ID | 1 |
Feature activation | +4.74e-03 |
Pos logit contributions | |
hands | +0.032 |
pans | +0.029 |
paws | +0.029 |
sle | +0.029 |
apr | +0.029 |
Neg logit contributions | |
ained | -0.029 |
fault | -0.026 |
ectar | -0.023 |
Ag | -0.023 |
ier | -0.023 |
Token | Big |
Token ID | 12804 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
ained | +0.008 |
ectar | +0.007 |
ust | +0.006 |
Ag | +0.006 |
fault | +0.006 |
Neg logit contributions | |
hands | -0.007 |
sle | -0.007 |
paws | -0.007 |
apr | -0.007 |
pans | -0.007 |
Token | fan |
Token ID | 4336 |
Feature activation | +9.49e-04 |
Pos logit contributions | |
sle | +0.090 |
hands | +0.080 |
apr | +0.075 |
paws | +0.075 |
pans | +0.071 |
Neg logit contributions | |
ained | -0.137 |
fault | -0.122 |
bows | -0.121 |
ectar | -0.121 |
ill | -0.120 |
Token | !" |
Token ID | 2474 |
Feature activation | -4.73e-03 |
Pos logit contributions | |
ained | +0.002 |
Ag | +0.002 |
Prin | +0.002 |
ectar | +0.002 |
ust | +0.002 |
Neg logit contributions | |
hands | -0.001 |
sle | -0.001 |
paws | -0.001 |
cheeks | -0.001 |
load | -0.001 |
Token | she |
Token ID | 673 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
hands | +0.007 |
sle | +0.007 |
paws | +0.006 |
fingers | +0.006 |
apr | +0.006 |
Neg logit contributions | |
ained | -0.008 |
Ag | -0.007 |
THE | -0.007 |
ectar | -0.007 |
Prin | -0.007 |
Token | said |
Token ID | 531 |
Feature activation | -2.31e-03 |
Pos logit contributions | |
ained | +0.025 |
THE | +0.022 |
ectar | +0.022 |
Ag | +0.022 |
perspective | +0.021 |
Neg logit contributions | |
hands | -0.017 |
sle | -0.016 |
paws | -0.015 |
fingers | -0.014 |
apr | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
hands | +0.003 |
sle | +0.003 |
paws | +0.003 |
fingers | +0.003 |
Daddy | +0.003 |
Neg logit contributions | |
ained | -0.004 |
THE | -0.004 |
Ag | -0.004 |
Prin | -0.004 |
ust | -0.004 |
Token | It |
Token ID | 632 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
hands | +0.028 |
sle | +0.027 |
paws | +0.026 |
fingers | +0.024 |
apr | +0.024 |
Neg logit contributions | |
ained | -0.036 |
Ag | -0.032 |
THE | -0.031 |
ectar | -0.031 |
ust | -0.031 |
Token | 's |
Token ID | 338 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
hands | +0.049 |
sle | +0.048 |
paws | +0.044 |
fingers | +0.039 |
pans | +0.038 |
Neg logit contributions | |
ained | -0.119 |
Ag | -0.109 |
ectar | -0.106 |
perspective | -0.106 |
THE | -0.106 |
Token | called |
Token ID | 1444 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
hands | +0.020 |
sle | +0.020 |
paws | +0.019 |
fingers | +0.017 |
Daddy | +0.017 |
Neg logit contributions | |
ained | -0.035 |
Ag | -0.033 |
perspective | -0.031 |
THE | -0.031 |
Kay | -0.031 |
Token | The |
Token ID | 383 |
Feature activation | -3.76e-02 |
Pos logit contributions | |
hands | +0.064 |
sle | +0.063 |
paws | +0.059 |
fingers | +0.055 |
apr | +0.054 |
Neg logit contributions | |
ained | -0.119 |
Prin | -0.106 |
THE | -0.106 |
ectar | -0.106 |
Ag | -0.105 |
Token | Three |
Token ID | 7683 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
hands | +0.048 |
sle | +0.046 |
paws | +0.044 |
fingers | +0.041 |
apr | +0.041 |
Neg logit contributions | |
ained | -0.072 |
Ag | -0.063 |
THE | -0.063 |
Prin | -0.063 |
ectar | -0.063 |
Token | Little |
Token ID | 7703 |
Feature activation | -7.41e-02 |
Pos logit contributions | |
hands | +0.043 |
sle | +0.042 |
paws | +0.040 |
apr | +0.037 |
fingers | +0.037 |
Neg logit contributions | |
ained | -0.055 |
THE | -0.048 |
Ag | -0.048 |
ectar | -0.048 |
Prin | -0.048 |
Token | Pigs |
Token ID | 49210 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
sle | +0.099 |
hands | +0.099 |
paws | +0.093 |
fingers | +0.086 |
apr | +0.086 |
Neg logit contributions | |
ained | -0.133 |
Ag | -0.118 |
Prin | -0.116 |
ectar | -0.116 |
THE | -0.116 |
Token | . |
Token ID | 13 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
hands | +0.020 |
sle | +0.019 |
Daddy | +0.018 |
paws | +0.018 |
load | +0.017 |
Neg logit contributions | |
ained | -0.038 |
Ag | -0.037 |
Kay | -0.035 |
ust | -0.035 |
Prin | -0.034 |
Token | Do |
Token ID | 2141 |
Feature activation | +1.01e-03 |
Pos logit contributions | |
hands | +0.025 |
sle | +0.025 |
paws | +0.023 |
fingers | +0.022 |
apr | +0.022 |
Neg logit contributions | |
ained | -0.028 |
Ag | -0.024 |
THE | -0.024 |
ectar | -0.024 |
Prin | -0.024 |
Token | you |
Token ID | 345 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
ained | +0.002 |
THE | +0.002 |
Ag | +0.002 |
Prin | +0.002 |
ust | +0.002 |
Neg logit contributions | |
sle | -0.001 |
hands | -0.001 |
paws | -0.001 |
fingers | -0.001 |
apr | -0.001 |
Token | know |
Token ID | 760 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
ained | +0.007 |
Ag | +0.006 |
THE | +0.006 |
ectar | +0.006 |
Kay | +0.006 |
Neg logit contributions | |
hands | -0.008 |
paws | -0.007 |
sle | -0.007 |
fingers | -0.007 |
apr | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
hands | +0.025 |
sle | +0.024 |
paws | +0.023 |
fingers | +0.022 |
apr | +0.022 |
Neg logit contributions | |
ained | -0.033 |
Ag | -0.029 |
ectar | -0.028 |
THE | -0.028 |
Prin | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -1.81e-02 |
Pos logit contributions | |
hands | +0.022 |
sle | +0.021 |
paws | +0.020 |
apr | +0.019 |
Daddy | +0.019 |
Neg logit contributions | |
ained | -0.031 |
ectar | -0.027 |
Ag | -0.027 |
ust | -0.027 |
perspective | -0.027 |
Token | When |
Token ID | 2215 |
Feature activation | -4.41e-02 |
Pos logit contributions | |
hands | +0.025 |
apr | +0.024 |
paws | +0.023 |
Daddy | +0.022 |
pans | +0.022 |
Neg logit contributions | |
ained | -0.030 |
fault | -0.030 |
bows | -0.029 |
ier | -0.028 |
ectar | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | -3.71e-02 |
Pos logit contributions | |
hands | +0.064 |
paws | +0.058 |
Daddy | +0.057 |
sle | +0.057 |
fingers | +0.054 |
Neg logit contributions | |
ained | -0.081 |
ectar | -0.072 |
ust | -0.071 |
ala | -0.071 |
Prin | -0.070 |
Token | was |
Token ID | 373 |
Feature activation | -4.40e-02 |
Pos logit contributions | |
hands | +0.044 |
sle | +0.041 |
paws | +0.040 |
Daddy | +0.037 |
fingers | +0.036 |
Neg logit contributions | |
ained | -0.073 |
ectar | -0.067 |
perspective | -0.066 |
Ag | -0.065 |
ust | -0.064 |
Token | time |
Token ID | 640 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
sle | +0.067 |
hands | +0.067 |
paws | +0.064 |
fingers | +0.060 |
pans | +0.060 |
Neg logit contributions | |
ained | -0.075 |
THE | -0.063 |
Ag | -0.062 |
Prin | -0.061 |
ust | -0.061 |
Token | to |
Token ID | 284 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
hands | +0.107 |
sle | +0.100 |
paws | +0.095 |
Daddy | +0.091 |
fingers | +0.091 |
Neg logit contributions | |
ained | -0.132 |
Prin | -0.118 |
Ag | -0.117 |
ectar | -0.116 |
THE | -0.115 |
Token | go |
Token ID | 467 |
Feature activation | -5.43e-02 |
Pos logit contributions | |
hands | +0.039 |
sle | +0.038 |
paws | +0.035 |
fingers | +0.032 |
apr | +0.032 |
Neg logit contributions | |
ained | -0.085 |
THE | -0.077 |
Ag | -0.076 |
Prin | -0.075 |
ectar | -0.075 |
Token | home |
Token ID | 1363 |
Feature activation | -3.49e-02 |
Pos logit contributions | |
hands | +0.080 |
sle | +0.078 |
paws | +0.072 |
Daddy | +0.068 |
fingers | +0.066 |
Neg logit contributions | |
ained | -0.096 |
Prin | -0.086 |
ust | -0.085 |
ectar | -0.084 |
Ag | -0.083 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
hands | +0.031 |
sle | +0.028 |
paws | +0.026 |
Daddy | +0.026 |
fingers | +0.024 |
Neg logit contributions | |
ained | -0.084 |
Prin | -0.076 |
THE | -0.075 |
ust | -0.075 |
Ag | -0.074 |
Token | Jack |
Token ID | 3619 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
hands | +0.012 |
Daddy | +0.010 |
paws | +0.010 |
fingers | +0.009 |
Dad | +0.008 |
Neg logit contributions | |
ained | -0.033 |
ala | -0.030 |
ectar | -0.030 |
Prin | -0.029 |
ust | -0.029 |
Token | him |
Token ID | 683 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
hands | +0.041 |
sle | +0.040 |
paws | +0.040 |
fingers | +0.038 |
pans | +0.037 |
Neg logit contributions | |
Kay | -0.039 |
Prin | -0.039 |
ained | -0.039 |
Ag | -0.038 |
ala | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -7.36e-04 |
Pos logit contributions | |
hands | +0.036 |
sle | +0.034 |
paws | +0.032 |
Daddy | +0.029 |
fingers | +0.029 |
Neg logit contributions | |
ained | -0.066 |
Ag | -0.060 |
perspective | -0.058 |
ust | -0.058 |
Prin | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | -2.82e-03 |
Pos logit contributions | |
hands | +0.001 |
sle | +0.001 |
paws | +0.001 |
Daddy | +0.001 |
fingers | +0.001 |
Neg logit contributions | |
ained | -0.001 |
ust | -0.001 |
perspective | -0.001 |
THE | -0.001 |
Ag | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -6.62e-03 |
Pos logit contributions | |
hands | +0.004 |
sle | +0.004 |
paws | +0.004 |
apr | +0.004 |
fingers | +0.004 |
Neg logit contributions | |
ained | -0.005 |
Ag | -0.004 |
THE | -0.004 |
ectar | -0.004 |
ust | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | +4.69e-03 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.011 |
paws | +0.010 |
pans | +0.010 |
apr | +0.010 |
Neg logit contributions | |
ained | -0.011 |
ectar | -0.009 |
ust | -0.009 |
Ag | -0.009 |
perspective | -0.009 |
Token | Sir |
Token ID | 22788 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
ained | +0.007 |
Ag | +0.006 |
THE | +0.006 |
Prin | +0.006 |
Kay | +0.005 |
Neg logit contributions | |
hands | -0.008 |
sle | -0.008 |
paws | -0.008 |
fingers | -0.008 |
apr | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
sle | +0.101 |
hands | +0.097 |
apr | +0.096 |
paws | +0.092 |
pans | +0.090 |
Neg logit contributions | |
ained | -0.119 |
THE | -0.109 |
Prin | -0.107 |
ala | -0.107 |
ill | -0.106 |
Token | sir |
Token ID | 15967 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
hands | +0.014 |
sle | +0.013 |
paws | +0.013 |
apr | +0.012 |
fingers | +0.012 |
Neg logit contributions | |
ained | -0.020 |
Ag | -0.018 |
THE | -0.018 |
Prin | -0.017 |
ust | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
sle | +0.028 |
hands | +0.027 |
paws | +0.025 |
fingers | +0.022 |
Daddy | +0.022 |
Neg logit contributions | |
ained | -0.065 |
Ag | -0.058 |
THE | -0.057 |
ectar | -0.057 |
ust | -0.057 |
Token | can |
Token ID | 460 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
hands | +0.013 |
sle | +0.013 |
paws | +0.012 |
fingers | +0.011 |
apr | +0.011 |
Neg logit contributions | |
ained | -0.021 |
Ag | -0.018 |
THE | -0.018 |
ectar | -0.018 |
Prin | -0.018 |
Token | you |
Token ID | 345 |
Feature activation | +2.44e-03 |
Pos logit contributions | |
apr | +0.037 |
sle | +0.035 |
hands | +0.034 |
paws | +0.034 |
plates | +0.033 |
Neg logit contributions | |
Ag | -0.015 |
ila | -0.015 |
ala | -0.015 |
she | -0.014 |
Prin | -0.014 |
Token | He |
Token ID | 679 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
hands | +0.013 |
sle | +0.012 |
paws | +0.012 |
fingers | +0.011 |
apr | +0.011 |
Neg logit contributions | |
ained | -0.016 |
Ag | -0.014 |
THE | -0.014 |
ectar | -0.014 |
Prin | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
hands | +0.031 |
sle | +0.030 |
paws | +0.028 |
fingers | +0.027 |
apr | +0.027 |
Neg logit contributions | |
ained | -0.038 |
Ag | -0.034 |
THE | -0.033 |
Prin | -0.033 |
ectar | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +7.64e-03 |
Pos logit contributions | |
hands | +0.003 |
sle | +0.003 |
paws | +0.003 |
Daddy | +0.003 |
fingers | +0.003 |
Neg logit contributions | |
ained | -0.008 |
THE | -0.007 |
Ag | -0.007 |
ust | -0.007 |
ectar | -0.007 |
Token | " |
Token ID | 366 |
Feature activation | +6.05e-03 |
Pos logit contributions | |
ained | +0.014 |
Ag | +0.012 |
THE | +0.012 |
ectar | +0.012 |
Prin | +0.012 |
Neg logit contributions | |
hands | -0.011 |
sle | -0.010 |
paws | -0.010 |
fingers | -0.009 |
apr | -0.009 |
Token | Ho |
Token ID | 28900 |
Feature activation | -5.89e-02 |
Pos logit contributions | |
ained | +0.010 |
fault | +0.009 |
ectar | +0.009 |
olving | +0.008 |
perspective | +0.008 |
Neg logit contributions | |
sle | -0.010 |
hands | -0.009 |
Daddy | -0.009 |
pans | -0.009 |
apr | -0.008 |
Token | ho |
Token ID | 8169 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
sle | +0.071 |
hands | +0.069 |
paws | +0.068 |
apr | +0.066 |
pans | +0.064 |
Neg logit contributions | |
ained | -0.104 |
ala | -0.097 |
ectar | -0.094 |
ust | -0.092 |
THE | -0.092 |
Token | ho |
Token ID | 8169 |
Feature activation | -7.09e-02 |
Pos logit contributions | |
sle | +0.101 |
hands | +0.100 |
apr | +0.097 |
paws | +0.096 |
pans | +0.096 |
Neg logit contributions | |
ained | -0.119 |
ala | -0.109 |
ub | -0.104 |
THE | -0.104 |
ill | -0.104 |
Token | , |
Token ID | 11 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
sle | +0.090 |
hands | +0.088 |
apr | +0.088 |
pans | +0.086 |
paws | +0.085 |
Neg logit contributions | |
ained | -0.122 |
ala | -0.113 |
ub | -0.109 |
THE | -0.108 |
ill | -0.108 |
Token | hello |
Token ID | 23748 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
hands | +0.013 |
sle | +0.013 |
paws | +0.012 |
fingers | +0.011 |
apr | +0.011 |
Neg logit contributions | |
ained | -0.028 |
Ag | -0.025 |
THE | -0.024 |
ectar | -0.024 |
Prin | -0.024 |
Token | Lily |
Token ID | 20037 |
Feature activation | -9.37e-03 |
Pos logit contributions | |
hands | +0.041 |
sle | +0.041 |
paws | +0.037 |
Daddy | +0.035 |
fingers | +0.034 |
Neg logit contributions | |
ained | -0.073 |
Ag | -0.064 |
Prin | -0.063 |
THE | -0.063 |
ectar | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
hands | +0.009 |
sle | +0.009 |
paws | +0.008 |
Daddy | +0.008 |
nose | +0.007 |
Neg logit contributions | |
ained | -0.022 |
Ag | -0.020 |
Kay | -0.020 |
ust | -0.019 |
Prin | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
hands | +0.015 |
Daddy | +0.015 |
sle | +0.014 |
Dad | +0.014 |
Grand | +0.013 |
Neg logit contributions | |
ained | -0.032 |
ier | -0.029 |
ust | -0.029 |
ectar | -0.029 |
Ag | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
hands | +0.024 |
sle | +0.023 |
Daddy | +0.022 |
apr | +0.021 |
paws | +0.020 |
Neg logit contributions | |
ained | -0.049 |
ier | -0.044 |
ectar | -0.044 |
ust | -0.044 |
Ag | -0.043 |
Token | When |
Token ID | 2215 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
apr | +0.027 |
Daddy | +0.025 |
grand | +0.025 |
hands | +0.024 |
drive | +0.024 |
Neg logit contributions | |
ained | -0.048 |
ier | -0.047 |
fault | -0.046 |
ectar | -0.046 |
bows | -0.041 |
Token | it |
Token ID | 340 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
Daddy | +0.056 |
hands | +0.056 |
sle | +0.051 |
Grand | +0.050 |
Dad | +0.049 |
Neg logit contributions | |
ained | -0.092 |
ust | -0.083 |
umpy | -0.080 |
ectar | -0.080 |
lessly | -0.079 |
Token | was |
Token ID | 373 |
Feature activation | -4.46e-02 |
Pos logit contributions | |
hands | +0.039 |
sle | +0.037 |
paws | +0.036 |
Daddy | +0.033 |
fingers | +0.032 |
Neg logit contributions | |
ained | -0.067 |
perspective | -0.060 |
Ag | -0.059 |
ectar | -0.059 |
ust | -0.058 |
Token | time |
Token ID | 640 |
Feature activation | -7.31e-02 |
Pos logit contributions | |
hands | +0.068 |
sle | +0.067 |
paws | +0.064 |
fingers | +0.060 |
pans | +0.060 |
Neg logit contributions | |
ained | -0.076 |
Prin | -0.064 |
THE | -0.064 |
Ag | -0.063 |
ectar | -0.063 |
Token | to |
Token ID | 284 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
hands | +0.101 |
sle | +0.094 |
paws | +0.089 |
Daddy | +0.086 |
fingers | +0.085 |
Neg logit contributions | |
ained | -0.137 |
Prin | -0.122 |
Ag | -0.122 |
ust | -0.120 |
ectar | -0.120 |
Token | go |
Token ID | 467 |
Feature activation | -5.24e-02 |
Pos logit contributions | |
hands | +0.033 |
sle | +0.032 |
paws | +0.029 |
fingers | +0.026 |
apr | +0.026 |
Neg logit contributions | |
ained | -0.080 |
Ag | -0.072 |
ectar | -0.071 |
THE | -0.071 |
ust | -0.071 |
Token | home |
Token ID | 1363 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
hands | +0.074 |
sle | +0.074 |
paws | +0.068 |
Daddy | +0.064 |
fingers | +0.061 |
Neg logit contributions | |
ained | -0.097 |
ust | -0.086 |
Prin | -0.084 |
Ag | -0.083 |
perspective | -0.082 |
Token | , |
Token ID | 11 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
hands | +0.030 |
sle | +0.028 |
Daddy | +0.026 |
paws | +0.025 |
fingers | +0.022 |
Neg logit contributions | |
ained | -0.091 |
THE | -0.082 |
Ag | -0.082 |
Prin | -0.082 |
ust | -0.081 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
Daddy | +0.014 |
hands | +0.013 |
Grand | +0.012 |
Mom | +0.012 |
Dad | +0.012 |
Neg logit contributions | |
ained | -0.032 |
ust | -0.029 |
ectar | -0.029 |
ying | -0.028 |
eway | -0.028 |
Token | her |
Token ID | 607 |
Feature activation | +7.05e-03 |
Pos logit contributions | |
hands | +0.036 |
sle | +0.035 |
paws | +0.033 |
Daddy | +0.031 |
fingers | +0.031 |
Neg logit contributions | |
ained | -0.049 |
THE | -0.042 |
Ag | -0.042 |
ust | -0.041 |
ectar | -0.041 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.48e-03 |
Pos logit contributions | |
ained | +0.022 |
Ag | +0.020 |
ust | +0.019 |
THE | +0.019 |
Prin | +0.019 |
Neg logit contributions | |
hands | -0.003 |
Daddy | -0.002 |
sle | -0.002 |
paws | -0.002 |
Dad | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +5.32e-03 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.010 |
Daddy | +0.010 |
forks | +0.010 |
paws | +0.010 |
Neg logit contributions | |
ained | -0.017 |
Ag | -0.016 |
ust | -0.014 |
Prin | -0.014 |
perspective | -0.014 |
Token | " |
Token ID | 366 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ained | +0.011 |
Ag | +0.010 |
ust | +0.010 |
perspective | +0.010 |
Prin | +0.010 |
Neg logit contributions | |
hands | -0.006 |
sle | -0.006 |
Daddy | -0.005 |
paws | -0.005 |
fingers | -0.005 |
Token | Are |
Token ID | 8491 |
Feature activation | -5.21e-03 |
Pos logit contributions | |
ained | +0.018 |
ectar | +0.015 |
fault | +0.015 |
ust | +0.015 |
Ag | +0.014 |
Neg logit contributions | |
sle | -0.016 |
hands | -0.015 |
apr | -0.015 |
pans | -0.014 |
forks | -0.014 |
Token | they |
Token ID | 484 |
Feature activation | -7.30e-02 |
Pos logit contributions | |
sle | +0.006 |
hands | +0.006 |
paws | +0.006 |
apr | +0.005 |
fingers | +0.005 |
Neg logit contributions | |
ained | -0.010 |
Ag | -0.009 |
THE | -0.009 |
Prin | -0.009 |
ectar | -0.009 |
Token | safe |
Token ID | 3338 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
hands | +0.115 |
sle | +0.109 |
paws | +0.106 |
Daddy | +0.102 |
forks | +0.100 |
Neg logit contributions | |
ained | -0.121 |
Ag | -0.105 |
perspective | -0.105 |
Prin | -0.105 |
Kay | -0.101 |
Token | ?". |
Token ID | 43634 |
Feature activation | -1.97e-03 |
Pos logit contributions | |
hands | +0.041 |
sle | +0.040 |
paws | +0.037 |
fingers | +0.034 |
Daddy | +0.034 |
Neg logit contributions | |
ained | -0.062 |
Ag | -0.055 |
Prin | -0.055 |
ust | -0.054 |
THE | -0.054 |
Token | Her |
Token ID | 2332 |
Feature activation | -3.29e-03 |
Pos logit contributions | |
hands | +0.003 |
Daddy | +0.002 |
paws | +0.002 |
sle | +0.002 |
fingers | +0.002 |
Neg logit contributions | |
ained | -0.004 |
ust | -0.003 |
ier | -0.003 |
THE | -0.003 |
Ag | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.90e-03 |
Pos logit contributions | |
sle | +0.003 |
apr | +0.002 |
hands | +0.002 |
pans | +0.002 |
paws | +0.002 |
Neg logit contributions | |
ained | -0.007 |
ectar | -0.006 |
Kay | -0.006 |
fault | -0.006 |
THE | -0.006 |
Token | put |
Token ID | 1234 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
ained | +0.003 |
Prin | +0.003 |
Ag | +0.003 |
THE | +0.003 |
ust | +0.003 |
Neg logit contributions | |
sle | -0.003 |
hands | -0.003 |
paws | -0.002 |
apr | -0.002 |
fingers | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
hands | +0.017 |
paws | +0.015 |
Daddy | +0.014 |
sle | +0.014 |
Dad | +0.013 |
Neg logit contributions | |
ained | -0.028 |
perspective | -0.026 |
Prin | -0.025 |
Ag | -0.025 |
THE | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
hands | +0.012 |
Daddy | +0.011 |
paws | +0.011 |
apr | +0.011 |
sle | +0.011 |
Neg logit contributions | |
ained | -0.028 |
ier | -0.025 |
fault | -0.025 |
ust | -0.024 |
ectar | -0.024 |
Token | But |
Token ID | 1537 |
Feature activation | -2.32e-02 |
Pos logit contributions | |
apr | +0.016 |
hands | +0.016 |
pans | +0.015 |
Daddy | +0.015 |
paws | +0.014 |
Neg logit contributions | |
ained | -0.023 |
fault | -0.023 |
ier | -0.021 |
bows | -0.020 |
ectar | -0.020 |
Token | then |
Token ID | 788 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
hands | +0.026 |
Daddy | +0.022 |
paws | +0.022 |
sle | +0.020 |
fingers | +0.020 |
Neg logit contributions | |
ained | -0.054 |
ust | -0.049 |
ectar | -0.048 |
Ag | -0.048 |
Prin | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | -9.58e-04 |
Pos logit contributions | |
hands | +0.014 |
Daddy | +0.012 |
paws | +0.012 |
sle | +0.011 |
Dad | +0.010 |
Neg logit contributions | |
ained | -0.034 |
ectar | -0.030 |
ust | -0.029 |
THE | -0.028 |
Acc | -0.028 |
Token | Little |
Token ID | 7703 |
Feature activation | -7.26e-02 |
Pos logit contributions | |
hands | +0.001 |
Daddy | +0.001 |
Dad | +0.001 |
paws | +0.001 |
Mom | +0.001 |
Neg logit contributions | |
ained | -0.002 |
ust | -0.002 |
ectar | -0.002 |
umpy | -0.002 |
perspective | -0.002 |
Token | Jack |
Token ID | 3619 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
hands | +0.079 |
sle | +0.079 |
paws | +0.073 |
apr | +0.068 |
fingers | +0.067 |
Neg logit contributions | |
ained | -0.150 |
Ag | -0.134 |
THE | -0.133 |
Prin | -0.132 |
ectar | -0.131 |
Token | noticed |
Token ID | 6810 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
hands | +0.024 |
paws | +0.023 |
sle | +0.022 |
fingers | +0.021 |
Daddy | +0.020 |
Neg logit contributions | |
ained | -0.039 |
ectar | -0.035 |
THE | -0.033 |
Ag | -0.033 |
perspective | -0.033 |
Token | that |
Token ID | 326 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
ained | +0.024 |
ectar | +0.022 |
ust | +0.022 |
THE | +0.021 |
Prin | +0.021 |
Neg logit contributions | |
hands | -0.010 |
Daddy | -0.010 |
paws | -0.009 |
sle | -0.008 |
Dad | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +4.41e-04 |
Pos logit contributions | |
ained | +0.027 |
ust | +0.025 |
THE | +0.025 |
ectar | +0.024 |
Ag | +0.024 |
Neg logit contributions | |
hands | -0.010 |
Daddy | -0.010 |
Dad | -0.008 |
paws | -0.008 |
forks | -0.008 |
Token | flowers |
Token ID | 12734 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ained | +0.001 |
ust | +0.001 |
THE | +0.001 |
ectar | +0.001 |
ill | +0.001 |
Neg logit contributions | |
hands | -0.000 |
sle | -0.000 |
paws | -0.000 |
fingers | -0.000 |
white | -0.000 |
Token | um |
Token ID | 388 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
hands | +0.038 |
sle | +0.037 |
paws | +0.034 |
apr | +0.032 |
fingers | +0.032 |
Neg logit contributions | |
ained | -0.067 |
Ag | -0.060 |
THE | -0.059 |
ectar | -0.059 |
ust | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
sle | +0.031 |
hands | +0.031 |
paws | +0.029 |
apr | +0.028 |
fingers | +0.027 |
Neg logit contributions | |
ained | -0.038 |
THE | -0.034 |
Prin | -0.034 |
Ag | -0.034 |
ust | -0.033 |
Token | Dad |
Token ID | 17415 |
Feature activation | -2.58e-02 |
Pos logit contributions | |
sle | +0.021 |
hands | +0.019 |
paws | +0.016 |
apr | +0.013 |
fingers | +0.013 |
Neg logit contributions | |
ained | -0.097 |
Ag | -0.090 |
THE | -0.088 |
Prin | -0.088 |
ectar | -0.088 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.61e-03 |
Pos logit contributions | |
hands | +0.035 |
sle | +0.035 |
paws | +0.033 |
apr | +0.031 |
fingers | +0.031 |
Neg logit contributions | |
ained | -0.046 |
Ag | -0.041 |
THE | -0.040 |
Prin | -0.040 |
ectar | -0.040 |
Token | at |
Token ID | 379 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
hands | +0.002 |
sle | +0.002 |
paws | +0.002 |
fingers | +0.002 |
Daddy | +0.002 |
Neg logit contributions | |
ained | -0.003 |
Ag | -0.003 |
ectar | -0.003 |
THE | -0.003 |
Prin | -0.003 |
Token | Little |
Token ID | 7703 |
Feature activation | -7.25e-02 |
Pos logit contributions | |
hands | +0.013 |
sle | +0.012 |
paws | +0.012 |
fingers | +0.011 |
apr | +0.011 |
Neg logit contributions | |
ained | -0.025 |
ectar | -0.022 |
Ag | -0.022 |
Prin | -0.022 |
THE | -0.022 |
Token | Johnny |
Token ID | 15470 |
Feature activation | -2.11e-02 |
Pos logit contributions | |
sle | +0.086 |
hands | +0.086 |
paws | +0.079 |
apr | +0.073 |
fingers | +0.073 |
Neg logit contributions | |
ained | -0.145 |
Ag | -0.129 |
THE | -0.127 |
Prin | -0.125 |
ectar | -0.124 |
Token | and |
Token ID | 290 |
Feature activation | -2.22e-02 |
Pos logit contributions | |
hands | +0.027 |
sle | +0.027 |
paws | +0.025 |
fingers | +0.024 |
apr | +0.023 |
Neg logit contributions | |
ained | -0.041 |
Ag | -0.036 |
THE | -0.035 |
ectar | -0.035 |
Prin | -0.035 |
Token | said |
Token ID | 531 |
Feature activation | -3.78e-04 |
Pos logit contributions | |
hands | +0.025 |
sle | +0.024 |
paws | +0.023 |
fingers | +0.021 |
Daddy | +0.021 |
Neg logit contributions | |
ained | -0.047 |
THE | -0.041 |
ectar | -0.041 |
Ag | -0.041 |
Prin | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | +8.83e-03 |
Pos logit contributions | |
hands | +0.000 |
paws | +0.000 |
sle | +0.000 |
Daddy | +0.000 |
cheeks | +0.000 |
Neg logit contributions | |
ained | -0.001 |
THE | -0.001 |
Prin | -0.001 |
ectar | -0.001 |
ust | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | -1.18e-03 |
Pos logit contributions | |
ained | +0.018 |
ectar | +0.016 |
ust | +0.016 |
Prin | +0.016 |
THE | +0.016 |
Neg logit contributions | |
hands | -0.011 |
sle | -0.010 |
paws | -0.010 |
Daddy | -0.009 |
fingers | -0.009 |
Token | big |
Token ID | 1263 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
hands | +0.013 |
sle | +0.012 |
paws | +0.012 |
fingers | +0.011 |
pans | +0.010 |
Neg logit contributions | |
ained | -0.020 |
Ag | -0.017 |
THE | -0.017 |
Prin | -0.017 |
ectar | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
hands | +0.014 |
sle | +0.013 |
paws | +0.012 |
fingers | +0.011 |
forks | +0.011 |
Neg logit contributions | |
ained | -0.023 |
Ag | -0.021 |
THE | -0.020 |
ust | -0.020 |
Prin | -0.020 |
Token | bright |
Token ID | 6016 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.011 |
paws | +0.010 |
apr | +0.010 |
fingers | +0.009 |
Neg logit contributions | |
ained | -0.023 |
Ag | -0.021 |
THE | -0.021 |
ectar | -0.021 |
Prin | -0.021 |
Token | light |
Token ID | 1657 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
hands | +0.041 |
sle | +0.039 |
paws | +0.036 |
fingers | +0.034 |
pans | +0.033 |
Neg logit contributions | |
ained | -0.082 |
Ag | -0.073 |
THE | -0.072 |
ust | -0.072 |
Prin | -0.071 |
Token | was |
Token ID | 373 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
hands | +0.025 |
sle | +0.025 |
paws | +0.023 |
fingers | +0.022 |
pans | +0.021 |
Neg logit contributions | |
ained | -0.040 |
Ag | -0.036 |
Prin | -0.035 |
THE | -0.035 |
ust | -0.035 |
Token | streaming |
Token ID | 11305 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
hands | +0.017 |
sle | +0.017 |
paws | +0.015 |
Daddy | +0.015 |
fingers | +0.014 |
Neg logit contributions | |
ained | -0.032 |
Ag | -0.029 |
THE | -0.029 |
perspective | -0.028 |
ust | -0.028 |
Token | through |
Token ID | 832 |
Feature activation | -9.37e-03 |
Pos logit contributions | |
hands | +0.097 |
sle | +0.096 |
paws | +0.091 |
apr | +0.086 |
fingers | +0.085 |
Neg logit contributions | |
ained | -0.132 |
Ag | -0.115 |
THE | -0.114 |
ectar | -0.113 |
Prin | -0.113 |
Token | her |
Token ID | 607 |
Feature activation | +2.49e-03 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.010 |
paws | +0.009 |
fingers | +0.009 |
pans | +0.008 |
Neg logit contributions | |
ained | -0.020 |
Ag | -0.018 |
THE | -0.018 |
ectar | -0.018 |
Prin | -0.017 |
Token | curtains |
Token ID | 41160 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
ained | +0.006 |
ectar | +0.006 |
THE | +0.006 |
ust | +0.006 |
perspective | +0.006 |
Neg logit contributions | |
sle | -0.001 |
apr | -0.001 |
hands | -0.001 |
pans | -0.001 |
forks | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.03e-03 |
Pos logit contributions | |
ained | +0.060 |
Ag | +0.056 |
Kay | +0.053 |
Prin | +0.052 |
known | +0.052 |
Neg logit contributions | |
hands | -0.035 |
sle | -0.032 |
paws | -0.031 |
fingers | -0.030 |
plates | -0.029 |
Token | It |
Token ID | 632 |
Feature activation | -1.35e-02 |
Pos logit contributions | |
hands | +0.001 |
sle | +0.001 |
paws | +0.001 |
apr | +0.001 |
fingers | +0.001 |
Neg logit contributions | |
ained | -0.002 |
Ag | -0.002 |
THE | -0.002 |
Prin | -0.002 |
ectar | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
ained | +0.030 |
THE | +0.027 |
ectar | +0.027 |
ust | +0.027 |
ount | +0.026 |
Neg logit contributions | |
hands | -0.022 |
paws | -0.019 |
fingers | -0.018 |
help | -0.017 |
white | -0.017 |
Token | offer |
Token ID | 2897 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
ained | +0.050 |
ectar | +0.044 |
Ag | +0.043 |
ount | +0.043 |
ust | +0.042 |
Neg logit contributions | |
hands | -0.019 |
help | -0.018 |
paws | -0.017 |
load | -0.016 |
sle | -0.015 |
Token | ; |
Token ID | 26 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
hands | +0.023 |
paws | +0.021 |
sle | +0.020 |
fingers | +0.019 |
Daddy | +0.019 |
Neg logit contributions | |
ained | -0.037 |
ust | -0.032 |
Ag | -0.032 |
THE | -0.031 |
Prin | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
hands | +0.027 |
Daddy | +0.024 |
paws | +0.023 |
sle | +0.022 |
fingers | +0.022 |
Neg logit contributions | |
ained | -0.037 |
Ag | -0.032 |
Prin | -0.031 |
ount | -0.031 |
ust | -0.030 |
Token | sunlight |
Token ID | 19606 |
Feature activation | -1.77e-02 |
Pos logit contributions | |
ained | +0.004 |
ust | +0.004 |
Ag | +0.004 |
ectar | +0.004 |
ill | +0.004 |
Neg logit contributions | |
hands | -0.002 |
sle | -0.002 |
paws | -0.002 |
fingers | -0.002 |
white | -0.002 |
Token | streaming |
Token ID | 11305 |
Feature activation | -7.20e-02 |
Pos logit contributions | |
hands | +0.023 |
sle | +0.020 |
paws | +0.020 |
fingers | +0.019 |
Daddy | +0.019 |
Neg logit contributions | |
ained | -0.034 |
Ag | -0.032 |
Prin | -0.032 |
ust | -0.031 |
Kay | -0.031 |
Token | through |
Token ID | 832 |
Feature activation | -7.47e-03 |
Pos logit contributions | |
hands | +0.095 |
sle | +0.086 |
paws | +0.084 |
fingers | +0.080 |
Daddy | +0.075 |
Neg logit contributions | |
ained | -0.145 |
Ag | -0.130 |
THE | -0.129 |
Prin | -0.128 |
ectar | -0.128 |
Token | the |
Token ID | 262 |
Feature activation | +1.11e-03 |
Pos logit contributions | |
hands | +0.010 |
paws | +0.008 |
sle | +0.008 |
fingers | +0.008 |
Daddy | +0.008 |
Neg logit contributions | |
ained | -0.016 |
Ag | -0.014 |
ust | -0.014 |
THE | -0.014 |
ectar | -0.014 |
Token | trees |
Token ID | 7150 |
Feature activation | +6.13e-03 |
Pos logit contributions | |
ained | +0.002 |
Ag | +0.002 |
ectar | +0.002 |
ust | +0.002 |
THE | +0.002 |
Neg logit contributions | |
hands | -0.001 |
sle | -0.001 |
paws | -0.001 |
fingers | -0.001 |
pans | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +4.12e-03 |
Pos logit contributions | |
ained | +0.013 |
Ag | +0.012 |
Kay | +0.012 |
Prin | +0.012 |
ust | +0.012 |
Neg logit contributions | |
hands | -0.007 |
sle | -0.006 |
paws | -0.006 |
fingers | -0.006 |
nose | -0.005 |
Token | birds |
Token ID | 10087 |
Feature activation | -7.71e-04 |
Pos logit contributions | |
ained | +0.009 |
ust | +0.008 |
Ag | +0.008 |
ala | +0.008 |
THE | +0.007 |
Neg logit contributions | |
hands | -0.005 |
paws | -0.005 |
sle | -0.005 |
fingers | -0.005 |
white | -0.004 |
Token | ever |
Token ID | 1683 |
Feature activation | -3.61e-03 |
Pos logit contributions | |
hands | +0.022 |
sle | +0.019 |
paws | +0.018 |
fingers | +0.018 |
Daddy | +0.018 |
Neg logit contributions | |
ained | -0.031 |
Prin | -0.029 |
ust | -0.027 |
THE | -0.026 |
eway | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
hands | +0.004 |
paws | +0.003 |
sle | +0.003 |
fingers | +0.003 |
Daddy | +0.003 |
Neg logit contributions | |
ained | -0.008 |
Prin | -0.007 |
Ag | -0.007 |
ectar | -0.007 |
Kay | -0.007 |
Token | when |
Token ID | 618 |
Feature activation | -3.10e-02 |
Pos logit contributions | |
hands | +0.016 |
Daddy | +0.014 |
paws | +0.013 |
sle | +0.013 |
Dad | +0.013 |
Neg logit contributions | |
ained | -0.026 |
ectar | -0.024 |
perspective | -0.024 |
ust | -0.024 |
Prin | -0.024 |
Token | the |
Token ID | 262 |
Feature activation | -4.65e-04 |
Pos logit contributions | |
hands | +0.038 |
sle | +0.035 |
Daddy | +0.035 |
paws | +0.033 |
Dad | +0.031 |
Neg logit contributions | |
ained | -0.061 |
ectar | -0.057 |
ust | -0.057 |
Prin | -0.056 |
ount | -0.054 |
Token | sun |
Token ID | 4252 |
Feature activation | -3.50e-02 |
Pos logit contributions | |
hands | +0.001 |
sle | +0.001 |
paws | +0.001 |
fingers | +0.000 |
pans | +0.000 |
Neg logit contributions | |
ained | -0.001 |
Ag | -0.001 |
ectar | -0.001 |
THE | -0.001 |
ust | -0.001 |
Token | went |
Token ID | 1816 |
Feature activation | -7.19e-02 |
Pos logit contributions | |
hands | +0.039 |
sle | +0.038 |
paws | +0.035 |
Daddy | +0.034 |
cheeks | +0.032 |
Neg logit contributions | |
ained | -0.072 |
ust | -0.069 |
perspective | -0.068 |
ectar | -0.067 |
Ag | -0.066 |
Token | down |
Token ID | 866 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
sle | +0.069 |
hands | +0.066 |
Daddy | +0.060 |
paws | +0.057 |
white | +0.055 |
Neg logit contributions | |
ust | -0.156 |
ectar | -0.152 |
ained | -0.151 |
perspective | -0.150 |
fault | -0.149 |
Token | Tommy |
Token ID | 19919 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
hands | +0.039 |
Daddy | +0.038 |
sle | +0.034 |
Dad | +0.034 |
white | +0.030 |
Neg logit contributions | |
ust | -0.106 |
ained | -0.102 |
ectar | -0.099 |
perspective | -0.098 |
Acc | -0.096 |
Token | and |
Token ID | 290 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
hands | +0.034 |
sle | +0.032 |
paws | +0.031 |
fingers | +0.028 |
Daddy | +0.028 |
Neg logit contributions | |
ained | -0.055 |
Ag | -0.050 |
ectar | -0.049 |
Prin | -0.049 |
ust | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +4.05e-04 |
Pos logit contributions | |
hands | +0.033 |
sle | +0.031 |
Daddy | +0.029 |
paws | +0.029 |
Dad | +0.026 |
Neg logit contributions | |
ained | -0.068 |
ectar | -0.063 |
ust | -0.062 |
perspective | -0.062 |
Ag | -0.059 |
Token | queen |
Token ID | 16599 |
Feature activation | -2.35e-04 |
Pos logit contributions | |
ained | +0.001 |
ectar | +0.001 |
Ag | +0.001 |
ust | +0.001 |
THE | +0.001 |
Neg logit contributions | |
hands | -0.000 |
sle | -0.000 |
paws | -0.000 |
fingers | -0.000 |
apr | -0.000 |
Token | would |
Token ID | 561 |
Feature activation | -2.44e-03 |
Pos logit contributions | |
ained | +0.057 |
Prin | +0.050 |
ala | +0.049 |
perspective | +0.049 |
Kay | +0.048 |
Neg logit contributions | |
help | -0.031 |
load | -0.030 |
drive | -0.029 |
hands | -0.028 |
t | -0.028 |
Token | love |
Token ID | 1842 |
Feature activation | -3.44e-03 |
Pos logit contributions | |
hands | +0.004 |
sle | +0.004 |
paws | +0.004 |
fingers | +0.003 |
cheeks | +0.003 |
Neg logit contributions | |
ained | -0.004 |
Ag | -0.003 |
THE | -0.003 |
Prin | -0.003 |
ectar | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
hands | +0.006 |
sle | +0.006 |
paws | +0.006 |
apr | +0.006 |
cheeks | +0.006 |
Neg logit contributions | |
ained | -0.004 |
THE | -0.004 |
Ag | -0.004 |
ectar | -0.004 |
perspective | -0.004 |
Token | play |
Token ID | 711 |
Feature activation | -2.03e-03 |
Pos logit contributions | |
ained | +0.030 |
Ag | +0.027 |
THE | +0.026 |
ectar | +0.026 |
Prin | +0.026 |
Neg logit contributions | |
hands | -0.015 |
sle | -0.014 |
paws | -0.013 |
fingers | -0.012 |
apr | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | +1.72e-03 |
Pos logit contributions | |
hands | +0.003 |
sle | +0.003 |
paws | +0.003 |
apr | +0.002 |
pans | +0.002 |
Neg logit contributions | |
ained | -0.004 |
ust | -0.003 |
perspective | -0.003 |
Kay | -0.003 |
Ag | -0.003 |
Token | Big |
Token ID | 4403 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
ained | +0.003 |
THE | +0.002 |
Prin | +0.002 |
ectar | +0.002 |
Ag | +0.002 |
Neg logit contributions | |
sle | -0.002 |
hands | -0.002 |
apr | -0.002 |
chin | -0.002 |
cheeks | -0.002 |
Token | gie |
Token ID | 22699 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
apr | +0.112 |
hands | +0.106 |
plates | +0.105 |
sle | +0.105 |
forks | +0.105 |
Neg logit contributions | |
ained | -0.108 |
inas | -0.095 |
bows | -0.092 |
Ag | -0.087 |
perspective | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +2.26e-05 |
Pos logit contributions | |
hands | +0.022 |
paws | +0.021 |
sle | +0.019 |
nose | +0.018 |
fingers | +0.018 |
Neg logit contributions | |
ained | -0.038 |
Ag | -0.037 |
Kay | -0.037 |
Prin | -0.035 |
pour | -0.034 |
Token | He |
Token ID | 679 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
ained | +0.000 |
THE | +0.000 |
Ag | +0.000 |
ectar | +0.000 |
Prin | +0.000 |
Neg logit contributions | |
hands | -0.000 |
sle | -0.000 |
apr | -0.000 |
paws | -0.000 |
fingers | -0.000 |
Token | is |
Token ID | 318 |
Feature activation | -5.04e-03 |
Pos logit contributions | |
hands | +0.024 |
sle | +0.024 |
paws | +0.023 |
apr | +0.022 |
fingers | +0.021 |
Neg logit contributions | |
ained | -0.031 |
Ag | -0.027 |
THE | -0.027 |
ectar | -0.026 |
Prin | -0.026 |
Token | so |
Token ID | 523 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
hands | +0.005 |
sle | +0.005 |
paws | +0.005 |
Daddy | +0.004 |
pans | +0.004 |
Neg logit contributions | |
ained | -0.011 |
Ag | -0.010 |
perspective | -0.010 |
ust | -0.010 |
THE | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -2.23e-02 |
Pos logit contributions | |
hands | +0.004 |
sle | +0.004 |
paws | +0.003 |
fingers | +0.003 |
nose | +0.003 |
Neg logit contributions | |
ained | -0.007 |
Ag | -0.006 |
Prin | -0.006 |
Kay | -0.006 |
ust | -0.006 |
Token | made |
Token ID | 925 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
hands | +0.029 |
sle | +0.028 |
paws | +0.026 |
fingers | +0.024 |
apr | +0.024 |
Neg logit contributions | |
ained | -0.044 |
THE | -0.038 |
ectar | -0.038 |
Ag | -0.038 |
ust | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
hands | +0.031 |
sle | +0.027 |
paws | +0.026 |
Daddy | +0.025 |
fingers | +0.025 |
Neg logit contributions | |
ained | -0.067 |
Ag | -0.060 |
THE | -0.060 |
ust | -0.059 |
perspective | -0.059 |
Token | wish |
Token ID | 4601 |
Feature activation | +1.19e-03 |
Pos logit contributions | |
hands | +0.030 |
sle | +0.030 |
paws | +0.027 |
fingers | +0.026 |
Daddy | +0.024 |
Neg logit contributions | |
ained | -0.059 |
Ag | -0.051 |
ectar | -0.050 |
THE | -0.049 |
ust | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
ained | +0.003 |
Prin | +0.002 |
Ag | +0.002 |
ust | +0.002 |
Kay | +0.002 |
Neg logit contributions | |
hands | -0.001 |
sle | -0.001 |
fingers | -0.001 |
paws | -0.001 |
nose | -0.001 |
Token | Little |
Token ID | 7703 |
Feature activation | -7.17e-02 |
Pos logit contributions | |
hands | +0.030 |
Daddy | +0.028 |
paws | +0.026 |
sle | +0.026 |
Dad | +0.025 |
Neg logit contributions | |
ained | -0.055 |
ectar | -0.048 |
perspective | -0.048 |
ust | -0.048 |
Ag | -0.048 |
Token | Jack |
Token ID | 3619 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
sle | +0.080 |
hands | +0.080 |
paws | +0.073 |
apr | +0.068 |
fingers | +0.068 |
Neg logit contributions | |
ained | -0.147 |
Ag | -0.131 |
THE | -0.130 |
Prin | -0.129 |
ectar | -0.128 |
Token | wished |
Token ID | 16555 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
hands | +0.016 |
sle | +0.015 |
paws | +0.015 |
fingers | +0.014 |
cheeks | +0.013 |
Neg logit contributions | |
ained | -0.026 |
Ag | -0.023 |
ectar | -0.023 |
THE | -0.022 |
ust | -0.022 |
Token | for |
Token ID | 329 |
Feature activation | -3.49e-04 |
Pos logit contributions | |
hands | +0.015 |
Daddy | +0.014 |
sle | +0.013 |
paws | +0.013 |
fingers | +0.012 |
Neg logit contributions | |
ained | -0.026 |
Prin | -0.023 |
Ag | -0.022 |
ust | -0.022 |
ectar | -0.022 |
Token | more |
Token ID | 517 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
hands | +0.000 |
sle | +0.000 |
paws | +0.000 |
apr | +0.000 |
fingers | +0.000 |
Neg logit contributions | |
ained | -0.001 |
THE | -0.001 |
ectar | -0.001 |
Ag | -0.001 |
Prin | -0.001 |
Token | days |
Token ID | 1528 |
Feature activation | -2.59e-02 |
Pos logit contributions | |
ained | +0.057 |
Ag | +0.049 |
Prin | +0.048 |
THE | +0.048 |
ectar | +0.047 |
Neg logit contributions | |
hands | -0.036 |
sle | -0.034 |
paws | -0.032 |
fingers | -0.031 |
Daddy | -0.029 |
Token | why |
Token ID | 1521 |
Feature activation | +6.27e-03 |
Pos logit contributions | |
hands | +0.051 |
sle | +0.048 |
paws | +0.046 |
Daddy | +0.044 |
fingers | +0.044 |
Neg logit contributions | |
ained | -0.065 |
Ag | -0.056 |
THE | -0.056 |
Prin | -0.056 |
ectar | -0.055 |
Token | Tom |
Token ID | 4186 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
ained | +0.012 |
Prin | +0.012 |
perspective | +0.011 |
Ag | +0.011 |
ust | +0.011 |
Neg logit contributions | |
hands | -0.008 |
Daddy | -0.008 |
Dad | -0.007 |
Mom | -0.007 |
paws | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
hands | +0.017 |
sle | +0.016 |
paws | +0.015 |
load | +0.015 |
Daddy | +0.014 |
Neg logit contributions | |
ained | -0.030 |
Ag | -0.028 |
ectar | -0.028 |
perspective | -0.028 |
THE | -0.027 |
Token | Jen |
Token ID | 13364 |
Feature activation | -1.95e-03 |
Pos logit contributions | |
hands | +0.053 |
sle | +0.050 |
paws | +0.049 |
fingers | +0.048 |
apr | +0.047 |
Neg logit contributions | |
ained | -0.039 |
THE | -0.032 |
Prin | -0.032 |
Ag | -0.032 |
ectar | -0.032 |
Token | did |
Token ID | 750 |
Feature activation | +3.00e-02 |
Pos logit contributions | |
hands | +0.003 |
paws | +0.002 |
sle | +0.002 |
cheeks | +0.002 |
fingers | +0.002 |
Neg logit contributions | |
ained | -0.004 |
Ag | -0.003 |
ectar | -0.003 |
THE | -0.003 |
perspective | -0.003 |
Token | such |
Token ID | 884 |
Feature activation | +8.35e-02 |
Pos logit contributions | |
ained | +0.059 |
ectar | +0.055 |
Prin | +0.053 |
perspective | +0.053 |
Ag | +0.052 |
Neg logit contributions | |
hands | -0.039 |
help | -0.035 |
Daddy | -0.034 |
load | -0.033 |
paws | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
ained | +0.182 |
Ag | +0.161 |
THE | +0.161 |
ectar | +0.160 |
Prin | +0.159 |
Neg logit contributions | |
hands | -0.086 |
sle | -0.085 |
paws | -0.078 |
fingers | -0.072 |
apr | -0.071 |
Token | silly |
Token ID | 14397 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
ained | +0.034 |
Ag | +0.029 |
THE | +0.029 |
ectar | +0.029 |
Prin | +0.028 |
Neg logit contributions | |
hands | -0.030 |
sle | -0.030 |
paws | -0.028 |
fingers | -0.027 |
apr | -0.027 |
Token | thing |
Token ID | 1517 |
Feature activation | +1.65e-02 |
Pos logit contributions | |
ained | +0.038 |
Prin | +0.035 |
THE | +0.034 |
Ag | +0.034 |
ectar | +0.033 |
Neg logit contributions | |
hands | -0.032 |
sle | -0.030 |
paws | -0.029 |
fingers | -0.027 |
cheeks | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +7.10e-03 |
Pos logit contributions | |
ained | +0.037 |
Prin | +0.035 |
perspective | +0.035 |
Kay | +0.035 |
Ag | +0.035 |
Neg logit contributions | |
hands | -0.015 |
sle | -0.014 |
Daddy | -0.014 |
plates | -0.013 |
forks | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -1.86e-03 |
Pos logit contributions | |
ained | +0.015 |
perspective | +0.014 |
THE | +0.013 |
ust | +0.013 |
ectar | +0.013 |
Neg logit contributions | |
hands | -0.008 |
Daddy | -0.008 |
Dad | -0.008 |
paws | -0.007 |
sle | -0.007 |
Token | not |
Token ID | 407 |
Feature activation | +2.57e-02 |
Pos logit contributions | |
ained | +0.031 |
ount | +0.028 |
ectar | +0.028 |
ala | +0.027 |
perspective | +0.027 |
Neg logit contributions | |
hands | -0.020 |
paws | -0.018 |
help | -0.017 |
drive | -0.016 |
Daddy | -0.016 |
Token | ride |
Token ID | 6594 |
Feature activation | -6.23e-03 |
Pos logit contributions | |
ained | +0.057 |
Ag | +0.051 |
THE | +0.051 |
Prin | +0.050 |
ectar | +0.050 |
Neg logit contributions | |
hands | -0.028 |
sle | -0.026 |
paws | -0.026 |
fingers | -0.024 |
cheeks | -0.023 |
Token | his |
Token ID | 465 |
Feature activation | +4.55e-03 |
Pos logit contributions | |
hands | +0.007 |
paws | +0.007 |
sle | +0.007 |
fingers | +0.006 |
apr | +0.006 |
Neg logit contributions | |
ained | -0.013 |
ectar | -0.012 |
Ag | -0.012 |
perspective | -0.012 |
Prin | -0.012 |
Token | bike |
Token ID | 7161 |
Feature activation | -1.39e-03 |
Pos logit contributions | |
ained | +0.009 |
THE | +0.008 |
Ag | +0.008 |
ust | +0.008 |
perspective | +0.008 |
Neg logit contributions | |
sle | -0.005 |
hands | -0.005 |
paws | -0.005 |
apr | -0.005 |
pans | -0.005 |
Token | at |
Token ID | 379 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
hands | +0.002 |
drive | +0.002 |
paws | +0.002 |
sle | +0.002 |
load | +0.002 |
Neg logit contributions | |
ectar | -0.003 |
ained | -0.002 |
Ag | -0.002 |
Kay | -0.002 |
eway | -0.002 |
Token | such |
Token ID | 884 |
Feature activation | +9.01e-02 |
Pos logit contributions | |
ained | +0.025 |
Ag | +0.022 |
THE | +0.022 |
ectar | +0.022 |
Prin | +0.022 |
Neg logit contributions | |
hands | -0.016 |
sle | -0.016 |
paws | -0.015 |
fingers | -0.014 |
apr | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +9.10e-03 |
Pos logit contributions | |
ained | +0.235 |
ount | +0.221 |
ectar | +0.217 |
inas | +0.215 |
Ag | +0.213 |
Neg logit contributions | |
hands | -0.067 |
paws | -0.059 |
fingers | -0.048 |
Daddy | -0.044 |
sle | -0.041 |
Token | high |
Token ID | 1029 |
Feature activation | +2.48e-03 |
Pos logit contributions | |
ained | +0.020 |
ectar | +0.018 |
ala | +0.017 |
ount | +0.017 |
Ag | +0.017 |
Neg logit contributions | |
hands | -0.010 |
sle | -0.010 |
paws | -0.009 |
fingers | -0.008 |
load | -0.008 |
Token | speed |
Token ID | 2866 |
Feature activation | +4.94e-03 |
Pos logit contributions | |
ained | +0.005 |
Ag | +0.005 |
ectar | +0.004 |
Kay | +0.004 |
THE | +0.004 |
Neg logit contributions | |
hands | -0.003 |
sle | -0.003 |
paws | -0.003 |
fingers | -0.003 |
load | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +6.18e-04 |
Pos logit contributions | |
ectar | +0.011 |
Kay | +0.011 |
Ag | +0.010 |
ained | +0.010 |
Acc | +0.010 |
Neg logit contributions | |
hands | -0.005 |
load | -0.004 |
drive | -0.004 |
sle | -0.004 |
paws | -0.004 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -6.63e-03 |
Pos logit contributions | |
ained | +0.001 |
THE | +0.001 |
Ag | +0.001 |
ectar | +0.001 |
Prin | +0.001 |
Neg logit contributions | |
sle | -0.001 |
hands | -0.001 |
paws | -0.001 |
pans | -0.001 |
apr | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.53e-03 |
Pos logit contributions | |
hands | +0.005 |
sle | +0.004 |
paws | +0.004 |
fingers | +0.004 |
white | +0.004 |
Neg logit contributions | |
ained | -0.008 |
Ag | -0.007 |
fault | -0.007 |
ectar | -0.007 |
Prin | -0.007 |
Token | When |
Token ID | 1649 |
Feature activation | -2.54e-02 |
Pos logit contributions | |
ained | +0.003 |
Ag | +0.002 |
THE | +0.002 |
Prin | +0.002 |
ectar | +0.002 |
Neg logit contributions | |
hands | -0.002 |
sle | -0.002 |
paws | -0.002 |
apr | -0.002 |
fingers | -0.002 |
Token | he |
Token ID | 339 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
hands | +0.031 |
sle | +0.031 |
paws | +0.029 |
Daddy | +0.027 |
pans | +0.026 |
Neg logit contributions | |
ained | -0.053 |
ust | -0.047 |
ectar | -0.046 |
Ag | -0.045 |
ala | -0.044 |
Token | reached |
Token ID | 4251 |
Feature activation | -3.16e-02 |
Pos logit contributions | |
hands | +0.016 |
sle | +0.016 |
paws | +0.015 |
apr | +0.015 |
fingers | +0.015 |
Neg logit contributions | |
ained | -0.017 |
Prin | -0.016 |
THE | -0.016 |
Ag | -0.015 |
ala | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
hands | +0.035 |
sle | +0.035 |
paws | +0.032 |
fingers | +0.030 |
apr | +0.030 |
Neg logit contributions | |
ained | -0.066 |
Ag | -0.059 |
THE | -0.058 |
ectar | -0.058 |
Prin | -0.058 |
Token | tre |
Token ID | 2054 |
Feature activation | +7.06e-02 |
Pos logit contributions | |
ained | +0.020 |
Ag | +0.018 |
ectar | +0.018 |
THE | +0.018 |
ust | +0.017 |
Neg logit contributions | |
hands | -0.011 |
sle | -0.011 |
paws | -0.010 |
fingers | -0.010 |
apr | -0.010 |
Token | et |
Token ID | 316 |
Feature activation | -3.56e-03 |
Pos logit contributions | |
ained | +0.110 |
Ag | +0.100 |
THE | +0.097 |
Prin | +0.096 |
ectar | +0.095 |
Neg logit contributions | |
hands | -0.112 |
sle | -0.110 |
paws | -0.103 |
fingers | -0.100 |
apr | -0.100 |
Token | op |
Token ID | 404 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
hands | +0.004 |
sle | +0.004 |
paws | +0.004 |
nose | +0.003 |
cub | +0.003 |
Neg logit contributions | |
ained | -0.008 |
Ag | -0.007 |
ust | -0.007 |
ectar | -0.007 |
Kay | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +5.39e-03 |
Pos logit contributions | |
hands | +0.012 |
sle | +0.011 |
paws | +0.010 |
Daddy | +0.009 |
nose | +0.009 |
Neg logit contributions | |
ained | -0.026 |
ust | -0.024 |
Ag | -0.024 |
THE | -0.023 |
ectar | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | -5.20e-03 |
Pos logit contributions | |
ained | +0.010 |
Ag | +0.009 |
ectar | +0.009 |
ust | +0.009 |
THE | +0.009 |
Neg logit contributions | |
hands | -0.007 |
sle | -0.007 |
paws | -0.007 |
fingers | -0.006 |
Daddy | -0.006 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.76e-02 |
Pos logit contributions | |
hands | +0.006 |
sle | +0.006 |
paws | +0.005 |
fingers | +0.005 |
pans | +0.005 |
Neg logit contributions | |
ained | -0.011 |
ectar | -0.010 |
THE | -0.010 |
Ag | -0.010 |
ust | -0.009 |
Token | mind |
Token ID | 2000 |
Feature activation | -3.46e-03 |
Pos logit contributions | |
ained | +0.066 |
THE | +0.057 |
eway | +0.056 |
Ag | +0.055 |
Prin | +0.055 |
Neg logit contributions | |
hands | -0.035 |
paws | -0.031 |
help | -0.030 |
Daddy | -0.030 |
load | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
hands | +0.004 |
Daddy | +0.004 |
fingers | +0.003 |
daddy | +0.003 |
t | +0.003 |
Neg logit contributions | |
ained | -0.008 |
ulture | -0.008 |
Prin | -0.007 |
Ag | -0.007 |
narrative | -0.007 |
Token | because |
Token ID | 780 |
Feature activation | +5.75e-03 |
Pos logit contributions | |
ained | +0.079 |
eway | +0.074 |
ust | +0.072 |
ectar | +0.071 |
perspective | +0.070 |
Neg logit contributions | |
hands | -0.041 |
Daddy | -0.037 |
paws | -0.036 |
cheeks | -0.035 |
fingers | -0.035 |
Token | she |
Token ID | 673 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
ained | +0.010 |
ount | +0.010 |
Ag | +0.010 |
Prin | +0.010 |
ub | +0.009 |
Neg logit contributions | |
hands | -0.008 |
Daddy | -0.008 |
Mom | -0.008 |
orange | -0.007 |
mom | -0.007 |
Token | had |
Token ID | 550 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
ained | +0.026 |
Ag | +0.022 |
THE | +0.022 |
ectar | +0.022 |
Prin | +0.022 |
Neg logit contributions | |
hands | -0.023 |
sle | -0.023 |
paws | -0.022 |
fingers | -0.021 |
apr | -0.020 |
Token | such |
Token ID | 884 |
Feature activation | +7.51e-02 |
Pos logit contributions | |
ained | +0.036 |
eway | +0.033 |
ectar | +0.032 |
THE | +0.032 |
ying | +0.032 |
Neg logit contributions | |
hands | -0.024 |
paws | -0.022 |
fingers | -0.020 |
apr | -0.019 |
eyes | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +4.59e-03 |
Pos logit contributions | |
ained | +0.179 |
ount | +0.163 |
inas | +0.163 |
ala | +0.162 |
ectar | +0.161 |
Neg logit contributions | |
hands | -0.068 |
paws | -0.059 |
fingers | -0.052 |
apr | -0.050 |
sle | -0.048 |
Token | fun |
Token ID | 1257 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
ained | +0.009 |
THE | +0.008 |
ectar | +0.008 |
Ag | +0.008 |
Prin | +0.008 |
Neg logit contributions | |
hands | -0.006 |
sle | -0.005 |
paws | -0.005 |
fingers | -0.005 |
apr | -0.005 |
Token | day |
Token ID | 1110 |
Feature activation | +1.24e-04 |
Pos logit contributions | |
ained | +0.063 |
Prin | +0.057 |
ectar | +0.057 |
ust | +0.057 |
ount | +0.057 |
Neg logit contributions | |
hands | -0.033 |
sle | -0.029 |
paws | -0.029 |
t | -0.027 |
fingers | -0.026 |
Token | with |
Token ID | 351 |
Feature activation | +2.06e-02 |
Pos logit contributions | |
ained | +0.000 |
Prin | +0.000 |
Ag | +0.000 |
THE | +0.000 |
ust | +0.000 |
Neg logit contributions | |
hands | -0.000 |
sle | -0.000 |
paws | -0.000 |
fingers | -0.000 |
Daddy | -0.000 |
Token | her |
Token ID | 607 |
Feature activation | +1.43e-03 |
Pos logit contributions | |
ained | +0.035 |
Ag | +0.030 |
THE | +0.030 |
Prin | +0.030 |
ust | +0.030 |
Neg logit contributions | |
hands | -0.032 |
sle | -0.030 |
paws | -0.030 |
fingers | -0.029 |
apr | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -1.28e-02 |
Pos logit contributions | |
hands | +0.008 |
sle | +0.007 |
paws | +0.007 |
fingers | +0.007 |
apr | +0.007 |
Neg logit contributions | |
ained | -0.008 |
Ag | -0.007 |
ust | -0.007 |
ectar | -0.007 |
perspective | -0.007 |
Token | were |
Token ID | 547 |
Feature activation | +1.08e-03 |
Pos logit contributions | |
hands | +0.018 |
sle | +0.017 |
paws | +0.017 |
fingers | +0.015 |
Daddy | +0.015 |
Neg logit contributions | |
ained | -0.023 |
ectar | -0.020 |
Ag | -0.020 |
ust | -0.020 |
Prin | -0.019 |
Token | grateful |
Token ID | 14066 |
Feature activation | +1.67e-02 |
Pos logit contributions | |
ained | +0.002 |
perspective | +0.002 |
Prin | +0.002 |
ust | +0.002 |
Ag | +0.002 |
Neg logit contributions | |
hands | -0.001 |
paws | -0.001 |
sle | -0.001 |
Daddy | -0.001 |
fingers | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +9.49e-03 |
Pos logit contributions | |
ained | +0.039 |
Prin | +0.035 |
ount | +0.034 |
eway | +0.034 |
Ag | +0.033 |
Neg logit contributions | |
hands | -0.018 |
Daddy | -0.016 |
paws | -0.016 |
sle | -0.015 |
fingers | -0.015 |
Token | have |
Token ID | 423 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
ained | +0.016 |
Ag | +0.014 |
THE | +0.014 |
Prin | +0.014 |
ectar | +0.014 |
Neg logit contributions | |
sle | -0.014 |
hands | -0.014 |
paws | -0.013 |
apr | -0.012 |
pans | -0.012 |
Token | such |
Token ID | 884 |
Feature activation | +7.47e-02 |
Pos logit contributions | |
ained | +0.048 |
Ag | +0.042 |
Prin | +0.041 |
THE | +0.041 |
Kay | +0.040 |
Neg logit contributions | |
sle | -0.045 |
hands | -0.042 |
paws | -0.040 |
pans | -0.039 |
fingers | -0.038 |
Token | a |
Token ID | 257 |
Feature activation | +5.95e-03 |
Pos logit contributions | |
ained | +0.178 |
Ag | +0.157 |
perspective | +0.157 |
ectar | +0.157 |
inas | +0.156 |
Neg logit contributions | |
hands | -0.064 |
sle | -0.057 |
paws | -0.056 |
apr | -0.050 |
fingers | -0.047 |
Token | happy |
Token ID | 3772 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
ained | +0.011 |
THE | +0.010 |
Ag | +0.010 |
ectar | +0.010 |
Prin | +0.010 |
Neg logit contributions | |
hands | -0.008 |
sle | -0.008 |
paws | -0.007 |
fingers | -0.007 |
apr | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +1.22e-02 |
Pos logit contributions | |
ained | +0.044 |
Ag | +0.039 |
ectar | +0.038 |
THE | +0.038 |
Prin | +0.038 |
Neg logit contributions | |
hands | -0.026 |
sle | -0.025 |
paws | -0.024 |
fingers | -0.022 |
apr | -0.021 |
Token | adventurous |
Token ID | 39770 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
ained | +0.023 |
perspective | +0.021 |
ust | +0.020 |
Prin | +0.020 |
ala | +0.020 |
Neg logit contributions | |
hands | -0.017 |
paws | -0.015 |
sle | -0.015 |
Daddy | -0.014 |
fingers | -0.013 |
Token | little |
Token ID | 1310 |
Feature activation | -6.50e-03 |
Pos logit contributions | |
ained | +0.022 |
Ag | +0.019 |
THE | +0.019 |
ectar | +0.019 |
Prin | +0.019 |
Neg logit contributions | |
hands | -0.015 |
sle | -0.014 |
paws | -0.014 |
fingers | -0.013 |
Daddy | -0.012 |
Token | He |
Token ID | 679 |
Feature activation | -1.22e-03 |
Pos logit contributions | |
ained | +0.002 |
perspective | +0.002 |
THE | +0.002 |
Prin | +0.002 |
inas | +0.002 |
Neg logit contributions | |
hands | -0.001 |
paws | -0.001 |
Daddy | -0.001 |
fingers | -0.001 |
Dad | -0.001 |
Token | thought |
Token ID | 1807 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
hands | +0.002 |
sle | +0.001 |
paws | +0.001 |
fingers | +0.001 |
apr | +0.001 |
Neg logit contributions | |
ained | -0.002 |
THE | -0.002 |
ectar | -0.002 |
Ag | -0.002 |
perspective | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | +1.14e-02 |
Pos logit contributions | |
hands | +0.028 |
sle | +0.027 |
paws | +0.026 |
fingers | +0.025 |
apr | +0.024 |
Neg logit contributions | |
ained | -0.035 |
THE | -0.030 |
Ag | -0.030 |
Prin | -0.030 |
ust | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
ained | +0.023 |
Ag | +0.020 |
THE | +0.020 |
ectar | +0.020 |
ust | +0.020 |
Neg logit contributions | |
sle | -0.013 |
hands | -0.013 |
paws | -0.012 |
apr | -0.011 |
pans | -0.011 |
Token | way |
Token ID | 835 |
Feature activation | -2.26e-02 |
Pos logit contributions | |
ained | +0.026 |
ount | +0.023 |
ying | +0.022 |
ectar | +0.022 |
ala | +0.022 |
Neg logit contributions | |
hands | -0.010 |
sle | -0.010 |
paws | -0.009 |
t | -0.009 |
white | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +2.79e-02 |
Pos logit contributions | |
hands | +0.025 |
Daddy | +0.020 |
paws | +0.019 |
sle | +0.018 |
hand | +0.017 |
Neg logit contributions | |
Prin | -0.051 |
ained | -0.050 |
ectar | -0.049 |
ust | -0.049 |
former | -0.048 |
Token | improve |
Token ID | 2987 |
Feature activation | +4.02e-02 |
Pos logit contributions | |
ained | +0.068 |
THE | +0.060 |
ectar | +0.060 |
Ag | +0.059 |
ust | +0.058 |
Neg logit contributions | |
hands | -0.025 |
load | -0.022 |
paws | -0.022 |
sle | -0.021 |
Daddy | -0.020 |
Token | his |
Token ID | 465 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
ained | +0.097 |
Prin | +0.087 |
ust | +0.087 |
Ag | +0.085 |
ount | +0.083 |
Neg logit contributions | |
hands | -0.046 |
paws | -0.037 |
fingers | -0.036 |
sle | -0.035 |
Daddy | -0.035 |
Token | castle |
Token ID | 16669 |
Feature activation | +4.12e-02 |
Pos logit contributions | |
ained | +0.024 |
Ag | +0.021 |
THE | +0.021 |
ectar | +0.020 |
Prin | +0.020 |
Neg logit contributions | |
hands | -0.024 |
sle | -0.023 |
paws | -0.022 |
fingers | -0.021 |
apr | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +4.63e-03 |
Pos logit contributions | |
ained | +0.098 |
Ag | +0.095 |
Kay | +0.091 |
ala | +0.090 |
Acc | +0.090 |
Neg logit contributions | |
hands | -0.043 |
paws | -0.037 |
fingers | -0.033 |
load | -0.032 |
nose | -0.032 |
Token | He |
Token ID | 679 |
Feature activation | +2.04e-03 |
Pos logit contributions | |
ained | +0.009 |
perspective | +0.009 |
THE | +0.008 |
Prin | +0.008 |
ust | +0.008 |
Neg logit contributions | |
hands | -0.006 |
paws | -0.005 |
sle | -0.005 |
Daddy | -0.005 |
fingers | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | +5.24e-03 |
Pos logit contributions | |
ained | +0.036 |
ust | +0.030 |
THE | +0.030 |
Ag | +0.030 |
perspective | +0.030 |
Neg logit contributions | |
hands | -0.027 |
paws | -0.022 |
Daddy | -0.022 |
fingers | -0.021 |
eyes | -0.021 |
Token | mom |
Token ID | 1995 |
Feature activation | -3.74e-03 |
Pos logit contributions | |
ained | +0.014 |
Ag | +0.013 |
Prin | +0.012 |
ust | +0.012 |
lessly | +0.012 |
Neg logit contributions | |
hands | -0.005 |
paws | -0.004 |
fingers | -0.003 |
Daddy | -0.003 |
sle | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +6.80e-04 |
Pos logit contributions | |
hands | +0.004 |
plates | +0.003 |
Daddy | +0.003 |
forks | +0.003 |
sle | +0.003 |
Neg logit contributions | |
Ag | -0.009 |
ained | -0.009 |
perspective | -0.008 |
Prin | -0.008 |
ust | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | -6.87e-03 |
Pos logit contributions | |
ained | +0.001 |
ier | +0.001 |
ust | +0.001 |
THE | +0.001 |
perspective | +0.001 |
Neg logit contributions | |
hands | -0.001 |
Daddy | -0.001 |
paws | -0.001 |
sle | -0.001 |
Dad | -0.001 |
Token | beautiful |
Token ID | 4950 |
Feature activation | -2.87e-03 |
Pos logit contributions | |
hands | +0.007 |
sle | +0.006 |
paws | +0.006 |
fingers | +0.006 |
plates | +0.005 |
Neg logit contributions | |
ained | -0.016 |
ust | -0.014 |
Ag | -0.014 |
THE | -0.014 |
eway | -0.013 |
Token | l |
Token ID | 300 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
hands | +0.002 |
sle | +0.002 |
paws | +0.002 |
fingers | +0.002 |
cheeks | +0.002 |
Neg logit contributions | |
ained | -0.007 |
ust | -0.006 |
Ag | -0.006 |
THE | -0.006 |
Prin | -0.006 |
Token | ily |
Token ID | 813 |
Feature activation | +3.23e-03 |
Pos logit contributions | |
ained | +0.050 |
perspective | +0.044 |
Fighting | +0.042 |
spe | +0.041 |
inas | +0.041 |
Neg logit contributions | |
hands | -0.064 |
paws | -0.061 |
sle | -0.056 |
fingers | -0.056 |
cheeks | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | -8.35e-03 |
Pos logit contributions | |
ained | +0.006 |
Ag | +0.006 |
THE | +0.006 |
perspective | +0.006 |
ectar | +0.005 |
Neg logit contributions | |
hands | -0.004 |
paws | -0.004 |
sle | -0.004 |
fingers | -0.004 |
cheeks | -0.004 |
Token | sad |
Token ID | 6507 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
hands | +0.010 |
sle | +0.009 |
paws | +0.009 |
white | +0.009 |
Daddy | +0.009 |
Neg logit contributions | |
ained | -0.016 |
perspective | -0.016 |
Ag | -0.015 |
ust | -0.015 |
eway | -0.015 |
Token | because |
Token ID | 780 |
Feature activation | -6.21e-03 |
Pos logit contributions | |
ained | +0.033 |
Prin | +0.031 |
Ag | +0.031 |
Kay | +0.031 |
eway | +0.030 |
Neg logit contributions | |
hands | -0.011 |
Daddy | -0.009 |
eyes | -0.009 |
paws | -0.009 |
fingers | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | -6.33e-03 |
Pos logit contributions | |
Daddy | +0.010 |
hands | +0.010 |
Mom | +0.009 |
Dad | +0.009 |
orange | +0.008 |
Neg logit contributions | |
ained | -0.011 |
Ag | -0.010 |
perspective | -0.010 |
Prin | -0.010 |
ust | -0.010 |
Token | top |
Token ID | 1353 |
Feature activation | -9.71e-03 |
Pos logit contributions | |
sle | +0.003 |
paws | +0.002 |
hands | +0.002 |
apr | +0.002 |
Daddy | +0.002 |
Neg logit contributions | |
ained | -0.004 |
perspective | -0.003 |
THE | -0.003 |
Prin | -0.003 |
fault | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
hands | +0.014 |
sle | +0.014 |
paws | +0.013 |
apr | +0.013 |
fingers | +0.013 |
Neg logit contributions | |
ained | -0.016 |
Ag | -0.014 |
THE | -0.014 |
ectar | -0.014 |
Prin | -0.014 |
Token | but |
Token ID | 475 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
ained | +0.060 |
Ag | +0.052 |
ectar | +0.051 |
THE | +0.051 |
ust | +0.051 |
Neg logit contributions | |
hands | -0.053 |
sle | -0.050 |
paws | -0.049 |
fingers | -0.047 |
apr | -0.045 |
Token | it |
Token ID | 340 |
Feature activation | -6.49e-03 |
Pos logit contributions | |
hands | +0.032 |
paws | +0.028 |
Daddy | +0.027 |
fingers | +0.027 |
sle | +0.026 |
Neg logit contributions | |
ained | -0.051 |
perspective | -0.046 |
Ag | -0.046 |
ust | -0.045 |
inas | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | -6.30e-03 |
Pos logit contributions | |
hands | +0.009 |
paws | +0.008 |
sle | +0.008 |
fingers | +0.008 |
forks | +0.007 |
Neg logit contributions | |
ained | -0.012 |
Ag | -0.011 |
perspective | -0.011 |
THE | -0.011 |
ectar | -0.011 |
Token | stuck |
Token ID | 7819 |
Feature activation | +3.65e-02 |
Pos logit contributions | |
hands | +0.010 |
sle | +0.010 |
paws | +0.009 |
apr | +0.009 |
fingers | +0.009 |
Neg logit contributions | |
ained | -0.010 |
THE | -0.009 |
Ag | -0.009 |
ectar | -0.009 |
ust | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -7.07e-04 |
Pos logit contributions | |
ained | +0.069 |
Prin | +0.064 |
Ag | +0.064 |
Kay | +0.063 |
THE | +0.063 |
Neg logit contributions | |
hands | -0.047 |
sle | -0.043 |
paws | -0.043 |
fingers | -0.040 |
forks | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | -2.79e-03 |
Pos logit contributions | |
hands | +0.001 |
sle | +0.001 |
paws | +0.001 |
Daddy | +0.001 |
fingers | +0.001 |
Neg logit contributions | |
ained | -0.001 |
THE | -0.001 |
Ag | -0.001 |
perspective | -0.001 |
inas | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -4.09e-03 |
Pos logit contributions | |
sle | +0.004 |
hands | +0.004 |
paws | +0.004 |
apr | +0.004 |
fingers | +0.004 |
Neg logit contributions | |
ained | -0.004 |
THE | -0.004 |
Ag | -0.004 |
Prin | -0.004 |
ectar | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | +1.35e-02 |
Pos logit contributions | |
hands | +0.006 |
sle | +0.005 |
paws | +0.005 |
pans | +0.005 |
fingers | +0.005 |
Neg logit contributions | |
ained | -0.008 |
perspective | -0.007 |
fault | -0.007 |
ectar | -0.007 |
Ag | -0.006 |
Token | Help |
Token ID | 22087 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
ained | +0.023 |
ectar | +0.021 |
inas | +0.020 |
perspective | +0.020 |
THE | +0.020 |
Neg logit contributions | |
hands | -0.020 |
pans | -0.018 |
paws | -0.018 |
sle | -0.018 |
apr | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | -9.64e-04 |
Pos logit contributions | |
ained | +0.050 |
Ag | +0.044 |
ount | +0.043 |
ulture | +0.043 |
Prin | +0.043 |
Neg logit contributions | |
hands | -0.019 |
paws | -0.017 |
sle | -0.015 |
fingers | -0.014 |
Daddy | -0.014 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
hands | +0.001 |
paws | +0.001 |
Daddy | +0.001 |
sle | +0.001 |
Dad | +0.001 |
Neg logit contributions | |
ained | -0.002 |
ier | -0.002 |
Ag | -0.002 |
ust | -0.002 |
perspective | -0.002 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.68e-02 |
Pos logit contributions | |
hands | +0.023 |
sle | +0.021 |
paws | +0.020 |
Daddy | +0.019 |
cub | +0.018 |
Neg logit contributions | |
ained | -0.051 |
ust | -0.049 |
Ag | -0.047 |
inas | -0.047 |
perspective | -0.047 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.45e-03 |
Pos logit contributions | |
ained | +0.032 |
Ag | +0.027 |
Prin | +0.026 |
THE | +0.025 |
ectar | +0.025 |
Neg logit contributions | |
hands | -0.054 |
sle | -0.051 |
paws | -0.050 |
Daddy | -0.050 |
fingers | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
ained | +0.004 |
Ag | +0.003 |
ectar | +0.003 |
perspective | +0.003 |
ust | +0.003 |
Neg logit contributions | |
hands | -0.001 |
sle | -0.001 |
paws | -0.001 |
fingers | -0.001 |
apr | -0.001 |
Token | time |
Token ID | 640 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
ained | +0.022 |
ust | +0.022 |
THE | +0.018 |
perspective | +0.018 |
Prin | +0.018 |
Neg logit contributions | |
sle | -0.040 |
pans | -0.038 |
hands | -0.038 |
forks | -0.036 |
cheeks | -0.036 |
Token | there |
Token ID | 612 |
Feature activation | -2.88e-03 |
Pos logit contributions | |
ained | +0.039 |
Ag | +0.035 |
THE | +0.034 |
ectar | +0.034 |
ust | +0.034 |
Neg logit contributions | |
sle | -0.028 |
hands | -0.027 |
apr | -0.025 |
paws | -0.025 |
pans | -0.024 |
Token | was |
Token ID | 373 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
hands | +0.004 |
sle | +0.004 |
paws | +0.004 |
fingers | +0.003 |
Daddy | +0.003 |
Neg logit contributions | |
ained | -0.005 |
Ag | -0.005 |
ectar | -0.005 |
THE | -0.005 |
Prin | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -1.57e-02 |
Pos logit contributions | |
sle | +0.019 |
hands | +0.018 |
paws | +0.016 |
pans | +0.016 |
cheeks | +0.016 |
Neg logit contributions | |
ained | -0.033 |
THE | -0.029 |
Ag | -0.029 |
Prin | -0.029 |
ectar | -0.028 |
Token | little |
Token ID | 1310 |
Feature activation | -1.06e-02 |
Pos logit contributions | |
hands | +0.017 |
sle | +0.015 |
paws | +0.015 |
apr | +0.014 |
fingers | +0.014 |
Neg logit contributions | |
Prin | -0.030 |
Ag | -0.029 |
ained | -0.029 |
THE | -0.028 |
ectar | -0.028 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
hands | +0.019 |
apr | +0.018 |
sle | +0.018 |
paws | +0.017 |
fingers | +0.017 |
Neg logit contributions | |
ained | -0.013 |
ectar | -0.012 |
Prin | -0.012 |
ala | -0.011 |
perspective | -0.011 |
Token | doll |
Token ID | 3654 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
ained | +0.036 |
ectar | +0.033 |
THE | +0.033 |
perspective | +0.032 |
fault | +0.032 |
Neg logit contributions | |
sle | -0.025 |
pans | -0.022 |
hands | -0.022 |
apr | -0.022 |
forks | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
ained | +0.066 |
Ag | +0.063 |
Kay | +0.060 |
lessly | +0.059 |
ust | +0.059 |
Neg logit contributions | |
hands | -0.022 |
paws | -0.020 |
fingers | -0.017 |
nose | -0.016 |
load | -0.016 |
Token | dress |
Token ID | 6576 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
ained | +0.025 |
Ag | +0.022 |
THE | +0.022 |
Prin | +0.021 |
ectar | +0.021 |
Neg logit contributions | |
hands | -0.015 |
sle | -0.015 |
paws | -0.014 |
fingers | -0.013 |
apr | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +3.12e-02 |
Pos logit contributions | |
ained | +0.032 |
perspective | +0.029 |
Ag | +0.029 |
Prin | +0.029 |
Fighting | +0.029 |
Neg logit contributions | |
hands | -0.014 |
paws | -0.012 |
nose | -0.012 |
fingers | -0.012 |
sle | -0.012 |
Token | so |
Token ID | 523 |
Feature activation | +9.37e-03 |
Pos logit contributions | |
ained | +0.062 |
Ag | +0.053 |
THE | +0.053 |
perspective | +0.053 |
ust | +0.052 |
Neg logit contributions | |
hands | -0.043 |
paws | -0.039 |
sle | -0.039 |
fingers | -0.037 |
Daddy | -0.037 |
Token | she |
Token ID | 673 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
ained | +0.013 |
ount | +0.011 |
Ag | +0.011 |
perspective | +0.011 |
ust | +0.011 |
Neg logit contributions | |
hands | -0.018 |
paws | -0.017 |
fingers | -0.016 |
sle | -0.016 |
Daddy | -0.016 |
Token | got |
Token ID | 1392 |
Feature activation | +1.94e-02 |
Pos logit contributions | |
ained | +0.048 |
Prin | +0.045 |
Ag | +0.043 |
ust | +0.042 |
THE | +0.042 |
Neg logit contributions | |
sle | -0.048 |
hands | -0.044 |
paws | -0.041 |
apr | -0.041 |
fingers | -0.039 |
Token | some |
Token ID | 617 |
Feature activation | +9.04e-03 |
Pos logit contributions | |
ained | +0.035 |
Ag | +0.031 |
THE | +0.031 |
ust | +0.030 |
ectar | +0.030 |
Neg logit contributions | |
hands | -0.027 |
sle | -0.026 |
paws | -0.025 |
fingers | -0.024 |
apr | -0.023 |
Token | glue |
Token ID | 22749 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
ained | +0.018 |
ectar | +0.016 |
Ag | +0.016 |
Prin | +0.016 |
THE | +0.016 |
Neg logit contributions | |
sle | -0.011 |
hands | -0.010 |
paws | -0.009 |
apr | -0.009 |
pans | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +1.42e-03 |
Pos logit contributions | |
ained | +0.045 |
Kay | +0.043 |
eway | +0.043 |
Prin | +0.043 |
ust | +0.042 |
Neg logit contributions | |
hands | -0.021 |
fingers | -0.017 |
paws | -0.016 |
t | -0.016 |
plates | -0.016 |
Token | put |
Token ID | 1234 |
Feature activation | +1.19e-02 |
Pos logit contributions | |
ained | +0.003 |
Prin | +0.002 |
Ag | +0.002 |
THE | +0.002 |
inas | +0.002 |
Neg logit contributions | |
sle | -0.002 |
hands | -0.002 |
paws | -0.002 |
apr | -0.001 |
chin | -0.001 |
Token | window |
Token ID | 4324 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
hands | +0.005 |
sle | +0.005 |
paws | +0.005 |
fingers | +0.005 |
apr | +0.005 |
Neg logit contributions | |
ained | -0.009 |
THE | -0.008 |
Prin | -0.008 |
Ag | -0.008 |
ectar | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
hands | +0.018 |
sle | +0.017 |
paws | +0.016 |
fingers | +0.015 |
Daddy | +0.014 |
Neg logit contributions | |
ained | -0.026 |
Ag | -0.023 |
Prin | -0.022 |
ust | -0.022 |
THE | -0.022 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
hands | +0.016 |
sle | +0.015 |
paws | +0.014 |
fingers | +0.013 |
apr | +0.013 |
Neg logit contributions | |
ained | -0.030 |
Ag | -0.026 |
THE | -0.026 |
ectar | -0.026 |
ust | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -7.47e-03 |
Pos logit contributions | |
hands | +0.015 |
sle | +0.015 |
paws | +0.014 |
fingers | +0.013 |
apr | +0.013 |
Neg logit contributions | |
ained | -0.027 |
THE | -0.024 |
Ag | -0.024 |
ectar | -0.024 |
Prin | -0.024 |
Token | snow |
Token ID | 6729 |
Feature activation | -1.04e-02 |
Pos logit contributions | |
hands | +0.008 |
sle | +0.007 |
paws | +0.007 |
fingers | +0.006 |
apr | +0.006 |
Neg logit contributions | |
ained | -0.016 |
THE | -0.014 |
Ag | -0.014 |
Prin | -0.014 |
ectar | -0.014 |
Token | man |
Token ID | 805 |
Feature activation | -2.20e-02 |
Pos logit contributions | |
sle | +0.015 |
hands | +0.015 |
paws | +0.014 |
pans | +0.013 |
fingers | +0.013 |
Neg logit contributions | |
ained | -0.019 |
Ag | -0.017 |
ust | -0.016 |
Prin | -0.016 |
Kay | -0.016 |
Token | in |
Token ID | 287 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
hands | +0.031 |
sle | +0.030 |
paws | +0.028 |
fingers | +0.027 |
apr | +0.026 |
Neg logit contributions | |
ained | -0.040 |
Ag | -0.035 |
ectar | -0.034 |
Prin | -0.034 |
THE | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +9.71e-03 |
Pos logit contributions | |
hands | +0.018 |
sle | +0.018 |
paws | +0.016 |
fingers | +0.015 |
apr | +0.015 |
Neg logit contributions | |
ained | -0.031 |
THE | -0.027 |
Ag | -0.027 |
Prin | -0.027 |
ectar | -0.027 |
Token | yard |
Token ID | 12699 |
Feature activation | +8.77e-03 |
Pos logit contributions | |
ained | +0.020 |
Ag | +0.018 |
ectar | +0.018 |
ust | +0.018 |
THE | +0.018 |
Neg logit contributions | |
hands | -0.011 |
sle | -0.011 |
paws | -0.010 |
apr | -0.009 |
fingers | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -9.99e-03 |
Pos logit contributions | |
ained | +0.021 |
ust | +0.020 |
Ag | +0.020 |
Prin | +0.019 |
ectar | +0.019 |
Neg logit contributions | |
hands | -0.008 |
sle | -0.008 |
nose | -0.007 |
plates | -0.007 |
load | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
hands | +0.015 |
sle | +0.015 |
paws | +0.014 |
Daddy | +0.013 |
fingers | +0.013 |
Neg logit contributions | |
ained | -0.018 |
THE | -0.015 |
Ag | -0.015 |
ust | -0.015 |
ectar | -0.015 |
Token | It |
Token ID | 632 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
hands | +0.004 |
Daddy | +0.004 |
paws | +0.004 |
eyes | +0.003 |
Mom | +0.003 |
Neg logit contributions | |
ained | -0.009 |
ust | -0.009 |
perspective | -0.009 |
ying | -0.008 |
spe | -0.008 |
Token | pur |
Token ID | 1308 |
Feature activation | +9.14e-03 |
Pos logit contributions | |
hands | +0.025 |
paws | +0.024 |
sle | +0.023 |
fingers | +0.021 |
nose | +0.021 |
Neg logit contributions | |
ained | -0.051 |
perspective | -0.047 |
ectar | -0.045 |
THE | -0.045 |
Ag | -0.044 |
Token | red |
Token ID | 445 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
ained | +0.016 |
THE | +0.014 |
Ag | +0.013 |
perspective | +0.013 |
ust | +0.013 |
Neg logit contributions | |
hands | -0.014 |
sle | -0.013 |
paws | -0.013 |
fingers | -0.012 |
cheeks | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -8.54e-03 |
Pos logit contributions | |
hands | +0.018 |
paws | +0.016 |
brown | +0.015 |
fingers | +0.015 |
white | +0.014 |
Neg logit contributions | |
ained | -0.039 |
Ag | -0.035 |
perspective | -0.034 |
Kay | -0.033 |
ount | -0.033 |
Token | rubbed |
Token ID | 31862 |
Feature activation | -1.61e-02 |
Pos logit contributions | |
hands | +0.009 |
sle | +0.009 |
paws | +0.009 |
fingers | +0.008 |
pans | +0.008 |
Neg logit contributions | |
ained | -0.019 |
THE | -0.017 |
ust | -0.017 |
perspective | -0.016 |
ectar | -0.016 |
Token | its |
Token ID | 663 |
Feature activation | -5.74e-03 |
Pos logit contributions | |
hands | +0.025 |
paws | +0.023 |
fingers | +0.021 |
sle | +0.021 |
Daddy | +0.020 |
Neg logit contributions | |
ained | -0.031 |
ust | -0.027 |
perspective | -0.027 |
Ag | -0.026 |
THE | -0.026 |
Token | face |
Token ID | 1986 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
sle | +0.005 |
apr | +0.005 |
forks | +0.005 |
Daddy | +0.005 |
hands | +0.005 |
Neg logit contributions | |
ained | -0.012 |
ectar | -0.011 |
Prin | -0.010 |
ust | -0.010 |
THE | -0.010 |
Token | against |
Token ID | 1028 |
Feature activation | -3.56e-02 |
Pos logit contributions | |
hands | +0.022 |
paws | +0.020 |
fingers | +0.018 |
nose | +0.018 |
brown | +0.018 |
Neg logit contributions | |
ained | -0.044 |
Ag | -0.042 |
perspective | -0.041 |
Kay | -0.040 |
THE | -0.038 |
Token | Lily |
Token ID | 20037 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
hands | +0.055 |
sle | +0.052 |
paws | +0.051 |
fingers | +0.048 |
apr | +0.047 |
Neg logit contributions | |
ained | -0.062 |
THE | -0.052 |
Ag | -0.052 |
ectar | -0.052 |
ust | -0.052 |
Token | 's |
Token ID | 338 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
ained | +0.051 |
Ag | +0.049 |
Kay | +0.047 |
THE | +0.046 |
Prin | +0.045 |
Neg logit contributions | |
hands | -0.023 |
paws | -0.020 |
sle | -0.019 |
fingers | -0.019 |
nose | -0.017 |
Token | hand |
Token ID | 1021 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
ained | +0.024 |
ectar | +0.023 |
THE | +0.022 |
ust | +0.022 |
Ag | +0.022 |
Neg logit contributions | |
sle | -0.009 |
hands | -0.008 |
apr | -0.008 |
pans | -0.008 |
paws | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +7.38e-04 |
Pos logit contributions | |
ained | +0.027 |
ust | +0.026 |
ount | +0.025 |
ectar | +0.024 |
ala | +0.024 |
Neg logit contributions | |
hands | -0.007 |
Daddy | -0.006 |
paws | -0.005 |
fingers | -0.004 |
Mom | -0.004 |
Token | bird |
Token ID | 6512 |
Feature activation | +1.30e-02 |
Pos logit contributions | |
ained | +0.001 |
THE | +0.001 |
Prin | +0.001 |
Ag | +0.001 |
ectar | +0.001 |
Neg logit contributions | |
hands | -0.001 |
sle | -0.001 |
paws | -0.001 |
apr | -0.001 |
fingers | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | +4.39e-04 |
Pos logit contributions | |
ained | +0.027 |
Ag | +0.024 |
ectar | +0.024 |
ust | +0.023 |
eway | +0.023 |
Neg logit contributions | |
hands | -0.015 |
sle | -0.015 |
paws | -0.015 |
fingers | -0.013 |
cub | -0.013 |
Token | wing |
Token ID | 8539 |
Feature activation | +7.16e-04 |
Pos logit contributions | |
ained | +0.001 |
THE | +0.001 |
ectar | +0.001 |
Ag | +0.001 |
ust | +0.001 |
Neg logit contributions | |
hands | -0.001 |
sle | -0.001 |
paws | -0.001 |
apr | -0.001 |
pans | -0.001 |
Token | started |
Token ID | 2067 |
Feature activation | +6.59e-03 |
Pos logit contributions | |
ained | +0.001 |
ust | +0.001 |
Ag | +0.001 |
ectar | +0.001 |
ala | +0.001 |
Neg logit contributions | |
hands | -0.001 |
paws | -0.001 |
sle | -0.001 |
nose | -0.001 |
fingers | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +1.38e-02 |
Pos logit contributions | |
ained | +0.013 |
Ag | +0.011 |
ust | +0.011 |
THE | +0.011 |
Kay | +0.011 |
Neg logit contributions | |
hands | -0.009 |
sle | -0.008 |
paws | -0.008 |
fingers | -0.008 |
eyes | -0.007 |
Token | heal |
Token ID | 12035 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
ained | +0.026 |
Ag | +0.023 |
THE | +0.022 |
ectar | +0.022 |
ust | +0.022 |
Neg logit contributions | |
hands | -0.018 |
sle | -0.018 |
paws | -0.017 |
fingers | -0.016 |
apr | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
ained | +0.023 |
Ag | +0.021 |
ount | +0.020 |
ust | +0.020 |
Kay | +0.020 |
Neg logit contributions | |
hands | -0.014 |
paws | -0.013 |
sle | -0.013 |
fingers | -0.012 |
Daddy | -0.012 |
Token | One |
Token ID | 1881 |
Feature activation | -6.91e-03 |
Pos logit contributions | |
hands | +0.010 |
paws | +0.010 |
Daddy | +0.009 |
sle | +0.008 |
cheeks | +0.008 |
Neg logit contributions | |
ained | -0.027 |
THE | -0.025 |
ust | -0.025 |
Ag | -0.025 |
ala | -0.024 |
Token | day |
Token ID | 1110 |
Feature activation | -2.53e-02 |
Pos logit contributions | |
hands | +0.010 |
sle | +0.010 |
paws | +0.010 |
fingers | +0.009 |
apr | +0.009 |
Neg logit contributions | |
ained | -0.012 |
Ag | -0.010 |
THE | -0.010 |
ectar | -0.010 |
Prin | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +8.33e-03 |
Pos logit contributions | |
hands | +0.025 |
sle | +0.023 |
paws | +0.022 |
fingers | +0.020 |
apr | +0.019 |
Neg logit contributions | |
ained | -0.058 |
Ag | -0.051 |
ust | -0.051 |
THE | -0.051 |
ectar | -0.051 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +2.21e-03 |
Pos logit contributions | |
hands | +0.029 |
sle | +0.027 |
paws | +0.026 |
fingers | +0.024 |
Daddy | +0.024 |
Neg logit contributions | |
ained | -0.045 |
Ag | -0.040 |
ectar | -0.040 |
THE | -0.039 |
Prin | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
ained | +0.005 |
ectar | +0.004 |
Ag | +0.004 |
perspective | +0.004 |
THE | +0.004 |
Neg logit contributions | |
hands | -0.003 |
paws | -0.003 |
sle | -0.002 |
fingers | -0.002 |
apr | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +1.30e-03 |
Pos logit contributions | |
hands | +0.035 |
paws | +0.031 |
sle | +0.031 |
Daddy | +0.031 |
fingers | +0.030 |
Neg logit contributions | |
ained | -0.038 |
Ag | -0.034 |
ectar | -0.033 |
THE | -0.033 |
ust | -0.032 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
THE | +0.002 |
ained | +0.002 |
fault | +0.002 |
perspective | +0.002 |
Ag | +0.002 |
Neg logit contributions | |
sle | -0.002 |
chops | -0.002 |
load | -0.001 |
pans | -0.001 |
555 | -0.001 |
Token | played |
Token ID | 2826 |
Feature activation | +2.81e-03 |
Pos logit contributions | |
hands | +0.017 |
sle | +0.016 |
paws | +0.015 |
fingers | +0.014 |
apr | +0.014 |
Neg logit contributions | |
ained | -0.022 |
Ag | -0.020 |
THE | -0.020 |
ectar | -0.019 |
Prin | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ained | +0.006 |
ust | +0.005 |
ala | +0.005 |
ount | +0.005 |
ectar | +0.005 |
Neg logit contributions | |
hands | -0.004 |
apr | -0.003 |
paws | -0.003 |
plates | -0.003 |
fingers | -0.003 |
Token | game |
Token ID | 983 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
hands | +0.022 |
sle | +0.021 |
paws | +0.020 |
fingers | +0.019 |
apr | +0.019 |
Neg logit contributions | |
ained | -0.021 |
Ag | -0.018 |
THE | -0.018 |
Prin | -0.018 |
ectar | -0.018 |
Token | of |
Token ID | 286 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
ained | +0.032 |
Prin | +0.030 |
Acc | +0.029 |
Ag | +0.029 |
ust | +0.029 |
Neg logit contributions | |
hands | -0.018 |
paws | -0.016 |
plates | -0.015 |
help | -0.014 |
fingers | -0.014 |
Token | soccer |
Token ID | 11783 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
ained | +0.034 |
Ag | +0.029 |
THE | +0.029 |
Prin | +0.029 |
ectar | +0.029 |
Neg logit contributions | |
sle | -0.027 |
hands | -0.027 |
paws | -0.025 |
fingers | -0.024 |
apr | -0.024 |
Token | with |
Token ID | 351 |
Feature activation | -9.86e-03 |
Pos logit contributions | |
ained | +0.035 |
ount | +0.033 |
ust | +0.032 |
Kay | +0.032 |
Acc | +0.032 |
Neg logit contributions | |
hands | -0.019 |
paws | -0.016 |
plates | -0.015 |
forks | -0.014 |
fingers | -0.014 |
Token | their |
Token ID | 511 |
Feature activation | -1.14e-02 |
Pos logit contributions | |
hands | +0.012 |
paws | +0.010 |
sle | +0.010 |
fingers | +0.010 |
apr | +0.009 |
Neg logit contributions | |
ained | -0.021 |
ust | -0.019 |
ectar | -0.019 |
Ag | -0.019 |
THE | -0.019 |
Token | She |
Token ID | 3347 |
Feature activation | +1.80e-03 |
Pos logit contributions | |
hands | +0.008 |
apr | +0.007 |
sle | +0.007 |
pans | +0.007 |
paws | +0.007 |
Neg logit contributions | |
ained | -0.014 |
fault | -0.014 |
ier | -0.014 |
bows | -0.013 |
ectar | -0.013 |
Token | begged |
Token ID | 32946 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
ained | +0.003 |
Ag | +0.003 |
THE | +0.003 |
ectar | +0.003 |
Prin | +0.003 |
Neg logit contributions | |
hands | -0.002 |
sle | -0.002 |
paws | -0.002 |
fingers | -0.002 |
apr | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | +4.70e-04 |
Pos logit contributions | |
hands | +0.045 |
sle | +0.044 |
paws | +0.042 |
apr | +0.040 |
fingers | +0.040 |
Neg logit contributions | |
ained | -0.042 |
Ag | -0.036 |
THE | -0.036 |
ectar | -0.035 |
Prin | -0.035 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.29e-03 |
Pos logit contributions | |
ained | +0.001 |
Ag | +0.001 |
THE | +0.001 |
Prin | +0.001 |
ectar | +0.001 |
Neg logit contributions | |
hands | -0.000 |
sle | -0.000 |
paws | -0.000 |
fingers | -0.000 |
apr | -0.000 |
Token | to |
Token ID | 284 |
Feature activation | +4.85e-04 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.010 |
paws | +0.010 |
Daddy | +0.010 |
forks | +0.010 |
Neg logit contributions | |
ained | -0.016 |
Ag | -0.015 |
Prin | -0.014 |
perspective | -0.014 |
Kay | -0.014 |
Token | let |
Token ID | 1309 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
ained | +0.001 |
Prin | +0.001 |
Kay | +0.001 |
Ag | +0.001 |
THE | +0.001 |
Neg logit contributions | |
sle | -0.001 |
hands | -0.001 |
paws | -0.001 |
pans | -0.000 |
fingers | -0.000 |
Token | her |
Token ID | 607 |
Feature activation | +1.18e-02 |
Pos logit contributions | |
sle | +0.059 |
hands | +0.057 |
paws | +0.056 |
pans | +0.053 |
fingers | +0.053 |
Neg logit contributions | |
ained | -0.036 |
Prin | -0.031 |
THE | -0.030 |
Ag | -0.030 |
ectar | -0.029 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
ained | +0.021 |
THE | +0.018 |
ust | +0.018 |
ectar | +0.018 |
ala | +0.018 |
Neg logit contributions | |
sle | -0.016 |
paws | -0.013 |
hands | -0.013 |
pans | -0.013 |
fiery | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | -2.10e-02 |
Pos logit contributions | |
sle | +0.022 |
chops | +0.021 |
fiery | +0.021 |
paws | +0.021 |
cheeks | +0.020 |
Neg logit contributions | |
ained | -0.010 |
THE | -0.009 |
Ag | -0.009 |
ectar | -0.008 |
ala | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.04e-03 |
Pos logit contributions | |
hands | +0.032 |
sle | +0.032 |
paws | +0.030 |
fingers | +0.029 |
apr | +0.028 |
Neg logit contributions | |
ained | -0.035 |
Ag | -0.030 |
THE | -0.030 |
Prin | -0.029 |
ectar | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | +1.58e-03 |
Pos logit contributions | |
hands | +0.003 |
Daddy | +0.002 |
paws | +0.002 |
fingers | +0.002 |
Mom | +0.002 |
Neg logit contributions | |
ained | -0.004 |
ier | -0.004 |
THE | -0.004 |
ust | -0.004 |
Ag | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.010 |
paws | +0.010 |
Daddy | +0.010 |
apr | +0.009 |
Neg logit contributions | |
ained | -0.018 |
ectar | -0.017 |
ust | -0.016 |
ala | -0.016 |
THE | -0.016 |
Token | A |
Token ID | 32 |
Feature activation | -1.26e-02 |
Pos logit contributions | |
hands | +0.022 |
sle | +0.020 |
paws | +0.020 |
Daddy | +0.020 |
apr | +0.020 |
Neg logit contributions | |
ained | -0.021 |
ectar | -0.020 |
ala | -0.019 |
fault | -0.018 |
bows | -0.018 |
Token | week |
Token ID | 1285 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
hands | +0.013 |
sle | +0.013 |
paws | +0.012 |
pans | +0.011 |
apr | +0.011 |
Neg logit contributions | |
ained | -0.027 |
ectar | -0.024 |
THE | -0.024 |
Ag | -0.024 |
ust | -0.024 |
Token | later |
Token ID | 1568 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
hands | +0.019 |
Daddy | +0.017 |
sle | +0.017 |
paws | +0.017 |
load | +0.015 |
Neg logit contributions | |
ained | -0.038 |
ectar | -0.034 |
ust | -0.034 |
THE | -0.033 |
Ag | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | +3.55e-03 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.010 |
Daddy | +0.009 |
paws | +0.009 |
Dad | +0.008 |
Neg logit contributions | |
ained | -0.034 |
ectar | -0.032 |
ust | -0.031 |
THE | -0.030 |
perspective | -0.030 |
Token | when |
Token ID | 618 |
Feature activation | -4.25e-02 |
Pos logit contributions | |
ained | +0.007 |
ectar | +0.007 |
THE | +0.007 |
Ag | +0.007 |
Prin | +0.007 |
Neg logit contributions | |
hands | -0.004 |
sle | -0.004 |
paws | -0.004 |
fingers | -0.003 |
apr | -0.003 |
Token | Johnny |
Token ID | 15470 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
hands | +0.052 |
sle | +0.052 |
paws | +0.048 |
apr | +0.045 |
fingers | +0.045 |
Neg logit contributions | |
ained | -0.084 |
Ag | -0.074 |
THE | -0.074 |
Prin | -0.072 |
ectar | -0.071 |
Token | came |
Token ID | 1625 |
Feature activation | -2.49e-02 |
Pos logit contributions | |
hands | +0.031 |
sle | +0.031 |
paws | +0.029 |
fingers | +0.026 |
apr | +0.026 |
Neg logit contributions | |
ained | -0.054 |
ectar | -0.047 |
Ag | -0.047 |
THE | -0.047 |
ust | -0.046 |
Token | back |
Token ID | 736 |
Feature activation | -1.08e-02 |
Pos logit contributions | |
hands | +0.032 |
sle | +0.028 |
paws | +0.027 |
Daddy | +0.026 |
fingers | +0.025 |
Neg logit contributions | |
ained | -0.050 |
Prin | -0.045 |
Ag | -0.045 |
ectar | -0.044 |
ust | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | -5.87e-04 |
Pos logit contributions | |
hands | +0.015 |
sle | +0.014 |
paws | +0.013 |
Daddy | +0.013 |
fingers | +0.012 |
Neg logit contributions | |
ained | -0.021 |
ust | -0.018 |
Prin | -0.018 |
Ag | -0.018 |
THE | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +9.04e-03 |
Pos logit contributions | |
hands | +0.001 |
sle | +0.001 |
paws | +0.001 |
Daddy | +0.000 |
apr | +0.000 |
Neg logit contributions | |
ained | -0.001 |
ectar | -0.001 |
ust | -0.001 |
THE | -0.001 |
Ag | -0.001 |
Token | picnic |
Token ID | 35715 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
hands | +0.001 |
paws | +0.001 |
fingers | +0.001 |
sle | +0.001 |
cheeks | +0.001 |
Neg logit contributions | |
THE | -0.001 |
Ag | -0.001 |
ust | -0.001 |
Prin | -0.001 |
perspective | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.17e-02 |
Pos logit contributions | |
ained | +0.034 |
Ag | +0.031 |
Prin | +0.031 |
Kay | +0.030 |
ust | +0.030 |
Neg logit contributions | |
hands | -0.025 |
sle | -0.024 |
paws | -0.023 |
plates | -0.021 |
forks | -0.021 |
Token | Pete |
Token ID | 17542 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
sle | +0.019 |
hands | +0.017 |
paws | +0.016 |
pans | +0.016 |
apr | +0.016 |
Neg logit contributions | |
ained | -0.019 |
THE | -0.016 |
Ag | -0.016 |
ectar | -0.016 |
Prin | -0.016 |
Token | had |
Token ID | 550 |
Feature activation | +9.00e-03 |
Pos logit contributions | |
sle | +0.018 |
hands | +0.017 |
paws | +0.016 |
fingers | +0.016 |
pans | +0.016 |
Neg logit contributions | |
ained | -0.015 |
Prin | -0.014 |
Ag | -0.014 |
THE | -0.014 |
Kay | -0.013 |
Token | been |
Token ID | 587 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
ained | +0.017 |
ectar | +0.015 |
Ag | +0.015 |
ust | +0.014 |
Prin | +0.014 |
Neg logit contributions | |
hands | -0.012 |
sle | -0.012 |
paws | -0.011 |
apr | -0.011 |
fingers | -0.011 |
Token | wanting |
Token ID | 10291 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
hands | +0.018 |
sle | +0.018 |
paws | +0.017 |
cheeks | +0.017 |
fingers | +0.017 |
Neg logit contributions | |
ained | -0.024 |
Ag | -0.021 |
ectar | -0.021 |
known | -0.020 |
Prin | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +5.96e-03 |
Pos logit contributions | |
hands | +0.045 |
sle | +0.044 |
paws | +0.042 |
fingers | +0.040 |
apr | +0.039 |
Neg logit contributions | |
ained | -0.059 |
Ag | -0.051 |
THE | -0.051 |
Prin | -0.050 |
ectar | -0.050 |
Token | go |
Token ID | 467 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
ained | +0.012 |
THE | +0.011 |
Ag | +0.011 |
ectar | +0.011 |
Prin | +0.011 |
Neg logit contributions | |
hands | -0.007 |
sle | -0.006 |
paws | -0.006 |
fingers | -0.006 |
apr | -0.006 |
Token | for |
Token ID | 329 |
Feature activation | +1.20e-02 |
Pos logit contributions | |
hands | +0.037 |
sle | +0.036 |
paws | +0.034 |
apr | +0.033 |
fingers | +0.033 |
Neg logit contributions | |
ained | -0.040 |
THE | -0.035 |
Ag | -0.034 |
ectar | -0.034 |
Prin | -0.033 |
Token | weeks |
Token ID | 2745 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
ained | +0.022 |
THE | +0.020 |
Ag | +0.020 |
Kay | +0.019 |
ectar | +0.019 |
Neg logit contributions | |
sle | -0.015 |
hands | -0.015 |
fingers | -0.013 |
paws | -0.013 |
chin | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +2.27e-02 |
Pos logit contributions | |
hands | +0.017 |
sle | +0.016 |
paws | +0.015 |
fingers | +0.014 |
Daddy | +0.014 |
Neg logit contributions | |
ained | -0.023 |
Prin | -0.021 |
Ag | -0.021 |
THE | -0.020 |
ectar | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -7.23e-03 |
Pos logit contributions | |
ained | +0.021 |
Prin | +0.019 |
Ag | +0.019 |
Kay | +0.018 |
THE | +0.018 |
Neg logit contributions | |
hands | -0.011 |
fingers | -0.009 |
paws | -0.009 |
eyes | -0.009 |
Daddy | -0.009 |
Token | They |
Token ID | 1119 |
Feature activation | -1.53e-02 |
Pos logit contributions | |
hands | +0.012 |
paws | +0.011 |
sle | +0.010 |
Daddy | +0.010 |
fingers | +0.010 |
Neg logit contributions | |
ained | -0.012 |
THE | -0.011 |
Ag | -0.011 |
perspective | -0.011 |
ust | -0.011 |
Token | say |
Token ID | 910 |
Feature activation | -3.89e-03 |
Pos logit contributions | |
hands | +0.017 |
sle | +0.015 |
paws | +0.015 |
fingers | +0.014 |
load | +0.013 |
Neg logit contributions | |
ained | -0.034 |
ectar | -0.031 |
THE | -0.030 |
Ag | -0.030 |
perspective | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +9.37e-04 |
Pos logit contributions | |
hands | +0.003 |
sle | +0.003 |
paws | +0.003 |
Daddy | +0.003 |
fingers | +0.003 |
Neg logit contributions | |
ained | -0.010 |
THE | -0.008 |
ust | -0.008 |
perspective | -0.008 |
Ag | -0.008 |
Token | " |
Token ID | 366 |
Feature activation | +4.78e-03 |
Pos logit contributions | |
ained | +0.002 |
ust | +0.002 |
Ag | +0.002 |
perspective | +0.002 |
THE | +0.002 |
Neg logit contributions | |
hands | -0.001 |
sle | -0.001 |
paws | -0.001 |
fingers | -0.001 |
Daddy | -0.001 |
Token | M |
Token ID | 44 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
ained | +0.008 |
fault | +0.008 |
ectar | +0.007 |
olving | +0.007 |
eway | +0.007 |
Neg logit contributions | |
hands | -0.007 |
pans | -0.007 |
fingers | -0.006 |
paws | -0.006 |
sle | -0.006 |
Token | ia |
Token ID | 544 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
hands | +0.070 |
sle | +0.067 |
paws | +0.066 |
fingers | +0.063 |
cheeks | +0.062 |
Neg logit contributions | |
ained | -0.053 |
Prin | -0.045 |
Ag | -0.045 |
THE | -0.044 |
perspective | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
hands | +0.020 |
paws | +0.017 |
sle | +0.015 |
fingers | +0.014 |
Daddy | +0.013 |
Neg logit contributions | |
ained | -0.059 |
Ag | -0.054 |
ectar | -0.054 |
THE | -0.054 |
ust | -0.053 |
Token | that |
Token ID | 326 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
hands | +0.019 |
sle | +0.019 |
paws | +0.018 |
apr | +0.017 |
fingers | +0.017 |
Neg logit contributions | |
ained | -0.026 |
THE | -0.023 |
Ag | -0.023 |
ectar | -0.022 |
Prin | -0.022 |
Token | is |
Token ID | 318 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
ained | +0.005 |
ectar | +0.004 |
Ag | +0.004 |
perspective | +0.004 |
THE | +0.004 |
Neg logit contributions | |
hands | -0.001 |
paws | -0.001 |
t | -0.001 |
sle | -0.001 |
nose | -0.001 |
Token | not |
Token ID | 407 |
Feature activation | -2.78e-02 |
Pos logit contributions | |
hands | +0.029 |
sle | +0.028 |
paws | +0.026 |
Daddy | +0.026 |
pans | +0.025 |
Neg logit contributions | |
ained | -0.040 |
perspective | -0.038 |
ectar | -0.036 |
Ag | -0.036 |
THE | -0.035 |
Token | old |
Token ID | 1468 |
Feature activation | +2.15e-02 |
Pos logit contributions | |
sle | +0.013 |
hands | +0.012 |
paws | +0.011 |
apr | +0.011 |
forks | +0.011 |
Neg logit contributions | |
ained | -0.017 |
ust | -0.015 |
THE | -0.014 |
Ag | -0.014 |
Prin | -0.014 |
Token | man |
Token ID | 582 |
Feature activation | +8.91e-03 |
Pos logit contributions | |
ained | +0.047 |
ust | +0.042 |
THE | +0.041 |
ectar | +0.041 |
ount | +0.040 |
Neg logit contributions | |
hands | -0.026 |
sle | -0.025 |
paws | -0.024 |
Daddy | -0.024 |
white | -0.023 |
Token | sitting |
Token ID | 5586 |
Feature activation | +2.92e-03 |
Pos logit contributions | |
ained | +0.017 |
ectar | +0.015 |
THE | +0.015 |
ust | +0.015 |
Ag | +0.015 |
Neg logit contributions | |
sle | -0.012 |
hands | -0.012 |
paws | -0.011 |
fingers | -0.010 |
pans | -0.010 |
Token | nearby |
Token ID | 6716 |
Feature activation | -1.01e-02 |
Pos logit contributions | |
ained | +0.006 |
ust | +0.006 |
Ag | +0.006 |
fault | +0.005 |
ectar | +0.005 |
Neg logit contributions | |
hands | -0.004 |
sle | -0.003 |
paws | -0.003 |
pans | -0.003 |
fingers | -0.003 |
Token | called |
Token ID | 1444 |
Feature activation | -4.24e-02 |
Pos logit contributions | |
hands | +0.011 |
sle | +0.010 |
Daddy | +0.010 |
paws | +0.010 |
load | +0.009 |
Neg logit contributions | |
ained | -0.023 |
ectar | -0.021 |
ust | -0.021 |
Ag | -0.020 |
THE | -0.020 |
Token | out |
Token ID | 503 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
hands | +0.045 |
sle | +0.044 |
paws | +0.041 |
fingers | +0.037 |
apr | +0.037 |
Neg logit contributions | |
ained | -0.092 |
Ag | -0.081 |
THE | -0.081 |
ectar | -0.081 |
ust | -0.080 |
Token | to |
Token ID | 284 |
Feature activation | -2.29e-02 |
Pos logit contributions | |
hands | +0.057 |
sle | +0.055 |
paws | +0.053 |
fingers | +0.049 |
Daddy | +0.048 |
Neg logit contributions | |
ained | -0.072 |
Ag | -0.061 |
THE | -0.061 |
Prin | -0.061 |
ectar | -0.061 |
Token | him |
Token ID | 683 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
sle | +0.029 |
hands | +0.029 |
paws | +0.027 |
fingers | +0.025 |
pans | +0.025 |
Neg logit contributions | |
ained | -0.042 |
Ag | -0.038 |
Prin | -0.038 |
THE | -0.038 |
Kay | -0.037 |
Token | . |
Token ID | 13 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
hands | +0.031 |
sle | +0.028 |
paws | +0.027 |
Daddy | +0.026 |
cub | +0.025 |
Neg logit contributions | |
ained | -0.061 |
Ag | -0.055 |
Prin | -0.054 |
THE | -0.052 |
Kay | -0.052 |
Token | He |
Token ID | 679 |
Feature activation | -1.66e-02 |
Pos logit contributions | |
sle | +0.017 |
hands | +0.017 |
paws | +0.016 |
apr | +0.016 |
fingers | +0.015 |
Neg logit contributions | |
ained | -0.019 |
Prin | -0.017 |
Ag | -0.016 |
THE | -0.016 |
ectar | -0.016 |
Token | said |
Token ID | 531 |
Feature activation | -6.56e-04 |
Pos logit contributions | |
hands | +0.022 |
sle | +0.021 |
paws | +0.020 |
fingers | +0.019 |
apr | +0.019 |
Neg logit contributions | |
ained | -0.032 |
ectar | -0.028 |
THE | -0.028 |
Ag | -0.027 |
perspective | -0.027 |
Token | said |
Token ID | 531 |
Feature activation | +3.64e-03 |
Pos logit contributions | |
hands | +0.001 |
sle | +0.001 |
paws | +0.001 |
apr | +0.001 |
fingers | +0.001 |
Neg logit contributions | |
ained | -0.001 |
Ag | -0.001 |
THE | -0.001 |
Prin | -0.001 |
ectar | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +9.97e-03 |
Pos logit contributions | |
ained | +0.010 |
ust | +0.009 |
perspective | +0.009 |
THE | +0.009 |
inas | +0.008 |
Neg logit contributions | |
hands | -0.003 |
paws | -0.002 |
sle | -0.002 |
Daddy | -0.002 |
cheeks | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | +5.33e-03 |
Pos logit contributions | |
ained | +0.021 |
ust | +0.019 |
perspective | +0.018 |
THE | +0.018 |
ectar | +0.018 |
Neg logit contributions | |
hands | -0.012 |
sle | -0.011 |
paws | -0.011 |
Daddy | -0.010 |
fingers | -0.010 |
Token | Angel |
Token ID | 33246 |
Feature activation | -2.39e-02 |
Pos logit contributions | |
ained | +0.009 |
fault | +0.008 |
ectar | +0.008 |
ying | +0.008 |
ier | +0.008 |
Neg logit contributions | |
hands | -0.008 |
sle | -0.008 |
paws | -0.007 |
pans | -0.007 |
apr | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
hands | +0.021 |
sle | +0.021 |
paws | +0.019 |
Daddy | +0.017 |
pans | +0.017 |
Neg logit contributions | |
ained | -0.056 |
Ag | -0.050 |
THE | -0.050 |
Prin | -0.049 |
ust | -0.049 |
Token | let |
Token ID | 1309 |
Feature activation | -3.18e-02 |
Pos logit contributions | |
hands | +0.012 |
sle | +0.012 |
paws | +0.011 |
Daddy | +0.010 |
fingers | +0.010 |
Neg logit contributions | |
ained | -0.024 |
Ag | -0.021 |
ectar | -0.020 |
THE | -0.020 |
Prin | -0.020 |
Token | us |
Token ID | 514 |
Feature activation | -6.46e-03 |
Pos logit contributions | |
sle | +0.040 |
hands | +0.037 |
apr | +0.036 |
fingers | +0.036 |
cheeks | +0.036 |
Neg logit contributions | |
ained | -0.058 |
Prin | -0.056 |
THE | -0.055 |
Kay | -0.052 |
Ag | -0.052 |
Token | look |
Token ID | 804 |
Feature activation | -3.08e-03 |
Pos logit contributions | |
sle | +0.008 |
hands | +0.007 |
apr | +0.007 |
paws | +0.007 |
pans | +0.007 |
Neg logit contributions | |
ained | -0.013 |
THE | -0.011 |
ectar | -0.011 |
Ag | -0.011 |
ust | -0.011 |
Token | over |
Token ID | 625 |
Feature activation | -2.65e-02 |
Pos logit contributions | |
hands | +0.004 |
sle | +0.004 |
paws | +0.004 |
fingers | +0.003 |
Daddy | +0.003 |
Neg logit contributions | |
ained | -0.006 |
Ag | -0.005 |
Prin | -0.005 |
ectar | -0.005 |
THE | -0.005 |
Token | there |
Token ID | 612 |
Feature activation | -5.16e-03 |
Pos logit contributions | |
hands | +0.037 |
sle | +0.035 |
paws | +0.033 |
fingers | +0.031 |
Daddy | +0.031 |
Neg logit contributions | |
ained | -0.049 |
Ag | -0.043 |
Prin | -0.043 |
ust | -0.042 |
ectar | -0.042 |
Token | by |
Token ID | 416 |
Feature activation | +1.79e-03 |
Pos logit contributions | |
hands | +0.006 |
sle | +0.006 |
paws | +0.006 |
Daddy | +0.005 |
fingers | +0.005 |
Neg logit contributions | |
ained | -0.010 |
Ag | -0.009 |
Prin | -0.009 |
Kay | -0.009 |
THE | -0.009 |