Token | get |
Token ID | 651 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
coc | +0.009 |
notebook | +0.009 |
goals | +0.008 |
packs | +0.008 |
goal | +0.008 |
Neg logit contributions | |
Chick | -0.006 |
bo | -0.006 |
him | -0.006 |
hey | -0.006 |
E | -0.006 |
Token | money |
Token ID | 1637 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
coc | +0.004 |
notebook | +0.004 |
goals | +0.004 |
goal | +0.004 |
trove | +0.004 |
Neg logit contributions | |
Chick | -0.003 |
bo | -0.003 |
him | -0.003 |
E | -0.003 |
Ch | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
him | +0.003 |
bo | +0.002 |
Chick | +0.002 |
B | +0.002 |
head | +0.002 |
Neg logit contributions | |
coc | -0.005 |
goals | -0.004 |
notebook | -0.004 |
goal | -0.004 |
Statue | -0.004 |
Token | buy |
Token ID | 2822 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
coc | +0.019 |
notebook | +0.019 |
goals | +0.018 |
pad | +0.018 |
packs | +0.017 |
Neg logit contributions | |
him | -0.009 |
Chick | -0.007 |
B | -0.007 |
Baby | -0.007 |
Ethan | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
coc | +0.047 |
notebook | +0.046 |
goal | +0.045 |
trove | +0.045 |
goals | +0.044 |
Neg logit contributions | |
him | -0.033 |
Chick | -0.029 |
B | -0.028 |
bo | -0.028 |
Baby | -0.027 |
Token | l |
Token ID | 300 |
Feature activation | +4.92e+00 |
Pos logit contributions | |
him | +0.001 |
Baby | +0.001 |
B | +0.001 |
Ethan | +0.001 |
bo | +0.001 |
Neg logit contributions | |
coc | -0.001 |
packs | -0.001 |
adow | -0.001 |
impressed | -0.001 |
tal | -0.001 |
Token | oll |
Token ID | 692 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
amaz | +0.167 |
mistake | +0.165 |
culture | +0.160 |
packs | +0.156 |
languages | +0.155 |
Neg logit contributions | |
bo | -0.082 |
izz | -0.073 |
head | -0.071 |
ick | -0.069 |
E | -0.068 |
Token | ipop |
Token ID | 42800 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
coc | +0.039 |
notebook | +0.035 |
goals | +0.035 |
goal | +0.033 |
trove | +0.031 |
Neg logit contributions | |
Chick | -0.066 |
bo | -0.066 |
him | -0.063 |
E | -0.060 |
head | -0.060 |
Token | . |
Token ID | 13 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
coc | +0.091 |
ey | +0.091 |
amaz | +0.090 |
culture | +0.088 |
goals | +0.088 |
Neg logit contributions | |
him | -0.028 |
bo | -0.023 |
Chick | -0.021 |
B | -0.020 |
head | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
coc | +0.005 |
notebook | +0.005 |
goals | +0.005 |
goal | +0.005 |
trove | +0.005 |
Neg logit contributions | |
Chick | -0.004 |
bo | -0.004 |
Ch | -0.003 |
E | -0.003 |
him | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
Chick | +0.002 |
bo | +0.002 |
Ch | +0.002 |
E | +0.002 |
him | +0.002 |
Neg logit contributions | |
coc | -0.003 |
notebook | -0.003 |
goals | -0.003 |
goal | -0.002 |
trove | -0.002 |
Token | be |
Token ID | 307 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
packs | +0.026 |
notebook | +0.024 |
adow | +0.024 |
ymes | +0.023 |
aj | +0.023 |
Neg logit contributions | |
him | -0.015 |
care | -0.014 |
B | -0.014 |
Chick | -0.013 |
bo | -0.013 |
Token | fun |
Token ID | 1257 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
coc | +0.034 |
notebook | +0.033 |
goal | +0.032 |
Statue | +0.032 |
poem | +0.030 |
Neg logit contributions | |
him | -0.026 |
Chick | -0.026 |
B | -0.024 |
bo | -0.024 |
Baby | -0.022 |
Token | to |
Token ID | 284 |
Feature activation | +4.97e-02 |
Pos logit contributions | |
coc | +0.026 |
notebook | +0.025 |
trove | +0.024 |
goals | +0.024 |
goal | +0.023 |
Neg logit contributions | |
him | -0.021 |
Chick | -0.020 |
B | -0.019 |
bo | -0.019 |
head | -0.018 |
Token | wrap |
Token ID | 14441 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
coc | +0.002 |
notebook | +0.001 |
goals | +0.001 |
goal | +0.001 |
trove | +0.001 |
Neg logit contributions | |
Chick | -0.001 |
bo | -0.001 |
Ch | -0.001 |
E | -0.001 |
him | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
Chick | +0.002 |
bo | +0.002 |
Ch | +0.002 |
E | +0.002 |
hey | +0.002 |
Neg logit contributions | |
coc | -0.004 |
notebook | -0.004 |
goals | -0.004 |
goal | -0.004 |
book | -0.004 |
Token | l |
Token ID | 300 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
packs | +0.015 |
adow | +0.015 |
culture | +0.014 |
notebook | +0.013 |
speech | +0.013 |
Neg logit contributions | |
E | -0.017 |
bo | -0.017 |
Chick | -0.016 |
B | -0.016 |
B | -0.016 |
Token | imes |
Token ID | 999 |
Feature activation | +3.79e+00 |
Pos logit contributions | |
culture | +0.104 |
notebook | +0.103 |
coc | +0.102 |
amaz | +0.099 |
packs | +0.099 |
Neg logit contributions | |
bo | -0.141 |
Chick | -0.132 |
E | -0.132 |
head | -0.128 |
B | -0.127 |
Token | with |
Token ID | 351 |
Feature activation | -9.11e-02 |
Pos logit contributions | |
coc | +0.118 |
notebook | +0.113 |
culture | +0.110 |
Statue | +0.110 |
poem | +0.109 |
Neg logit contributions | |
him | -0.077 |
bo | -0.073 |
Chick | -0.069 |
B | -0.064 |
B | -0.062 |
Token | string |
Token ID | 4731 |
Feature activation | -9.27e-01 |
Pos logit contributions | |
Chick | +0.002 |
bo | +0.002 |
him | +0.002 |
E | +0.001 |
Ch | +0.001 |
Neg logit contributions | |
coc | -0.003 |
notebook | -0.003 |
goals | -0.003 |
trove | -0.003 |
goal | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +6.20e-01 |
Pos logit contributions | |
Chick | +0.020 |
bo | +0.020 |
him | +0.019 |
B | +0.018 |
head | +0.017 |
Neg logit contributions | |
coc | -0.027 |
notebook | -0.027 |
goals | -0.025 |
trove | -0.025 |
goal | -0.024 |
Token | So |
Token ID | 1406 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
coc | +0.020 |
notebook | +0.020 |
goals | +0.019 |
trove | +0.018 |
goal | +0.018 |
Neg logit contributions | |
Chick | -0.011 |
bo | -0.011 |
him | -0.010 |
Ch | -0.010 |
E | -0.010 |
Token | She |
Token ID | 1375 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
coc | +0.009 |
notebook | +0.009 |
goals | +0.009 |
packs | +0.009 |
trove | +0.009 |
Neg logit contributions | |
Chick | -0.004 |
B | -0.004 |
Baby | -0.004 |
E | -0.004 |
Ch | -0.003 |
Token | wanted |
Token ID | 2227 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
ours | +0.025 |
packs | +0.024 |
decisions | +0.023 |
goals | +0.023 |
property | +0.023 |
Neg logit contributions | |
B | -0.010 |
Chick | -0.010 |
bo | -0.010 |
Ch | -0.009 |
Baby | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
coc | +0.016 |
notebook | +0.016 |
goals | +0.015 |
trove | +0.015 |
packs | +0.015 |
Neg logit contributions | |
Chick | -0.016 |
him | -0.015 |
bo | -0.015 |
B | -0.014 |
Baby | -0.014 |
Token | steal |
Token ID | 8711 |
Feature activation | +2.04e+00 |
Pos logit contributions | |
goals | +0.020 |
packs | +0.020 |
notebook | +0.020 |
trove | +0.019 |
ymes | +0.019 |
Neg logit contributions | |
him | -0.008 |
care | -0.007 |
B | -0.007 |
bo | -0.006 |
Chick | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
notebook | +0.069 |
trove | +0.069 |
packs | +0.067 |
adow | +0.067 |
stash | +0.065 |
Neg logit contributions | |
him | -0.039 |
B | -0.032 |
E | -0.031 |
Chick | -0.030 |
them | -0.030 |
Token | l |
Token ID | 300 |
Feature activation | +4.88e+00 |
Pos logit contributions | |
packs | +0.009 |
adow | +0.008 |
goals | +0.008 |
lair | +0.008 |
impressed | +0.008 |
Neg logit contributions | |
E | -0.008 |
B | -0.008 |
Chick | -0.008 |
head | -0.008 |
bo | -0.008 |
Token | ily |
Token ID | 813 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
culture | +0.148 |
packs | +0.143 |
amaz | +0.139 |
mistake | +0.139 |
languages | +0.139 |
Neg logit contributions | |
bo | -0.096 |
Chick | -0.088 |
head | -0.088 |
E | -0.087 |
Ch | -0.085 |
Token | to |
Token ID | 284 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
oral | +0.014 |
impressed | +0.013 |
ey | +0.013 |
pleased | +0.012 |
culture | +0.012 |
Neg logit contributions | |
bo | -0.007 |
him | -0.007 |
B | -0.007 |
Chick | -0.006 |
ny | -0.006 |
Token | keep |
Token ID | 1394 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
packs | +0.030 |
notebook | +0.030 |
aj | +0.029 |
endant | +0.029 |
goals | +0.029 |
Neg logit contributions | |
him | -0.015 |
them | -0.011 |
B | -0.011 |
care | -0.010 |
hey | -0.009 |
Token | it |
Token ID | 340 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
him | +0.005 |
Chick | +0.005 |
bo | +0.004 |
B | +0.004 |
Baby | +0.004 |
Neg logit contributions | |
coc | -0.008 |
notebook | -0.007 |
goals | -0.007 |
goal | -0.007 |
trove | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
coc | +0.004 |
notebook | +0.004 |
culture | +0.004 |
Statue | +0.004 |
goals | +0.004 |
Neg logit contributions | |
bo | -0.002 |
him | -0.002 |
Chick | -0.002 |
B | -0.002 |
Baby | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.84e-01 |
Pos logit contributions | |
him | +0.011 |
B | +0.010 |
cl | +0.010 |
Chick | +0.009 |
bo | +0.009 |
Neg logit contributions | |
coc | -0.030 |
goals | -0.030 |
notebook | -0.029 |
ey | -0.029 |
ours | -0.028 |
Token | She |
Token ID | 1375 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
coc | +0.007 |
notebook | +0.007 |
goals | +0.007 |
trove | +0.006 |
stash | +0.006 |
Neg logit contributions | |
Chick | -0.002 |
Baby | -0.002 |
B | -0.002 |
E | -0.002 |
head | -0.002 |
Token | carefully |
Token ID | 7773 |
Feature activation | -5.77e-01 |
Pos logit contributions | |
ours | +0.019 |
coc | +0.018 |
languages | +0.018 |
notebook | +0.018 |
goals | +0.018 |
Neg logit contributions | |
bo | -0.008 |
Baby | -0.008 |
Chick | -0.008 |
B | -0.007 |
him | -0.007 |
Token | placed |
Token ID | 4624 |
Feature activation | -7.54e-02 |
Pos logit contributions | |
Chick | +0.011 |
bo | +0.011 |
him | +0.010 |
Ch | +0.010 |
B | +0.010 |
Neg logit contributions | |
coc | -0.019 |
notebook | -0.018 |
goals | -0.018 |
goal | -0.017 |
trove | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +5.70e-01 |
Pos logit contributions | |
Chick | +0.002 |
bo | +0.002 |
him | +0.002 |
Ch | +0.002 |
E | +0.001 |
Neg logit contributions | |
coc | -0.002 |
notebook | -0.002 |
goals | -0.002 |
goal | -0.002 |
trove | -0.002 |
Token | l |
Token ID | 300 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
packs | +0.018 |
adow | +0.016 |
goals | +0.016 |
lair | +0.016 |
slaves | +0.016 |
Neg logit contributions | |
head | -0.011 |
bo | -0.011 |
B | -0.011 |
E | -0.011 |
St | -0.011 |
Token | imes |
Token ID | 999 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
notebook | +0.112 |
coc | +0.112 |
culture | +0.108 |
mistake | +0.106 |
goals | +0.105 |
Neg logit contributions | |
bo | -0.133 |
Chick | -0.127 |
Ch | -0.124 |
head | -0.124 |
E | -0.122 |
Token | in |
Token ID | 287 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
coc | +0.123 |
culture | +0.121 |
Statue | +0.119 |
notebook | +0.118 |
goals | +0.117 |
Neg logit contributions | |
him | -0.075 |
bo | -0.073 |
Chick | -0.065 |
B | -0.062 |
B | -0.062 |
Token | an |
Token ID | 281 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
notebook | +0.009 |
goals | +0.009 |
coc | +0.009 |
slaves | +0.009 |
adow | +0.008 |
Neg logit contributions | |
him | -0.004 |
Chick | -0.004 |
B | -0.004 |
Baby | -0.003 |
E | -0.003 |
Token | open |
Token ID | 1280 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
packs | +0.013 |
notebook | +0.013 |
trove | +0.012 |
coc | +0.012 |
kins | +0.012 |
Neg logit contributions | |
bo | -0.013 |
him | -0.013 |
Baby | -0.011 |
Chick | -0.011 |
E | -0.011 |
Token | space |
Token ID | 2272 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
head | +0.005 |
Baby | +0.005 |
B | +0.005 |
Chick | +0.005 |
bo | +0.005 |
Neg logit contributions | |
impressed | -0.005 |
slaves | -0.005 |
cooperative | -0.005 |
culture | -0.004 |
classmates | -0.004 |
Token | together |
Token ID | 1978 |
Feature activation | -7.20e-01 |
Pos logit contributions | |
bo | +0.019 |
Chick | +0.018 |
him | +0.018 |
Ch | +0.017 |
E | +0.017 |
Neg logit contributions | |
coc | -0.018 |
notebook | -0.017 |
goals | -0.015 |
trove | -0.015 |
poem | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
him | +0.014 |
them | +0.011 |
Chick | +0.010 |
B | +0.010 |
bo | +0.010 |
Neg logit contributions | |
coc | -0.024 |
notebook | -0.024 |
Statue | -0.023 |
ey | -0.022 |
endant | -0.022 |
Token | carefully |
Token ID | 7773 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
coc | +0.011 |
notebook | +0.011 |
goals | +0.010 |
packs | +0.010 |
adow | +0.010 |
Neg logit contributions | |
him | -0.006 |
Chick | -0.006 |
bo | -0.006 |
hey | -0.006 |
B | -0.006 |
Token | pick |
Token ID | 2298 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
him | +0.016 |
them | +0.013 |
bo | +0.012 |
B | +0.012 |
care | +0.011 |
Neg logit contributions | |
coc | -0.033 |
notebook | -0.031 |
pleased | -0.031 |
slaves | -0.030 |
trove | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
coc | +0.020 |
notebook | +0.020 |
trove | +0.019 |
goals | +0.018 |
goal | +0.018 |
Neg logit contributions | |
Chick | -0.015 |
bo | -0.015 |
him | -0.015 |
E | -0.014 |
B | -0.014 |
Token | l |
Token ID | 300 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
packs | +0.005 |
notebook | +0.005 |
impressed | +0.005 |
adow | +0.005 |
journal | +0.005 |
Neg logit contributions | |
E | -0.003 |
B | -0.003 |
Chick | -0.003 |
St | -0.003 |
bo | -0.003 |
Token | ily |
Token ID | 813 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
culture | +0.156 |
impressed | +0.150 |
amaz | +0.150 |
mistake | +0.147 |
languages | +0.146 |
Neg logit contributions | |
bo | -0.087 |
E | -0.083 |
Ch | -0.081 |
head | -0.077 |
Chick | -0.076 |
Token | from |
Token ID | 422 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
impressed | +0.001 |
pleased | +0.001 |
ey | +0.001 |
coc | +0.001 |
culture | +0.001 |
Neg logit contributions | |
bo | -0.000 |
B | -0.000 |
him | -0.000 |
Chick | -0.000 |
ny | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | -2.90e-01 |
Pos logit contributions | |
notebook | +0.023 |
coc | +0.023 |
adow | +0.023 |
trove | +0.023 |
stash | +0.022 |
Neg logit contributions | |
him | -0.014 |
Chick | -0.012 |
B | -0.012 |
Baby | -0.012 |
E | -0.011 |
Token | bush |
Token ID | 24484 |
Feature activation | +7.67e-01 |
Pos logit contributions | |
E | +0.005 |
B | +0.005 |
St | +0.005 |
Chick | +0.005 |
Mitt | +0.005 |
Neg logit contributions | |
packs | -0.010 |
impressed | -0.009 |
adow | -0.009 |
pleased | -0.008 |
languages | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
ey | +0.030 |
coc | +0.029 |
culture | +0.029 |
notebook | +0.029 |
poem | +0.028 |
Neg logit contributions | |
Chick | -0.008 |
him | -0.008 |
B | -0.008 |
head | -0.007 |
bo | -0.007 |
Token | " |
Token ID | 366 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
coc | +0.027 |
notebook | +0.025 |
packs | +0.024 |
goals | +0.024 |
adow | +0.023 |
Neg logit contributions | |
Chick | -0.029 |
B | -0.027 |
him | -0.027 |
Ch | -0.027 |
bo | -0.026 |
Token | Let |
Token ID | 5756 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
Chick | +0.018 |
bo | +0.017 |
him | +0.016 |
hey | +0.016 |
Ch | +0.015 |
Neg logit contributions | |
coc | -0.028 |
notebook | -0.027 |
goals | -0.026 |
goal | -0.025 |
poem | -0.025 |
Token | 's |
Token ID | 338 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
coc | +0.018 |
notebook | +0.017 |
goals | +0.016 |
trove | +0.016 |
packs | +0.015 |
Neg logit contributions | |
bo | -0.017 |
Chick | -0.017 |
him | -0.016 |
E | -0.016 |
Ch | -0.016 |
Token | sort |
Token ID | 3297 |
Feature activation | +4.60e-01 |
Pos logit contributions | |
Chick | +0.021 |
bo | +0.021 |
Ch | +0.019 |
E | +0.019 |
him | +0.019 |
Neg logit contributions | |
coc | -0.035 |
notebook | -0.034 |
goals | -0.032 |
goal | -0.031 |
trove | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | +5.45e-02 |
Pos logit contributions | |
notebook | +0.013 |
coc | +0.013 |
trove | +0.013 |
adow | +0.013 |
goals | +0.012 |
Neg logit contributions | |
Chick | -0.010 |
him | -0.010 |
bo | -0.009 |
E | -0.009 |
B | -0.009 |
Token | l |
Token ID | 300 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
packs | +0.001 |
notebook | +0.001 |
adow | +0.001 |
coc | +0.001 |
alk | +0.001 |
Neg logit contributions | |
E | -0.001 |
bo | -0.001 |
Chick | -0.001 |
him | -0.001 |
B | -0.001 |
Token | oll |
Token ID | 692 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
notebook | +0.162 |
coc | +0.160 |
culture | +0.159 |
packs | +0.155 |
network | +0.154 |
Neg logit contributions | |
bo | -0.081 |
E | -0.076 |
Chick | -0.074 |
Ch | -0.070 |
head | -0.069 |
Token | ipop |
Token ID | 42800 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
coc | +0.046 |
notebook | +0.044 |
goals | +0.040 |
goal | +0.038 |
trove | +0.037 |
Neg logit contributions | |
Chick | -0.081 |
bo | -0.080 |
him | -0.076 |
E | -0.076 |
Ch | -0.076 |
Token | into |
Token ID | 656 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
culture | +0.077 |
joy | +0.076 |
amaz | +0.074 |
languages | +0.073 |
poem | +0.073 |
Neg logit contributions | |
Chick | -0.031 |
head | -0.030 |
him | -0.030 |
bo | -0.027 |
ick | -0.025 |
Token | different |
Token ID | 1180 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
adow | +0.035 |
notebook | +0.034 |
culture | +0.032 |
sed | +0.032 |
ses | +0.031 |
Neg logit contributions | |
Chick | -0.028 |
E | -0.027 |
Baby | -0.024 |
him | -0.024 |
B | -0.024 |
Token | colors |
Token ID | 7577 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
E | +0.017 |
him | +0.015 |
Chick | +0.015 |
B | +0.015 |
Baby | +0.014 |
Neg logit contributions | |
ses | -0.018 |
pleased | -0.017 |
sed | -0.017 |
ocket | -0.017 |
adow | -0.017 |
Token | " |
Token ID | 366 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
coc | +0.020 |
goals | +0.019 |
packs | +0.019 |
notebook | +0.019 |
ocket | +0.018 |
Neg logit contributions | |
B | -0.016 |
him | -0.015 |
Chick | -0.014 |
Baby | -0.013 |
Pe | -0.013 |
Token | Let |
Token ID | 5756 |
Feature activation | +5.84e-01 |
Pos logit contributions | |
Chick | +0.018 |
bo | +0.016 |
hey | +0.016 |
him | +0.016 |
head | +0.016 |
Neg logit contributions | |
coc | -0.029 |
notebook | -0.028 |
goals | -0.026 |
goal | -0.025 |
poem | -0.025 |
Token | 's |
Token ID | 338 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
coc | +0.014 |
notebook | +0.014 |
goals | +0.013 |
goal | +0.012 |
book | +0.012 |
Neg logit contributions | |
Chick | -0.016 |
bo | -0.015 |
Ch | -0.015 |
E | -0.014 |
him | -0.014 |
Token | sort |
Token ID | 3297 |
Feature activation | +5.06e-01 |
Pos logit contributions | |
Chick | +0.024 |
bo | +0.023 |
Ch | +0.023 |
head | +0.022 |
E | +0.022 |
Neg logit contributions | |
coc | -0.033 |
notebook | -0.032 |
goal | -0.030 |
goals | -0.030 |
book | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +3.19e-02 |
Pos logit contributions | |
coc | +0.013 |
notebook | +0.013 |
goals | +0.012 |
trove | +0.011 |
goal | +0.011 |
Neg logit contributions | |
Chick | -0.013 |
bo | -0.013 |
him | -0.012 |
E | -0.012 |
Ch | -0.012 |
Token | l |
Token ID | 300 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.001 |
packs | +0.001 |
adow | +0.001 |
goals | +0.001 |
Neg logit contributions | |
bo | -0.001 |
E | -0.001 |
Chick | -0.001 |
him | -0.001 |
B | -0.001 |
Token | oll |
Token ID | 692 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
notebook | +0.159 |
coc | +0.158 |
culture | +0.158 |
amaz | +0.154 |
mistake | +0.152 |
Neg logit contributions | |
bo | -0.081 |
E | -0.073 |
Chick | -0.072 |
head | -0.069 |
Ch | -0.069 |
Token | ipop |
Token ID | 42800 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
coc | +0.047 |
notebook | +0.045 |
goals | +0.041 |
goal | +0.039 |
trove | +0.038 |
Neg logit contributions | |
Chick | -0.076 |
bo | -0.075 |
him | -0.071 |
E | -0.071 |
Ch | -0.071 |
Token | ." |
Token ID | 526 |
Feature activation | +2.85e-01 |
Pos logit contributions | |
joy | +0.074 |
amaz | +0.073 |
culture | +0.072 |
ey | +0.070 |
pleased | +0.070 |
Neg logit contributions | |
Chick | -0.034 |
head | -0.033 |
him | -0.032 |
bo | -0.030 |
ick | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
coc | +0.008 |
notebook | +0.008 |
goals | +0.007 |
goal | +0.007 |
book | +0.007 |
Neg logit contributions | |
Chick | -0.007 |
bo | -0.007 |
Ch | -0.006 |
E | -0.006 |
him | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -5.29e-01 |
Pos logit contributions | |
Chick | +0.002 |
bo | +0.002 |
hey | +0.002 |
head | +0.002 |
lon | +0.001 |
Neg logit contributions | |
coc | -0.001 |
notebook | -0.001 |
book | -0.001 |
goal | -0.001 |
goals | -0.001 |
Token | ! |
Token ID | 0 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
notebook | +0.020 |
coc | +0.020 |
endant | +0.019 |
ey | +0.019 |
impressed | +0.019 |
Neg logit contributions | |
him | -0.014 |
bo | -0.013 |
B | -0.013 |
Chick | -0.013 |
head | -0.012 |
Token | I |
Token ID | 314 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
coc | +0.019 |
notebook | +0.018 |
goals | +0.017 |
stash | +0.017 |
mistake | +0.016 |
Neg logit contributions | |
Chick | -0.015 |
Ch | -0.015 |
bo | -0.015 |
B | -0.015 |
E | -0.014 |
Token | know |
Token ID | 760 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
bo | +0.003 |
him | +0.002 |
Chick | +0.002 |
B | +0.002 |
care | +0.002 |
Neg logit contributions | |
coc | -0.005 |
notebook | -0.004 |
goals | -0.004 |
poem | -0.004 |
sentences | -0.004 |
Token | where |
Token ID | 810 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
him | +0.005 |
B | +0.005 |
Chick | +0.005 |
Baby | +0.004 |
Pe | +0.004 |
Neg logit contributions | |
notebook | -0.008 |
coc | -0.008 |
pleased | -0.007 |
goal | -0.007 |
ey | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
trove | +0.004 |
impressed | +0.004 |
pleased | +0.004 |
coc | +0.004 |
bek | +0.004 |
Neg logit contributions | |
him | -0.002 |
B | -0.001 |
Chick | -0.001 |
Baby | -0.001 |
care | -0.001 |
Token | l |
Token ID | 300 |
Feature activation | +4.76e+00 |
Pos logit contributions | |
ushes | +0.019 |
packs | +0.019 |
impressed | +0.018 |
pleased | +0.018 |
ocus | +0.017 |
Neg logit contributions | |
head | -0.013 |
nurses | -0.013 |
B | -0.013 |
Chick | -0.013 |
him | -0.012 |
Token | ily |
Token ID | 813 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
mistake | +0.166 |
amaz | +0.161 |
impressed | +0.156 |
packs | +0.153 |
rightful | +0.153 |
Neg logit contributions | |
bo | -0.077 |
head | -0.069 |
E | -0.063 |
izz | -0.062 |
ch | -0.060 |
Token | is |
Token ID | 318 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
coc | +0.009 |
impressed | +0.009 |
pleased | +0.008 |
amaz | +0.008 |
ey | +0.008 |
Neg logit contributions | |
bo | -0.007 |
him | -0.006 |
B | -0.005 |
Chick | -0.005 |
head | -0.005 |
Token | ." |
Token ID | 526 |
Feature activation | +3.73e-01 |
Pos logit contributions | |
Chick | +0.005 |
him | +0.005 |
B | +0.005 |
bo | +0.005 |
Pink | +0.004 |
Neg logit contributions | |
ey | -0.011 |
notebook | -0.011 |
amaz | -0.011 |
coc | -0.011 |
bek | -0.010 |
Token | Maxwell |
Token ID | 28276 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
coc | +0.013 |
goals | +0.013 |
notebook | +0.012 |
trove | +0.012 |
culture | +0.012 |
Neg logit contributions | |
Chick | -0.007 |
B | -0.006 |
him | -0.006 |
bo | -0.006 |
Baby | -0.006 |
Token | followed |
Token ID | 3940 |
Feature activation | -3.63e-01 |
Pos logit contributions | |
bo | +0.002 |
him | +0.002 |
B | +0.002 |
Chick | +0.002 |
Baby | +0.002 |
Neg logit contributions | |
ours | -0.004 |
coc | -0.004 |
packs | -0.004 |
notebook | -0.004 |
goals | -0.004 |
Token | He |
Token ID | 679 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
coc | +0.009 |
notebook | +0.009 |
goals | +0.008 |
culture | +0.008 |
poem | +0.008 |
Neg logit contributions | |
Chick | -0.004 |
Baby | -0.004 |
B | -0.004 |
him | -0.004 |
E | -0.003 |
Token | quickly |
Token ID | 2952 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
Chick | +0.002 |
Ch | +0.002 |
bo | +0.002 |
cl | +0.002 |
B | +0.002 |
Neg logit contributions | |
coc | -0.005 |
ours | -0.005 |
goals | -0.005 |
languages | -0.005 |
culture | -0.005 |
Token | hung |
Token ID | 9174 |
Feature activation | +3.69e-01 |
Pos logit contributions | |
coc | +0.015 |
notebook | +0.014 |
goals | +0.014 |
goal | +0.014 |
Statue | +0.013 |
Neg logit contributions | |
Chick | -0.009 |
bo | -0.008 |
him | -0.008 |
Ch | -0.008 |
B | -0.008 |
Token | colorful |
Token ID | 20239 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
coc | +0.012 |
notebook | +0.012 |
adow | +0.011 |
goal | +0.011 |
poem | +0.011 |
Neg logit contributions | |
him | -0.007 |
Chick | -0.007 |
bo | -0.007 |
head | -0.006 |
B | -0.006 |
Token | or |
Token ID | 393 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
coc | +0.004 |
notebook | +0.004 |
adow | +0.004 |
goals | +0.004 |
goal | +0.004 |
Neg logit contributions | |
Chick | -0.005 |
him | -0.005 |
head | -0.005 |
bo | -0.005 |
cl | -0.004 |
Token | nam |
Token ID | 7402 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
tal | +0.019 |
coc | +0.018 |
adow | +0.018 |
alk | +0.018 |
oral | +0.017 |
Neg logit contributions | |
him | -0.010 |
hey | -0.010 |
cl | -0.010 |
Ethan | -0.010 |
Chick | -0.009 |
Token | ents |
Token ID | 658 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
coc | +0.062 |
notebook | +0.054 |
goals | +0.046 |
packs | +0.046 |
goal | +0.043 |
Neg logit contributions | |
Chick | -0.180 |
bo | -0.174 |
hey | -0.172 |
Ch | -0.171 |
him | -0.171 |
Token | and |
Token ID | 290 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
coc | +0.021 |
notebook | +0.021 |
goals | +0.019 |
goal | +0.019 |
culture | +0.019 |
Neg logit contributions | |
him | -0.017 |
bo | -0.017 |
Chick | -0.016 |
head | -0.016 |
cl | -0.015 |
Token | tw |
Token ID | 665 |
Feature activation | -4.99e-03 |
Pos logit contributions | |
Chick | +0.005 |
him | +0.005 |
B | +0.004 |
head | +0.004 |
Ch | +0.004 |
Neg logit contributions | |
adow | -0.009 |
coc | -0.009 |
goals | -0.008 |
oral | -0.008 |
alk | -0.008 |
Token | ink |
Token ID | 676 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
Chick | +0.000 |
bo | +0.000 |
Ch | +0.000 |
him | +0.000 |
E | +0.000 |
Neg logit contributions | |
coc | -0.000 |
notebook | -0.000 |
goals | -0.000 |
packs | -0.000 |
trove | -0.000 |
Token | ling |
Token ID | 1359 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
bo | +0.017 |
Chick | +0.015 |
him | +0.015 |
head | +0.014 |
Ch | +0.014 |
Neg logit contributions | |
coc | -0.030 |
notebook | -0.029 |
goal | -0.027 |
goals | -0.027 |
ours | -0.026 |
Token | But |
Token ID | 887 |
Feature activation | +3.78e-02 |
Pos logit contributions | |
coc | +0.013 |
notebook | +0.013 |
goal | +0.012 |
backpack | +0.011 |
net | +0.011 |
Neg logit contributions | |
hey | -0.015 |
bo | -0.014 |
Ch | -0.014 |
Chick | -0.013 |
head | -0.013 |
Token | as |
Token ID | 355 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.001 |
goals | +0.001 |
goal | +0.001 |
trove | +0.001 |
Neg logit contributions | |
Chick | -0.001 |
bo | -0.001 |
him | -0.001 |
Ch | -0.001 |
E | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | -9.74e-01 |
Pos logit contributions | |
bo | +0.024 |
hey | +0.022 |
Ch | +0.021 |
E | +0.021 |
Chick | +0.021 |
Neg logit contributions | |
coc | -0.038 |
notebook | -0.036 |
goal | -0.033 |
book | -0.032 |
goals | -0.032 |
Token | picked |
Token ID | 6497 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Chick | +0.026 |
bo | +0.026 |
hey | +0.025 |
head | +0.024 |
Ch | +0.024 |
Neg logit contributions | |
coc | -0.024 |
notebook | -0.022 |
stash | -0.020 |
goal | -0.020 |
goals | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +8.75e-02 |
Pos logit contributions | |
coc | +0.007 |
notebook | +0.007 |
book | +0.006 |
goal | +0.006 |
statue | +0.006 |
Neg logit contributions | |
Ch | -0.010 |
hey | -0.010 |
bo | -0.010 |
Chick | -0.009 |
head | -0.009 |
Token | l |
Token ID | 300 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
coc | +0.002 |
notebook | +0.002 |
packs | +0.002 |
goals | +0.002 |
adow | +0.002 |
Neg logit contributions | |
Chick | -0.002 |
bo | -0.002 |
E | -0.002 |
Ch | -0.002 |
B | -0.002 |
Token | ily |
Token ID | 813 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
coc | +0.120 |
notebook | +0.119 |
packs | +0.116 |
goals | +0.116 |
culture | +0.115 |
Neg logit contributions | |
bo | -0.108 |
Chick | -0.107 |
E | -0.103 |
Ch | -0.102 |
him | -0.100 |
Token | , |
Token ID | 11 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
coc | +0.017 |
notebook | +0.017 |
goals | +0.016 |
culture | +0.016 |
speech | +0.016 |
Neg logit contributions | |
Chick | -0.013 |
bo | -0.012 |
him | -0.012 |
B | -0.012 |
E | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
coc | +0.041 |
notebook | +0.040 |
goals | +0.038 |
goal | +0.037 |
trove | +0.037 |
Neg logit contributions | |
Chick | -0.020 |
bo | -0.020 |
Ch | -0.018 |
E | -0.018 |
him | -0.018 |
Token | accidentally |
Token ID | 14716 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
coc | +0.009 |
goals | +0.009 |
packs | +0.009 |
notebook | +0.009 |
culture | +0.009 |
Neg logit contributions | |
bo | -0.006 |
Chick | -0.006 |
him | -0.006 |
Ch | -0.006 |
B | -0.006 |
Token | hurt |
Token ID | 5938 |
Feature activation | +2.33e-02 |
Pos logit contributions | |
Chick | +0.008 |
bo | +0.008 |
Ch | +0.007 |
E | +0.007 |
him | +0.007 |
Neg logit contributions | |
coc | -0.011 |
notebook | -0.011 |
goals | -0.010 |
goal | -0.010 |
trove | -0.010 |
Token | ! |
Token ID | 0 |
Feature activation | +7.00e-01 |
Pos logit contributions | |
coc | +0.011 |
notebook | +0.010 |
goals | +0.010 |
goal | +0.009 |
trove | +0.009 |
Neg logit contributions | |
Chick | -0.012 |
bo | -0.012 |
Ch | -0.011 |
him | -0.011 |
E | -0.011 |
Token | He |
Token ID | 679 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
coc | +0.024 |
notebook | +0.023 |
goals | +0.022 |
poem | +0.022 |
trove | +0.022 |
Neg logit contributions | |
bo | -0.012 |
Chick | -0.012 |
him | -0.011 |
E | -0.011 |
Ch | -0.011 |
Token | picked |
Token ID | 6497 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
packs | +0.008 |
goals | +0.008 |
coc | +0.008 |
notebook | +0.007 |
ours | +0.007 |
Neg logit contributions | |
bo | -0.004 |
Chick | -0.004 |
B | -0.004 |
him | -0.004 |
E | -0.004 |
Token | up |
Token ID | 510 |
Feature activation | +5.42e-01 |
Pos logit contributions | |
coc | +0.020 |
notebook | +0.019 |
book | +0.018 |
goals | +0.018 |
goal | +0.018 |
Neg logit contributions | |
hey | -0.028 |
Ch | -0.027 |
Chick | -0.027 |
bo | -0.027 |
head | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
coc | +0.012 |
notebook | +0.012 |
goals | +0.011 |
book | +0.011 |
goal | +0.010 |
Neg logit contributions | |
Chick | -0.015 |
bo | -0.015 |
hey | -0.015 |
Ch | -0.015 |
E | -0.014 |
Token | l |
Token ID | 300 |
Feature activation | +4.70e+00 |
Pos logit contributions | |
coc | +0.002 |
notebook | +0.002 |
goals | +0.002 |
goal | +0.002 |
book | +0.002 |
Neg logit contributions | |
Chick | -0.003 |
bo | -0.003 |
Ch | -0.003 |
him | -0.003 |
hey | -0.003 |
Token | oll |
Token ID | 692 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
coc | +0.143 |
notebook | +0.140 |
goals | +0.133 |
goal | +0.129 |
packs | +0.128 |
Neg logit contributions | |
bo | -0.094 |
Chick | -0.093 |
E | -0.087 |
Ch | -0.086 |
him | -0.086 |
Token | ipop |
Token ID | 42800 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
coc | +0.035 |
notebook | +0.035 |
book | +0.029 |
goals | +0.028 |
stash | +0.027 |
Neg logit contributions | |
Chick | -0.085 |
bo | -0.083 |
Ch | -0.082 |
hey | -0.082 |
E | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
coc | +0.077 |
culture | +0.075 |
goals | +0.074 |
notebook | +0.071 |
languages | +0.071 |
Neg logit contributions | |
him | -0.066 |
bo | -0.063 |
Chick | -0.062 |
B | -0.058 |
head | -0.057 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
coc | +0.011 |
goals | +0.011 |
adow | +0.011 |
notebook | +0.010 |
goal | +0.010 |
Neg logit contributions | |
Chick | -0.006 |
him | -0.006 |
B | -0.005 |
bo | -0.005 |
Baby | -0.005 |
Token | that |
Token ID | 326 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
Chick | +0.005 |
bo | +0.004 |
Ch | +0.004 |
E | +0.004 |
him | +0.004 |
Neg logit contributions | |
coc | -0.005 |
notebook | -0.005 |
goals | -0.005 |
goal | -0.005 |
book | -0.005 |
Token | string |
Token ID | 4731 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
Chick | +0.002 |
bo | +0.002 |
him | +0.002 |
E | +0.002 |
Ch | +0.002 |
Neg logit contributions | |
coc | -0.002 |
notebook | -0.002 |
goals | -0.002 |
trove | -0.002 |
packs | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
Chick | +0.020 |
bo | +0.020 |
him | +0.019 |
Ch | +0.019 |
head | +0.018 |
Neg logit contributions | |
coc | -0.018 |
notebook | -0.017 |
goals | -0.016 |
goal | -0.016 |
trove | -0.016 |
Token | carefully |
Token ID | 7773 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Chick | +0.006 |
bo | +0.006 |
him | +0.006 |
Ch | +0.006 |
B | +0.005 |
Neg logit contributions | |
coc | -0.009 |
notebook | -0.009 |
goals | -0.009 |
goal | -0.008 |
trove | -0.008 |
Token | wrapped |
Token ID | 12908 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
hey | +0.039 |
bo | +0.039 |
E | +0.038 |
Chick | +0.038 |
head | +0.037 |
Neg logit contributions | |
coc | -0.039 |
notebook | -0.039 |
packs | -0.035 |
stash | -0.035 |
book | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
hey | +0.011 |
Chick | +0.011 |
bo | +0.011 |
Ch | +0.011 |
head | +0.010 |
Neg logit contributions | |
coc | -0.011 |
notebook | -0.010 |
goals | -0.010 |
skills | -0.010 |
book | -0.010 |
Token | l |
Token ID | 300 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
packs | +0.016 |
adow | +0.015 |
culture | +0.014 |
speech | +0.014 |
lair | +0.014 |
Neg logit contributions | |
E | -0.016 |
bo | -0.016 |
B | -0.015 |
B | -0.015 |
St | -0.015 |
Token | imes |
Token ID | 999 |
Feature activation | +3.45e+00 |
Pos logit contributions | |
coc | +0.097 |
notebook | +0.096 |
culture | +0.090 |
packs | +0.087 |
goals | +0.086 |
Neg logit contributions | |
bo | -0.138 |
Chick | -0.135 |
E | -0.131 |
Ch | -0.130 |
him | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | +3.85e-01 |
Pos logit contributions | |
coc | +0.102 |
notebook | +0.098 |
poem | +0.093 |
goals | +0.093 |
culture | +0.092 |
Neg logit contributions | |
bo | -0.075 |
him | -0.073 |
Chick | -0.071 |
B | -0.065 |
cl | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
coc | +0.012 |
notebook | +0.012 |
goals | +0.011 |
trove | +0.010 |
poem | +0.010 |
Neg logit contributions | |
Chick | -0.008 |
bo | -0.008 |
him | -0.007 |
Ch | -0.007 |
E | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
coc | +0.005 |
notebook | +0.005 |
goals | +0.004 |
goal | +0.004 |
book | +0.004 |
Neg logit contributions | |
Chick | -0.005 |
bo | -0.005 |
Ch | -0.004 |
hey | -0.004 |
E | -0.004 |
Token | When |
Token ID | 2215 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
Chick | +0.009 |
bo | +0.008 |
hey | +0.008 |
him | +0.008 |
head | +0.008 |
Neg logit contributions | |
coc | -0.011 |
notebook | -0.010 |
goals | -0.010 |
goal | -0.010 |
statue | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
Chick | +0.006 |
bo | +0.006 |
him | +0.006 |
head | +0.006 |
hey | +0.006 |
Neg logit contributions | |
coc | -0.006 |
notebook | -0.006 |
goals | -0.006 |
goal | -0.006 |
poem | -0.005 |
Token | pale |
Token ID | 14005 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
coc | +0.011 |
notebook | +0.011 |
adow | +0.010 |
trove | +0.010 |
packs | +0.010 |
Neg logit contributions | |
Chick | -0.014 |
bo | -0.014 |
E | -0.013 |
Ch | -0.013 |
him | -0.013 |
Token | friend |
Token ID | 1545 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
ours | +0.013 |
packs | +0.012 |
culture | +0.012 |
goals | +0.012 |
trove | +0.012 |
Neg logit contributions | |
bo | -0.013 |
Chick | -0.013 |
B | -0.013 |
E | -0.012 |
him | -0.012 |
Token | showed |
Token ID | 3751 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
coc | +0.051 |
ours | +0.049 |
goals | +0.049 |
packs | +0.047 |
trove | +0.046 |
Neg logit contributions | |
bo | -0.038 |
B | -0.034 |
him | -0.033 |
Chick | -0.033 |
Baby | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -8.35e-02 |
Pos logit contributions | |
Chick | +0.009 |
bo | +0.009 |
Ch | +0.009 |
head | +0.009 |
hey | +0.009 |
Neg logit contributions | |
coc | -0.008 |
notebook | -0.008 |
goals | -0.008 |
book | -0.007 |
skills | -0.007 |
Token | l |
Token ID | 300 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
Chick | +0.002 |
E | +0.002 |
bo | +0.002 |
B | +0.002 |
Ch | +0.002 |
Neg logit contributions | |
packs | -0.002 |
coc | -0.002 |
notebook | -0.002 |
adow | -0.002 |
goals | -0.002 |
Token | oll |
Token ID | 692 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
coc | +0.151 |
notebook | +0.149 |
packs | +0.146 |
culture | +0.144 |
goals | +0.143 |
Neg logit contributions | |
bo | -0.083 |
Chick | -0.077 |
E | -0.077 |
him | -0.072 |
Ch | -0.072 |
Token | ipop |
Token ID | 42800 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
coc | +0.037 |
notebook | +0.034 |
goals | +0.032 |
goal | +0.030 |
trove | +0.029 |
Neg logit contributions | |
Chick | -0.072 |
bo | -0.071 |
him | -0.068 |
E | -0.067 |
Ch | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
culture | +0.073 |
Statue | +0.073 |
coc | +0.070 |
tal | +0.069 |
aj | +0.069 |
Neg logit contributions | |
him | -0.032 |
them | -0.020 |
bo | -0.018 |
ly | -0.018 |
Chick | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
coc | +0.026 |
notebook | +0.026 |
pad | +0.025 |
goals | +0.025 |
adow | +0.025 |
Neg logit contributions | |
him | -0.010 |
Chick | -0.007 |
B | -0.007 |
hey | -0.007 |
them | -0.006 |
Token | friend |
Token ID | 1545 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
him | +0.007 |
Chick | +0.007 |
B | +0.006 |
bo | +0.006 |
hey | +0.006 |
Neg logit contributions | |
ours | -0.011 |
coc | -0.011 |
ocus | -0.011 |
culture | -0.011 |
hasn | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | -6.02e-02 |
Pos logit contributions | |
Chick | +0.009 |
bo | +0.008 |
him | +0.008 |
E | +0.008 |
Ch | +0.008 |
Neg logit contributions | |
coc | -0.018 |
notebook | -0.017 |
goals | -0.016 |
trove | -0.016 |
packs | -0.016 |
Token | unw |
Token ID | 7379 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
bo | +0.001 |
Chick | +0.001 |
Ch | +0.001 |
him | +0.001 |
B | +0.001 |
Neg logit contributions | |
coc | -0.002 |
notebook | -0.002 |
goals | -0.002 |
goal | -0.002 |
packs | -0.002 |
Token | ra |
Token ID | 430 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.001 |
goals | +0.001 |
packs | +0.001 |
goal | +0.001 |
Neg logit contributions | |
Chick | -0.001 |
head | -0.001 |
Baby | -0.001 |
bo | -0.001 |
hey | -0.001 |
Token | pped |
Token ID | 1496 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
Chick | +0.004 |
bo | +0.003 |
E | +0.003 |
Ch | +0.003 |
hey | +0.003 |
Neg logit contributions | |
coc | -0.011 |
notebook | -0.010 |
goals | -0.010 |
trove | -0.010 |
book | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
Chick | +0.007 |
bo | +0.007 |
Ch | +0.007 |
hey | +0.007 |
E | +0.007 |
Neg logit contributions | |
coc | -0.007 |
notebook | -0.007 |
goals | -0.006 |
book | -0.006 |
goal | -0.006 |
Token | l |
Token ID | 300 |
Feature activation | +4.65e+00 |
Pos logit contributions | |
packs | +0.005 |
languages | +0.005 |
culture | +0.005 |
adow | +0.005 |
impressed | +0.005 |
Neg logit contributions | |
E | -0.003 |
bo | -0.003 |
Chick | -0.003 |
B | -0.002 |
St | -0.002 |
Token | oll |
Token ID | 692 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
coc | +0.148 |
notebook | +0.146 |
culture | +0.141 |
goals | +0.140 |
packs | +0.139 |
Neg logit contributions | |
bo | -0.085 |
Chick | -0.081 |
E | -0.078 |
Ch | -0.078 |
him | -0.076 |
Token | ipop |
Token ID | 42800 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
coc | +0.037 |
notebook | +0.035 |
goals | +0.031 |
goal | +0.029 |
book | +0.029 |
Neg logit contributions | |
Chick | -0.075 |
bo | -0.074 |
Ch | -0.071 |
E | -0.071 |
him | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | -6.35e-02 |
Pos logit contributions | |
culture | +0.070 |
coc | +0.070 |
notebook | +0.069 |
languages | +0.065 |
packs | +0.065 |
Neg logit contributions | |
him | -0.056 |
bo | -0.055 |
Chick | -0.052 |
head | -0.049 |
B | -0.048 |
Token | l |
Token ID | 300 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
Chick | +0.001 |
bo | +0.001 |
him | +0.001 |
Ch | +0.001 |
B | +0.001 |
Neg logit contributions | |
coc | -0.002 |
goals | -0.002 |
notebook | -0.002 |
adow | -0.002 |
culture | -0.002 |
Token | icked |
Token ID | 9484 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
coc | +0.049 |
notebook | +0.046 |
goals | +0.043 |
trove | +0.040 |
stash | +0.039 |
Neg logit contributions | |
Chick | -0.073 |
bo | -0.071 |
Ch | -0.068 |
E | -0.067 |
head | -0.067 |
Token | can |
Token ID | 460 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Chick | +0.011 |
bo | +0.011 |
him | +0.010 |
E | +0.010 |
Ch | +0.010 |
Neg logit contributions | |
coc | -0.011 |
notebook | -0.011 |
goals | -0.010 |
trove | -0.010 |
goal | -0.010 |
Token | help |
Token ID | 1037 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
coc | +0.008 |
notebook | +0.008 |
goal | +0.007 |
trove | +0.007 |
book | +0.007 |
Neg logit contributions | |
Chick | -0.004 |
bo | -0.004 |
Ch | -0.004 |
E | -0.004 |
head | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
coc | +0.015 |
notebook | +0.015 |
goals | +0.014 |
packs | +0.014 |
goal | +0.014 |
Neg logit contributions | |
Chick | -0.013 |
bo | -0.012 |
him | -0.012 |
E | -0.011 |
Ch | -0.011 |
Token | find |
Token ID | 1064 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
coc | +0.022 |
notebook | +0.021 |
goals | +0.020 |
goal | +0.019 |
packs | +0.019 |
Neg logit contributions | |
Chick | -0.020 |
bo | -0.019 |
him | -0.018 |
E | -0.018 |
hey | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
notebook | +0.034 |
coc | +0.033 |
goals | +0.032 |
goal | +0.032 |
pleased | +0.031 |
Neg logit contributions | |
Chick | -0.032 |
him | -0.030 |
B | -0.029 |
bo | -0.028 |
E | -0.027 |
Token | l |
Token ID | 300 |
Feature activation | +4.64e+00 |
Pos logit contributions | |
packs | +0.006 |
notebook | +0.006 |
impressed | +0.006 |
tal | +0.006 |
pleased | +0.006 |
Neg logit contributions | |
Chick | -0.005 |
B | -0.005 |
bo | -0.005 |
E | -0.004 |
head | -0.004 |
Token | ily |
Token ID | 813 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
amaz | +0.155 |
culture | +0.146 |
mistake | +0.146 |
impressed | +0.144 |
languages | +0.140 |
Neg logit contributions | |
bo | -0.081 |
head | -0.075 |
Chick | -0.070 |
ick | -0.069 |
izz | -0.068 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
ey | +0.017 |
impressed | +0.016 |
amaz | +0.016 |
coc | +0.015 |
pleased | +0.015 |
Neg logit contributions | |
bo | -0.009 |
him | -0.008 |
B | -0.007 |
Chick | -0.007 |
ny | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
coc | +0.011 |
notebook | +0.011 |
goals | +0.010 |
packs | +0.010 |
trove | +0.010 |
Neg logit contributions | |
Chick | -0.005 |
bo | -0.005 |
him | -0.005 |
Ch | -0.005 |
B | -0.005 |
Token | turned |
Token ID | 2900 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
coc | +0.006 |
notebook | +0.006 |
goals | +0.006 |
goal | +0.006 |
ours | +0.006 |
Neg logit contributions | |
Chick | -0.004 |
bo | -0.004 |
Ch | -0.004 |
him | -0.004 |
E | -0.004 |
Token | around |
Token ID | 1088 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
coc | +0.009 |
notebook | +0.009 |
goals | +0.008 |
goal | +0.008 |
book | +0.008 |
Neg logit contributions | |
Chick | -0.009 |
bo | -0.008 |
Ch | -0.008 |
E | -0.008 |
hey | -0.008 |
Token | true |
Token ID | 2081 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
coc | +0.015 |
notebook | +0.014 |
ses | +0.014 |
sed | +0.014 |
Statue | +0.013 |
Neg logit contributions | |
him | -0.014 |
Chick | -0.013 |
bo | -0.013 |
B | -0.013 |
them | -0.012 |
Token | ! |
Token ID | 0 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
coc | +0.027 |
notebook | +0.026 |
pleased | +0.025 |
impressed | +0.025 |
ses | +0.025 |
Neg logit contributions | |
him | -0.011 |
Chick | -0.009 |
bo | -0.008 |
B | -0.008 |
head | -0.007 |
Token | She |
Token ID | 1375 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
notebook | +0.016 |
coc | +0.016 |
goals | +0.015 |
trove | +0.015 |
culture | +0.015 |
Neg logit contributions | |
B | -0.008 |
Chick | -0.008 |
E | -0.008 |
Baby | -0.008 |
bo | -0.007 |
Token | thanked |
Token ID | 26280 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
ours | +0.017 |
coc | +0.015 |
packs | +0.015 |
property | +0.014 |
ymes | +0.014 |
Neg logit contributions | |
bo | -0.007 |
Chick | -0.006 |
him | -0.006 |
B | -0.006 |
Will | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
coc | +0.006 |
notebook | +0.005 |
poem | +0.005 |
reading | +0.005 |
book | +0.005 |
Neg logit contributions | |
bo | -0.005 |
Ch | -0.005 |
head | -0.005 |
Chick | -0.005 |
hey | -0.005 |
Token | l |
Token ID | 300 |
Feature activation | +4.61e+00 |
Pos logit contributions | |
packs | +0.017 |
coc | +0.016 |
ours | +0.016 |
tal | +0.015 |
goals | +0.015 |
Neg logit contributions | |
Ch | -0.015 |
E | -0.015 |
Chick | -0.015 |
him | -0.014 |
bo | -0.014 |
Token | ibrarian |
Token ID | 35808 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
coc | +0.119 |
packs | +0.116 |
ours | +0.116 |
goal | +0.111 |
notebook | +0.111 |
Neg logit contributions | |
bo | -0.110 |
Chick | -0.107 |
ick | -0.104 |
Ch | -0.103 |
him | -0.101 |
Token | and |
Token ID | 290 |
Feature activation | -1.88e-01 |
Pos logit contributions | |
coc | +0.038 |
goals | +0.035 |
notebook | +0.035 |
ours | +0.034 |
culture | +0.034 |
Neg logit contributions | |
him | -0.033 |
Chick | -0.033 |
bo | -0.032 |
B | -0.031 |
Baby | -0.030 |
Token | ran |
Token ID | 4966 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
him | +0.003 |
Chick | +0.003 |
B | +0.003 |
Baby | +0.003 |
bo | +0.002 |
Neg logit contributions | |
goals | -0.007 |
coc | -0.007 |
territory | -0.007 |
ours | -0.007 |
culture | -0.006 |
Token | off |
Token ID | 572 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Chick | +0.030 |
bo | +0.029 |
Ch | +0.028 |
E | +0.027 |
hey | +0.027 |
Neg logit contributions | |
coc | -0.025 |
notebook | -0.024 |
goals | -0.022 |
goal | -0.022 |
book | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
him | +0.003 |
Chick | +0.003 |
B | +0.003 |
bo | +0.003 |
cl | +0.003 |
Neg logit contributions | |
goals | -0.005 |
coc | -0.005 |
notebook | -0.005 |
culture | -0.004 |
poem | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
coc | +0.034 |
goals | +0.033 |
packs | +0.032 |
territory | +0.031 |
culture | +0.031 |
Neg logit contributions | |
bo | -0.010 |
B | -0.010 |
him | -0.010 |
Chick | -0.009 |
Baby | -0.009 |
Token | can |
Token ID | 460 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
packs | +0.024 |
lair | +0.024 |
goals | +0.022 |
territory | +0.022 |
yards | +0.022 |
Neg logit contributions | |
B | -0.013 |
Baby | -0.011 |
Chick | -0.011 |
him | -0.010 |
head | -0.010 |
Token | I |
Token ID | 314 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
Chick | +0.010 |
bo | +0.010 |
him | +0.009 |
B | +0.009 |
Ch | +0.009 |
Neg logit contributions | |
coc | -0.013 |
notebook | -0.013 |
goals | -0.013 |
pad | -0.012 |
packs | -0.012 |
Token | steal |
Token ID | 8711 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
bo | +0.004 |
him | +0.004 |
care | +0.003 |
B | +0.003 |
Chick | +0.003 |
Neg logit contributions | |
coc | -0.007 |
goals | -0.007 |
notebook | -0.007 |
culture | -0.007 |
packs | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
trove | +0.062 |
adow | +0.059 |
lair | +0.059 |
packs | +0.058 |
pleased | +0.057 |
Neg logit contributions | |
him | -0.035 |
them | -0.029 |
B | -0.029 |
E | -0.027 |
Chick | -0.024 |
Token | l |
Token ID | 300 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
E | +0.005 |
B | +0.005 |
Chick | +0.005 |
Ch | +0.005 |
head | +0.005 |
Neg logit contributions | |
packs | -0.007 |
goals | -0.006 |
impressed | -0.006 |
lair | -0.006 |
adow | -0.006 |
Token | ily |
Token ID | 813 |
Feature activation | +5.79e-02 |
Pos logit contributions | |
culture | +0.149 |
packs | +0.149 |
amaz | +0.148 |
impressed | +0.145 |
mistake | +0.145 |
Neg logit contributions | |
bo | -0.079 |
head | -0.076 |
E | -0.074 |
Ch | -0.072 |
Chick | -0.071 |
Token | ? |
Token ID | 30 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
amaz | +0.002 |
impressed | +0.002 |
pleased | +0.002 |
cooperative | +0.002 |
lair | +0.002 |
Neg logit contributions | |
bo | -0.001 |
B | -0.001 |
him | -0.001 |
le | -0.001 |
ie | -0.001 |
Token | Please |
Token ID | 4222 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
Chick | +0.000 |
B | +0.000 |
E | +0.000 |
bo | +0.000 |
Ch | +0.000 |
Neg logit contributions | |
coc | -0.000 |
notebook | -0.000 |
goals | -0.000 |
stash | -0.000 |
mistake | -0.000 |
Token | ? |
Token ID | 30 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
coc | +0.013 |
goals | +0.013 |
notebook | +0.013 |
packs | +0.013 |
culture | +0.012 |
Neg logit contributions | |
bo | -0.009 |
him | -0.009 |
Chick | -0.008 |
B | -0.008 |
hey | -0.008 |
Token | รข |
Token ID | 22940 |
Feature activation | +1.63e+00 |
Pos logit contributions | |
coc | +0.009 |
notebook | +0.008 |
goals | +0.008 |
mistake | +0.008 |
stash | +0.008 |
Neg logit contributions | |
Chick | -0.006 |
B | -0.006 |
E | -0.006 |
bo | -0.006 |
Ch | -0.006 |
Token | The |
Token ID | 383 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
Chick | +0.014 |
bo | +0.013 |
him | +0.013 |
B | +0.013 |
E | +0.012 |
Neg logit contributions | |
coc | -0.026 |
notebook | -0.025 |
goals | -0.024 |
trove | -0.024 |
packs | -0.024 |
Token | dog |
Token ID | 3290 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
bo | +0.008 |
Chick | +0.008 |
Ch | +0.008 |
him | +0.008 |
E | +0.008 |
Neg logit contributions | |
coc | -0.008 |
notebook | -0.007 |
packs | -0.007 |
adow | -0.007 |
goals | -0.007 |
Token | had |
Token ID | 550 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
coc | +0.014 |
notebook | +0.013 |
goals | +0.012 |
packs | +0.012 |
goal | +0.012 |
Neg logit contributions | |
bo | -0.013 |
Chick | -0.013 |
Ch | -0.012 |
him | -0.012 |
E | -0.012 |
Token | spotted |
Token ID | 13489 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
coc | +0.030 |
notebook | +0.029 |
goals | +0.027 |
adow | +0.027 |
trove | +0.027 |
Neg logit contributions | |
bo | -0.022 |
Chick | -0.022 |
him | -0.022 |
Ch | -0.021 |
B | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
coc | +0.019 |
notebook | +0.018 |
goals | +0.017 |
book | +0.017 |
trove | +0.016 |
Neg logit contributions | |
Chick | -0.007 |
bo | -0.007 |
Ch | -0.007 |
E | -0.006 |
hey | -0.006 |
Token | l |
Token ID | 300 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
packs | +0.009 |
adow | +0.008 |
impressed | +0.008 |
alk | +0.008 |
notebook | +0.008 |
Neg logit contributions | |
bo | -0.006 |
E | -0.006 |
him | -0.006 |
Chick | -0.006 |
B | -0.006 |
Token | oll |
Token ID | 692 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
coc | +0.146 |
notebook | +0.143 |
goals | +0.137 |
culture | +0.135 |
packs | +0.135 |
Neg logit contributions | |
bo | -0.085 |
Chick | -0.081 |
Ch | -0.076 |
E | -0.076 |
him | -0.075 |
Token | ipop |
Token ID | 42800 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
coc | +0.030 |
notebook | +0.029 |
book | +0.024 |
goals | +0.023 |
stash | +0.023 |
Neg logit contributions | |
Chick | -0.077 |
bo | -0.076 |
Ch | -0.075 |
hey | -0.074 |
E | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
culture | +0.070 |
coc | +0.068 |
notebook | +0.066 |
languages | +0.065 |
pleased | +0.064 |
Neg logit contributions | |
him | -0.038 |
bo | -0.034 |
Chick | -0.032 |
head | -0.030 |
B | -0.028 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
him | +0.006 |
Chick | +0.006 |
B | +0.006 |
bo | +0.005 |
Baby | +0.005 |
Neg logit contributions | |
adow | -0.012 |
coc | -0.011 |
goals | -0.011 |
packs | -0.011 |
notebook | -0.011 |
Token | it |
Token ID | 340 |
Feature activation | -9.99e-01 |
Pos logit contributions | |
Chick | +0.004 |
bo | +0.004 |
him | +0.003 |
Ch | +0.003 |
E | +0.003 |
Neg logit contributions | |
coc | -0.003 |
notebook | -0.003 |
goals | -0.003 |
trove | -0.003 |
goal | -0.003 |
Token | : |
Token ID | 25 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
bo | +0.016 |
him | +0.015 |
B | +0.015 |
ick | +0.015 |
Baby | +0.014 |
Neg logit contributions | |
coc | -0.022 |
ours | -0.019 |
goals | -0.019 |
notebook | -0.018 |
goal | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
coc | +0.048 |
notebook | +0.043 |
stash | +0.042 |
goals | +0.041 |
web | +0.040 |
Neg logit contributions | |
B | -0.035 |
him | -0.034 |
Chick | -0.033 |
Baby | -0.032 |
Ch | -0.032 |
Token | Who |
Token ID | 8241 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
Chick | +0.018 |
bo | +0.017 |
him | +0.016 |
hey | +0.015 |
head | +0.015 |
Neg logit contributions | |
coc | -0.027 |
notebook | -0.027 |
goals | -0.025 |
goal | -0.024 |
trove | -0.024 |
Token | ordered |
Token ID | 6149 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
him | +0.039 |
bo | +0.036 |
hey | +0.031 |
head | +0.030 |
care | +0.029 |
Neg logit contributions | |
coc | -0.066 |
joy | -0.059 |
pleased | -0.058 |
ey | -0.057 |
tal | -0.057 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
coc | +0.027 |
ses | +0.027 |
goals | +0.027 |
pleased | +0.027 |
slaves | +0.027 |
Neg logit contributions | |
him | -0.017 |
B | -0.014 |
Baby | -0.013 |
them | -0.013 |
head | -0.013 |
Token | l |
Token ID | 300 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
him | +0.004 |
head | +0.004 |
B | +0.004 |
Chick | +0.004 |
hey | +0.004 |
Neg logit contributions | |
coc | -0.007 |
notebook | -0.006 |
adow | -0.006 |
goals | -0.006 |
packs | -0.006 |
Token | ily |
Token ID | 813 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
amaz | +0.154 |
mistake | +0.154 |
culture | +0.152 |
impressed | +0.148 |
rightful | +0.147 |
Neg logit contributions | |
bo | -0.078 |
head | -0.075 |
izz | -0.072 |
Ch | -0.069 |
ick | -0.067 |
Token | flower |
Token ID | 15061 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
bo | +0.002 |
him | +0.002 |
B | +0.002 |
head | +0.002 |
Chick | +0.002 |
Neg logit contributions | |
coc | -0.003 |
goals | -0.003 |
ey | -0.003 |
amaz | -0.003 |
impressed | -0.003 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
goals | +0.016 |
joy | +0.015 |
ses | +0.014 |
cooperative | +0.014 |
amaz | +0.014 |
Neg logit contributions | |
bo | -0.008 |
Chick | -0.008 |
him | -0.008 |
ie | -0.008 |
head | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
Chick | +0.006 |
bo | +0.006 |
him | +0.006 |
B | +0.006 |
E | +0.005 |
Neg logit contributions | |
coc | -0.009 |
notebook | -0.009 |
goals | -0.009 |
trove | -0.008 |
ours | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.29e-01 |
Pos logit contributions | |
coc | +0.005 |
notebook | +0.005 |
goals | +0.005 |
ours | +0.005 |
trove | +0.005 |
Neg logit contributions | |
Chick | -0.003 |
bo | -0.003 |
E | -0.003 |
Ch | -0.003 |
B | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
coc | +0.012 |
trove | +0.012 |
Statue | +0.012 |
notebook | +0.012 |
wrist | +0.011 |
Neg logit contributions | |
him | -0.009 |
Chick | -0.008 |
Baby | -0.007 |
bo | -0.007 |
B | -0.007 |
Token | new |
Token ID | 649 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
him | +0.003 |
help | +0.002 |
care | +0.002 |
Baby | +0.002 |
Chick | +0.002 |
Neg logit contributions | |
coc | -0.003 |
trove | -0.003 |
Statue | -0.003 |
packs | -0.003 |
THE | -0.003 |
Token | knowledge |
Token ID | 3725 |
Feature activation | -4.34e-01 |
Pos logit contributions | |
him | +0.007 |
care | +0.007 |
Chick | +0.007 |
help | +0.006 |
Baby | +0.006 |
Neg logit contributions | |
coc | -0.010 |
Statue | -0.009 |
goals | -0.009 |
trove | -0.009 |
THE | -0.009 |
Token | he |
Token ID | 339 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
him | +0.008 |
care | +0.006 |
Chick | +0.006 |
ick | +0.006 |
bo | +0.006 |
Neg logit contributions | |
coc | -0.015 |
Statue | -0.014 |
notebook | -0.014 |
trove | -0.013 |
slaves | -0.013 |
Token | made |
Token ID | 925 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
coc | +0.002 |
ours | +0.002 |
packs | +0.002 |
ey | +0.002 |
tal | +0.002 |
Neg logit contributions | |
him | -0.001 |
bo | -0.001 |
Chick | -0.001 |
care | -0.001 |
lon | -0.001 |
Token | gu |
Token ID | 915 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
him | +0.008 |
Chick | +0.007 |
bo | +0.006 |
Baby | +0.006 |
B | +0.006 |
Neg logit contributions | |
coc | -0.012 |
notebook | -0.011 |
goals | -0.011 |
trove | -0.011 |
Statue | -0.010 |
Token | ac |
Token ID | 330 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
coc | +0.085 |
notebook | +0.075 |
impressed | +0.073 |
poem | +0.073 |
reading | +0.073 |
Neg logit contributions | |
bo | -0.155 |
Chick | -0.143 |
ick | -0.141 |
him | -0.139 |
lon | -0.138 |
Token | am |
Token ID | 321 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
coc | +0.048 |
notebook | +0.047 |
trove | +0.044 |
backpack | +0.042 |
goal | +0.042 |
Neg logit contributions | |
bo | -0.042 |
him | -0.037 |
Chick | -0.034 |
E | -0.034 |
cl | -0.033 |
Token | ole |
Token ID | 2305 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
coc | +0.010 |
notebook | +0.009 |
Statue | +0.008 |
trove | +0.008 |
speech | +0.008 |
Neg logit contributions | |
bo | -0.007 |
him | -0.007 |
head | -0.006 |
cl | -0.006 |
Chick | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
coc | +0.035 |
notebook | +0.032 |
ey | +0.031 |
hasn | +0.031 |
Statue | +0.030 |
Neg logit contributions | |
him | -0.022 |
bo | -0.019 |
head | -0.017 |
care | -0.016 |
Chick | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
coc | +0.005 |
ours | +0.005 |
trove | +0.005 |
notebook | +0.005 |
stash | +0.005 |
Neg logit contributions | |
him | -0.002 |
Chick | -0.002 |
bo | -0.002 |
B | -0.002 |
Baby | -0.002 |
Token | He |
Token ID | 679 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
Chick | +0.010 |
bo | +0.009 |
him | +0.009 |
E | +0.009 |
Ch | +0.008 |
Neg logit contributions | |
coc | -0.020 |
notebook | -0.020 |
goals | -0.018 |
trove | -0.018 |
packs | -0.018 |
Token | wanted |
Token ID | 2227 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
bo | +0.006 |
Chick | +0.006 |
him | +0.005 |
E | +0.005 |
Ch | +0.005 |
Neg logit contributions | |
coc | -0.005 |
notebook | -0.005 |
goals | -0.005 |
packs | -0.004 |
goal | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +1.67e-01 |
Pos logit contributions | |
coc | +0.006 |
notebook | +0.006 |
goals | +0.006 |
goal | +0.005 |
trove | +0.005 |
Neg logit contributions | |
Chick | -0.007 |
bo | -0.007 |
him | -0.006 |
Ch | -0.006 |
E | -0.006 |
Token | delay |
Token ID | 5711 |
Feature activation | +9.66e-02 |
Pos logit contributions | |
coc | +0.005 |
notebook | +0.005 |
goals | +0.004 |
goal | +0.004 |
book | +0.004 |
Neg logit contributions | |
Chick | -0.004 |
bo | -0.003 |
Ch | -0.003 |
E | -0.003 |
head | -0.003 |
Token | as |
Token ID | 355 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
coc | +0.003 |
adow | +0.003 |
trove | +0.003 |
notebook | +0.003 |
Statue | +0.003 |
Neg logit contributions | |
him | -0.002 |
Chick | -0.002 |
them | -0.001 |
Baby | -0.001 |
bo | -0.001 |
Token | long |
Token ID | 890 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
Chick | +0.050 |
bo | +0.049 |
him | +0.046 |
E | +0.046 |
Ch | +0.046 |
Neg logit contributions | |
coc | -0.062 |
notebook | -0.060 |
goals | -0.056 |
goal | -0.054 |
trove | -0.054 |
Token | as |
Token ID | 355 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
Chick | +0.110 |
Ch | +0.108 |
bo | +0.107 |
E | +0.105 |
hey | +0.100 |
Neg logit contributions | |
coc | -0.112 |
notebook | -0.107 |
goals | -0.105 |
reading | -0.097 |
goal | -0.096 |
Token | he |
Token ID | 339 |
Feature activation | -7.06e-01 |
Pos logit contributions | |
Chick | +0.043 |
bo | +0.042 |
Ch | +0.039 |
him | +0.039 |
E | +0.039 |
Neg logit contributions | |
coc | -0.074 |
notebook | -0.072 |
goals | -0.068 |
goal | -0.066 |
trove | -0.065 |
Token | could |
Token ID | 714 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
bo | +0.016 |
Chick | +0.016 |
him | +0.015 |
Ch | +0.015 |
E | +0.014 |
Neg logit contributions | |
coc | -0.021 |
notebook | -0.020 |
goals | -0.019 |
goal | -0.019 |
ours | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
him | +0.017 |
bo | +0.014 |
care | +0.011 |
Baby | +0.010 |
cl | +0.010 |
Neg logit contributions | |
coc | -0.039 |
culture | -0.039 |
notebook | -0.038 |
ymes | -0.038 |
trove | -0.037 |
Token | He |
Token ID | 679 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
Chick | +0.007 |
bo | +0.007 |
Ch | +0.007 |
E | +0.006 |
him | +0.006 |
Neg logit contributions | |
coc | -0.012 |
notebook | -0.012 |
goals | -0.011 |
goal | -0.011 |
book | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
Chick | +0.013 |
bo | +0.013 |
him | +0.012 |
Ch | +0.012 |
E | +0.012 |
Neg logit contributions | |
coc | -0.012 |
notebook | -0.011 |
goals | -0.011 |
goal | -0.010 |
trove | -0.010 |
Token | she |
Token ID | 673 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Chick | +0.007 |
him | +0.006 |
Baby | +0.006 |
B | +0.006 |
hey | +0.005 |
Neg logit contributions | |
coc | -0.028 |
goals | -0.028 |
notebook | -0.026 |
goal | -0.026 |
pad | -0.026 |
Token | could |
Token ID | 714 |
Feature activation | -2.25e-03 |
Pos logit contributions | |
bo | +0.006 |
Chick | +0.006 |
B | +0.005 |
him | +0.005 |
Ch | +0.005 |
Neg logit contributions | |
coc | -0.011 |
goals | -0.010 |
notebook | -0.010 |
ey | -0.010 |
packs | -0.010 |
Token | go |
Token ID | 467 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Chick | +0.000 |
bo | +0.000 |
Ch | +0.000 |
E | +0.000 |
head | +0.000 |
Neg logit contributions | |
coc | -0.000 |
notebook | -0.000 |
goals | -0.000 |
goal | -0.000 |
book | -0.000 |
Token | as |
Token ID | 355 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
Chick | +0.006 |
bo | +0.006 |
E | +0.006 |
Ch | +0.006 |
hey | +0.005 |
Neg logit contributions | |
coc | -0.005 |
notebook | -0.005 |
goals | -0.005 |
goal | -0.005 |
book | -0.005 |
Token | long |
Token ID | 890 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
Chick | +0.027 |
bo | +0.027 |
Ch | +0.025 |
E | +0.025 |
him | +0.025 |
Neg logit contributions | |
coc | -0.031 |
notebook | -0.030 |
goals | -0.029 |
goal | -0.027 |
book | -0.027 |
Token | as |
Token ID | 355 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
bo | +0.128 |
E | +0.127 |
Chick | +0.123 |
Ch | +0.120 |
hey | +0.120 |
Neg logit contributions | |
coc | -0.092 |
notebook | -0.083 |
reading | -0.082 |
packs | -0.081 |
goals | -0.080 |
Token | she |
Token ID | 673 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
Chick | +0.032 |
bo | +0.030 |
him | +0.028 |
Ch | +0.028 |
E | +0.028 |
Neg logit contributions | |
coc | -0.059 |
notebook | -0.057 |
goals | -0.054 |
goal | -0.053 |
trove | -0.053 |
Token | promised |
Token ID | 8072 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
bo | +0.012 |
Ch | +0.011 |
Chick | +0.011 |
B | +0.011 |
him | +0.010 |
Neg logit contributions | |
coc | -0.017 |
notebook | -0.016 |
ours | -0.016 |
goals | -0.015 |
culture | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
Chick | +0.022 |
bo | +0.022 |
Ch | +0.020 |
E | +0.020 |
him | +0.020 |
Neg logit contributions | |
coc | -0.025 |
notebook | -0.024 |
goals | -0.022 |
goal | -0.021 |
book | -0.021 |
Token | look |
Token ID | 804 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
Chick | +0.004 |
bo | +0.004 |
Ch | +0.004 |
E | +0.004 |
head | +0.003 |
Neg logit contributions | |
coc | -0.005 |
notebook | -0.005 |
goal | -0.004 |
goals | -0.004 |
book | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
coc | +0.028 |
notebook | +0.027 |
goals | +0.027 |
packs | +0.026 |
goal | +0.025 |
Neg logit contributions | |
him | -0.023 |
Chick | -0.021 |
bo | -0.020 |
B | -0.020 |
Baby | -0.020 |
Token | let |
Token ID | 1309 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
coc | +0.004 |
notebook | +0.004 |
goals | +0.004 |
goal | +0.004 |
packs | +0.004 |
Neg logit contributions | |
Chick | -0.002 |
bo | -0.002 |
him | -0.002 |
Ch | -0.002 |
E | -0.002 |
Token | him |
Token ID | 683 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
Ch | +0.003 |
E | +0.003 |
Chick | +0.003 |
bo | +0.003 |
hey | +0.002 |
Neg logit contributions | |
coc | -0.010 |
notebook | -0.010 |
book | -0.010 |
goal | -0.010 |
goals | -0.010 |
Token | go |
Token ID | 467 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
him | +0.022 |
bo | +0.022 |
Chick | +0.021 |
B | +0.019 |
Baby | +0.017 |
Neg logit contributions | |
coc | -0.051 |
notebook | -0.049 |
goals | -0.048 |
culture | -0.046 |
trove | -0.046 |
Token | as |
Token ID | 355 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
Chick | +0.005 |
bo | +0.005 |
him | +0.005 |
B | +0.005 |
head | +0.005 |
Neg logit contributions | |
coc | -0.007 |
notebook | -0.007 |
goals | -0.006 |
poem | -0.006 |
goal | -0.006 |
Token | long |
Token ID | 890 |
Feature activation | -4.21e+00 |
Pos logit contributions | |
Chick | +0.024 |
him | +0.023 |
bo | +0.022 |
E | +0.022 |
B | +0.022 |
Neg logit contributions | |
coc | -0.034 |
notebook | -0.034 |
goals | -0.031 |
trove | -0.031 |
goal | -0.030 |
Token | as |
Token ID | 355 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
E | +0.119 |
bo | +0.119 |
Chick | +0.117 |
Ch | +0.116 |
hey | +0.112 |
Neg logit contributions | |
coc | -0.095 |
notebook | -0.087 |
goals | -0.085 |
reading | -0.083 |
packs | -0.081 |
Token | he |
Token ID | 339 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
Chick | +0.029 |
bo | +0.027 |
him | +0.026 |
Ch | +0.025 |
E | +0.025 |
Neg logit contributions | |
coc | -0.061 |
notebook | -0.060 |
goals | -0.057 |
goal | -0.056 |
trove | -0.055 |
Token | promised |
Token ID | 8072 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
bo | +0.015 |
Chick | +0.013 |
Ch | +0.013 |
him | +0.013 |
B | +0.013 |
Neg logit contributions | |
coc | -0.025 |
ours | -0.024 |
notebook | -0.024 |
goals | -0.023 |
culture | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
him | +0.021 |
Chick | +0.020 |
bo | +0.019 |
B | +0.018 |
hey | +0.018 |
Neg logit contributions | |
coc | -0.026 |
notebook | -0.025 |
goals | -0.024 |
goal | -0.023 |
trove | -0.023 |
Token | be |
Token ID | 307 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
Chick | +0.004 |
bo | +0.004 |
him | +0.004 |
hey | +0.004 |
Ch | +0.004 |
Neg logit contributions | |
coc | -0.008 |
notebook | -0.008 |
goals | -0.007 |
packs | -0.007 |
goal | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
Chick | +0.029 |
him | +0.027 |
bo | +0.027 |
B | +0.026 |
Baby | +0.026 |
Neg logit contributions | |
coc | -0.042 |
trove | -0.040 |
goals | -0.040 |
notebook | -0.038 |
Statue | -0.037 |
Token | stay |
Token ID | 2652 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
Chick | +0.013 |
bo | +0.013 |
Ch | +0.012 |
him | +0.012 |
E | +0.012 |
Neg logit contributions | |
coc | -0.025 |
notebook | -0.024 |
goals | -0.023 |
goal | -0.022 |
trove | -0.022 |
Token | outside |
Token ID | 2354 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
coc | +0.000 |
notebook | +0.000 |
goals | +0.000 |
goal | +0.000 |
Statue | +0.000 |
Neg logit contributions | |
Chick | -0.000 |
bo | -0.000 |
him | -0.000 |
B | -0.000 |
Baby | -0.000 |
Token | for |
Token ID | 329 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
coc | +0.016 |
notebook | +0.016 |
Statue | +0.015 |
culture | +0.015 |
goals | +0.015 |
Neg logit contributions | |
Chick | -0.009 |
him | -0.008 |
B | -0.008 |
Baby | -0.007 |
ick | -0.007 |
Token | as |
Token ID | 355 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
coc | +0.008 |
notebook | +0.007 |
goals | +0.007 |
book | +0.006 |
goal | +0.006 |
Neg logit contributions | |
bo | -0.008 |
Chick | -0.008 |
Ch | -0.007 |
E | -0.007 |
head | -0.007 |
Token | long |
Token ID | 890 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
Chick | +0.041 |
B | +0.037 |
him | +0.037 |
E | +0.036 |
Baby | +0.035 |
Neg logit contributions | |
coc | -0.062 |
notebook | -0.061 |
goals | -0.059 |
goal | -0.058 |
trove | -0.058 |
Token | as |
Token ID | 355 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
bo | +0.118 |
E | +0.116 |
hey | +0.111 |
Chick | +0.111 |
Ch | +0.110 |
Neg logit contributions | |
coc | -0.097 |
notebook | -0.086 |
goals | -0.084 |
reading | -0.082 |
packs | -0.082 |
Token | she |
Token ID | 673 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
Chick | +0.040 |
him | +0.036 |
bo | +0.035 |
B | +0.035 |
Ch | +0.034 |
Neg logit contributions | |
coc | -0.073 |
notebook | -0.072 |
goals | -0.070 |
goal | -0.068 |
trove | -0.067 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
bo | +0.011 |
Chick | +0.011 |
Ch | +0.010 |
him | +0.010 |
B | +0.010 |
Neg logit contributions | |
coc | -0.016 |
notebook | -0.015 |
ours | -0.015 |
goals | -0.015 |
impressed | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.96e-02 |
Pos logit contributions | |
Chick | +0.004 |
him | +0.004 |
bo | +0.004 |
B | +0.004 |
Baby | +0.004 |
Neg logit contributions | |
coc | -0.006 |
notebook | -0.006 |
goals | -0.006 |
goal | -0.006 |
trove | -0.005 |
Token | as |
Token ID | 355 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
notebook | +0.001 |
Statue | +0.001 |
packs | +0.001 |
goals | +0.001 |
coc | +0.001 |
Neg logit contributions | |
B | -0.000 |
Chick | -0.000 |
him | -0.000 |
Baby | -0.000 |
head | -0.000 |
Token | said |
Token ID | 531 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
bo | +0.023 |
him | +0.022 |
Chick | +0.021 |
B | +0.019 |
hey | +0.019 |
Neg logit contributions | |
coc | -0.033 |
goals | -0.030 |
notebook | -0.030 |
trove | -0.029 |
goal | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
coc | +0.013 |
goals | +0.011 |
notebook | +0.011 |
trove | +0.011 |
stash | +0.011 |
Neg logit contributions | |
him | -0.007 |
Chick | -0.006 |
B | -0.006 |
bo | -0.006 |
Baby | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
coc | +0.039 |
ey | +0.036 |
trove | +0.035 |
tal | +0.034 |
notebook | +0.034 |
Neg logit contributions | |
bo | -0.014 |
him | -0.013 |
Chick | -0.010 |
B | -0.010 |
cl | -0.010 |
Token | okay |
Token ID | 8788 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
him | +0.005 |
Chick | +0.004 |
B | +0.004 |
Baby | +0.004 |
bo | +0.004 |
Neg logit contributions | |
Statue | -0.008 |
trove | -0.008 |
coc | -0.008 |
wrist | -0.007 |
statue | -0.007 |
Token | as |
Token ID | 355 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
coc | +0.005 |
notebook | +0.005 |
goals | +0.004 |
book | +0.004 |
poem | +0.004 |
Neg logit contributions | |
bo | -0.005 |
Chick | -0.005 |
Ch | -0.005 |
E | -0.005 |
hey | -0.005 |
Token | long |
Token ID | 890 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
Chick | +0.025 |
him | +0.024 |
B | +0.023 |
Baby | +0.022 |
Teddy | +0.020 |
Neg logit contributions | |
coc | -0.041 |
notebook | -0.040 |
trove | -0.040 |
stash | -0.039 |
goals | -0.039 |
Token | as |
Token ID | 355 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Chick | +0.075 |
bo | +0.071 |
him | +0.071 |
head | +0.066 |
B | +0.065 |
Neg logit contributions | |
coc | -0.138 |
notebook | -0.136 |
goals | -0.127 |
goal | -0.125 |
trove | -0.124 |
Token | he |
Token ID | 339 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
Chick | +0.038 |
him | +0.036 |
B | +0.033 |
Baby | +0.031 |
bo | +0.031 |
Neg logit contributions | |
coc | -0.064 |
notebook | -0.062 |
goals | -0.059 |
adow | -0.059 |
goal | -0.059 |
Token | stayed |
Token ID | 9658 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
bo | +0.015 |
him | +0.013 |
Chick | +0.013 |
B | +0.013 |
Ch | +0.012 |
Neg logit contributions | |
ours | -0.023 |
coc | -0.023 |
notebook | -0.023 |
packs | -0.022 |
culture | -0.022 |
Token | under |
Token ID | 739 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
bo | +0.007 |
Chick | +0.007 |
him | +0.007 |
B | +0.006 |
numb | +0.005 |
Neg logit contributions | |
coc | -0.011 |
notebook | -0.010 |
Statue | -0.010 |
poem | -0.010 |
dictionary | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
coc | +0.006 |
adow | +0.006 |
notebook | +0.006 |
trove | +0.006 |
pleased | +0.006 |
Neg logit contributions | |
him | -0.004 |
Chick | -0.003 |
B | -0.003 |
Baby | -0.003 |
bo | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
bo | +0.022 |
Chick | +0.022 |
him | +0.021 |
Baby | +0.020 |
Ch | +0.020 |
Neg logit contributions | |
coc | -0.027 |
goals | -0.026 |
notebook | -0.024 |
packs | -0.024 |
goal | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
coc | +0.009 |
notebook | +0.008 |
goals | +0.008 |
goal | +0.008 |
packs | +0.008 |
Neg logit contributions | |
Chick | -0.007 |
bo | -0.007 |
him | -0.006 |
E | -0.006 |
Ch | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
coc | +0.018 |
notebook | +0.016 |
goals | +0.016 |
packs | +0.016 |
ours | +0.015 |
Neg logit contributions | |
Chick | -0.011 |
bo | -0.011 |
him | -0.011 |
B | -0.010 |
Baby | -0.010 |
Token | ok |
Token ID | 12876 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
him | +0.011 |
Chick | +0.010 |
Baby | +0.010 |
B | +0.009 |
bo | +0.009 |
Neg logit contributions | |
Statue | -0.017 |
coc | -0.017 |
notebook | -0.016 |
wrist | -0.016 |
statue | -0.016 |
Token | as |
Token ID | 355 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Chick | +0.006 |
bo | +0.006 |
him | +0.006 |
head | +0.005 |
B | +0.005 |
Neg logit contributions | |
coc | -0.006 |
notebook | -0.006 |
goals | -0.006 |
goal | -0.006 |
trove | -0.005 |
Token | long |
Token ID | 890 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
him | +0.033 |
Chick | +0.032 |
Baby | +0.031 |
B | +0.030 |
Ethan | +0.027 |
Neg logit contributions | |
coc | -0.050 |
notebook | -0.048 |
goal | -0.047 |
web | -0.047 |
goals | -0.047 |
Token | as |
Token ID | 355 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
Chick | +0.091 |
bo | +0.090 |
Ch | +0.086 |
E | +0.084 |
hey | +0.081 |
Neg logit contributions | |
coc | -0.116 |
notebook | -0.113 |
goals | -0.107 |
goal | -0.102 |
book | -0.102 |
Token | he |
Token ID | 339 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
him | +0.034 |
Chick | +0.033 |
Baby | +0.031 |
B | +0.030 |
head | +0.028 |
Neg logit contributions | |
coc | -0.073 |
notebook | -0.071 |
goals | -0.067 |
goal | -0.066 |
trove | -0.065 |
Token | trusted |
Token ID | 13467 |
Feature activation | -4.16e-01 |
Pos logit contributions | |
bo | +0.013 |
him | +0.012 |
Chick | +0.012 |
B | +0.011 |
E | +0.011 |
Neg logit contributions | |
coc | -0.019 |
ours | -0.018 |
notebook | -0.018 |
packs | -0.018 |
goals | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | -3.65e-01 |
Pos logit contributions | |
him | +0.008 |
Chick | +0.007 |
bo | +0.007 |
Baby | +0.007 |
B | +0.006 |
Neg logit contributions | |
coc | -0.014 |
notebook | -0.014 |
goals | -0.013 |
goal | -0.013 |
trove | -0.013 |
Token | vegetable |
Token ID | 20236 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
him | +0.009 |
Baby | +0.009 |
E | +0.008 |
bo | +0.008 |
head | +0.008 |
Neg logit contributions | |
coc | -0.010 |
packs | -0.009 |
notebook | -0.009 |
adow | -0.008 |
trove | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
coc | +0.007 |
goals | +0.007 |
goal | +0.006 |
notebook | +0.006 |
culture | +0.006 |
Neg logit contributions | |
bo | -0.006 |
Chick | -0.005 |
him | -0.005 |
Baby | -0.005 |
Ch | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
coc | +0.003 |
notebook | +0.003 |
goals | +0.003 |
goal | +0.003 |
trove | +0.003 |
Neg logit contributions | |
Chick | -0.003 |
bo | -0.003 |
Ch | -0.003 |
E | -0.003 |
him | -0.003 |
Token | was |
Token ID | 373 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
coc | +0.011 |
notebook | +0.010 |
goals | +0.010 |
packs | +0.010 |
ours | +0.010 |
Neg logit contributions | |
Chick | -0.006 |
bo | -0.006 |
him | -0.006 |
B | -0.005 |
Ch | -0.005 |
Token | okay |
Token ID | 8788 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
him | +0.010 |
Chick | +0.010 |
Baby | +0.009 |
B | +0.009 |
bo | +0.009 |
Neg logit contributions | |
coc | -0.016 |
Statue | -0.016 |
notebook | -0.015 |
statue | -0.015 |
packs | -0.015 |
Token | as |
Token ID | 355 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
Chick | +0.007 |
bo | +0.007 |
him | +0.007 |
Ch | +0.006 |
E | +0.006 |
Neg logit contributions | |
coc | -0.008 |
notebook | -0.007 |
goals | -0.007 |
goal | -0.007 |
trove | -0.007 |
Token | long |
Token ID | 890 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
him | +0.030 |
Chick | +0.030 |
Baby | +0.028 |
B | +0.028 |
head | +0.025 |
Neg logit contributions | |
coc | -0.044 |
notebook | -0.042 |
goals | -0.042 |
pad | -0.042 |
trove | -0.041 |
Token | as |
Token ID | 355 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
bo | +0.100 |
Chick | +0.098 |
Ch | +0.095 |
E | +0.095 |
hey | +0.090 |
Neg logit contributions | |
coc | -0.107 |
notebook | -0.103 |
goals | -0.098 |
reading | -0.093 |
book | -0.093 |
Token | he |
Token ID | 339 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
him | +0.036 |
Chick | +0.036 |
B | +0.032 |
Baby | +0.031 |
head | +0.030 |
Neg logit contributions | |
coc | -0.065 |
notebook | -0.062 |
goals | -0.060 |
goal | -0.059 |
trove | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
bo | +0.018 |
Chick | +0.017 |
him | +0.016 |
Ch | +0.015 |
E | +0.015 |
Neg logit contributions | |
coc | -0.025 |
ours | -0.024 |
notebook | -0.023 |
packs | -0.023 |
culture | -0.023 |
Token | careful |
Token ID | 8161 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
him | +0.027 |
Chick | +0.025 |
Baby | +0.025 |
bo | +0.023 |
B | +0.022 |
Neg logit contributions | |
Statue | -0.044 |
coc | -0.043 |
languages | -0.041 |
notebook | -0.041 |
goal | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
Chick | +0.009 |
bo | +0.009 |
him | +0.009 |
head | +0.008 |
Baby | +0.008 |
Neg logit contributions | |
coc | -0.012 |
notebook | -0.012 |
goals | -0.011 |
trove | -0.011 |
goal | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.001 |
ours | +0.001 |
goals | +0.001 |
ey | +0.001 |
Neg logit contributions | |
him | -0.000 |
bo | -0.000 |
Chick | -0.000 |
B | -0.000 |
cl | -0.000 |
Token | watched |
Token ID | 7342 |
Feature activation | -6.94e-01 |
Pos logit contributions | |
him | +0.004 |
Baby | +0.004 |
B | +0.004 |
Chick | +0.004 |
bo | +0.004 |
Neg logit contributions | |
goals | -0.007 |
coc | -0.007 |
notebook | -0.007 |
goal | -0.007 |
trove | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
Chick | +0.015 |
bo | +0.015 |
him | +0.014 |
Ch | +0.014 |
E | +0.014 |
Neg logit contributions | |
coc | -0.020 |
notebook | -0.019 |
goals | -0.018 |
goal | -0.018 |
trove | -0.017 |
Token | for |
Token ID | 329 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
him | +0.017 |
bo | +0.015 |
Chick | +0.015 |
cl | +0.014 |
B | +0.013 |
Neg logit contributions | |
notebook | -0.033 |
coc | -0.033 |
dictionary | -0.030 |
ocket | -0.030 |
culture | -0.030 |
Token | as |
Token ID | 355 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
notebook | +0.005 |
coc | +0.005 |
goals | +0.004 |
packs | +0.004 |
adow | +0.004 |
Neg logit contributions | |
Chick | -0.004 |
him | -0.004 |
bo | -0.003 |
hey | -0.003 |
Ch | -0.003 |
Token | long |
Token ID | 890 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
Chick | +0.039 |
him | +0.039 |
B | +0.036 |
Baby | +0.034 |
head | +0.033 |
Neg logit contributions | |
coc | -0.080 |
notebook | -0.078 |
pad | -0.075 |
goals | -0.074 |
stash | -0.074 |
Token | as |
Token ID | 355 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
bo | +0.113 |
E | +0.112 |
Chick | +0.112 |
Ch | +0.110 |
hey | +0.106 |
Neg logit contributions | |
coc | -0.095 |
notebook | -0.088 |
goals | -0.086 |
packs | -0.082 |
reading | -0.081 |
Token | they |
Token ID | 484 |
Feature activation | -3.15e-01 |
Pos logit contributions | |
Chick | +0.039 |
bo | +0.036 |
him | +0.035 |
Ch | +0.033 |
E | +0.033 |
Neg logit contributions | |
coc | -0.078 |
notebook | -0.076 |
goals | -0.073 |
goal | -0.071 |
trove | -0.070 |
Token | could |
Token ID | 714 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
bo | +0.006 |
him | +0.006 |
Chick | +0.005 |
Ch | +0.005 |
B | +0.005 |
Neg logit contributions | |
coc | -0.010 |
notebook | -0.010 |
poem | -0.010 |
goals | -0.010 |
dictionary | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +5.24e-02 |
Pos logit contributions | |
bo | +0.021 |
him | +0.021 |
Chick | +0.020 |
B | +0.019 |
cl | +0.018 |
Neg logit contributions | |
coc | -0.033 |
notebook | -0.032 |
goals | -0.030 |
poem | -0.030 |
dictionary | -0.029 |
Token | They |
Token ID | 1119 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
coc | +0.002 |
notebook | +0.002 |
trove | +0.002 |
book | +0.002 |
stash | +0.002 |
Neg logit contributions | |
Chick | -0.001 |
Baby | -0.001 |
him | -0.001 |
bo | -0.001 |
E | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | +6.67e-01 |
Pos logit contributions | |
coc | +0.021 |
notebook | +0.020 |
goals | +0.019 |
goal | +0.018 |
trove | +0.018 |
Neg logit contributions | |
Chick | -0.027 |
bo | -0.026 |
Ch | -0.025 |
him | -0.025 |
E | -0.025 |
Token | it |
Token ID | 340 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
coc | +0.016 |
notebook | +0.016 |
goals | +0.015 |
goal | +0.014 |
book | +0.014 |
Neg logit contributions | |
Chick | -0.018 |
bo | -0.017 |
Ch | -0.016 |
E | -0.016 |
him | -0.016 |
Token | was |
Token ID | 373 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
coc | +0.022 |
notebook | +0.021 |
goals | +0.020 |
ours | +0.019 |
packs | +0.019 |
Neg logit contributions | |
Chick | -0.017 |
bo | -0.016 |
Ch | -0.016 |
him | -0.015 |
B | -0.015 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.56e-03 |
Pos logit contributions | |
Chick | +0.003 |
B | +0.003 |
him | +0.003 |
Baby | +0.003 |
bo | +0.003 |
Neg logit contributions | |
coc | -0.005 |
Statue | -0.005 |
notebook | -0.005 |
statue | -0.005 |
goal | -0.005 |
Token | as |
Token ID | 355 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
coc | +0.000 |
notebook | +0.000 |
goals | +0.000 |
goal | +0.000 |
trove | +0.000 |
Neg logit contributions | |
Chick | -0.000 |
bo | -0.000 |
him | -0.000 |
Ch | -0.000 |
B | -0.000 |
Token | long |
Token ID | 890 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
Chick | +0.034 |
B | +0.033 |
him | +0.030 |
Baby | +0.028 |
head | +0.028 |
Neg logit contributions | |
trove | -0.043 |
stash | -0.043 |
coc | -0.043 |
notebook | -0.043 |
goal | -0.042 |
Token | as |
Token ID | 355 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
bo | +0.102 |
Chick | +0.098 |
Ch | +0.095 |
E | +0.095 |
hey | +0.089 |
Neg logit contributions | |
coc | -0.108 |
notebook | -0.102 |
goals | -0.097 |
reading | -0.092 |
book | -0.091 |
Token | they |
Token ID | 484 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
Chick | +0.040 |
B | +0.036 |
him | +0.036 |
Baby | +0.033 |
head | +0.032 |
Neg logit contributions | |
coc | -0.065 |
notebook | -0.064 |
trove | -0.062 |
adow | -0.062 |
stash | -0.062 |
Token | didn |
Token ID | 1422 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
bo | +0.006 |
Chick | +0.006 |
Ch | +0.006 |
B | +0.006 |
him | +0.006 |
Neg logit contributions | |
coc | -0.009 |
notebook | -0.009 |
trove | -0.009 |
ours | -0.009 |
goals | -0.009 |
Token | 't |
Token ID | 470 |
Feature activation | -7.34e-02 |
Pos logit contributions | |
Chick | +0.008 |
bo | +0.007 |
Ch | +0.007 |
hey | +0.007 |
E | +0.007 |
Neg logit contributions | |
coc | -0.019 |
notebook | -0.018 |
goals | -0.017 |
goal | -0.017 |
book | -0.017 |
Token | make |
Token ID | 787 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
Chick | +0.002 |
bo | +0.002 |
him | +0.001 |
hey | +0.001 |
B | +0.001 |
Neg logit contributions | |
coc | -0.002 |
notebook | -0.002 |
goals | -0.002 |
trove | -0.002 |
goal | -0.002 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.73e-02 |
Pos logit contributions | |
bo | +0.008 |
him | +0.007 |
Chick | +0.007 |
B | +0.006 |
only | +0.006 |
Neg logit contributions | |
coc | -0.014 |
notebook | -0.014 |
trove | -0.013 |
tal | -0.013 |
Statue | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
coc | +0.001 |
trove | +0.001 |
goals | +0.001 |
tal | +0.001 |
Statue | +0.001 |
Neg logit contributions | |
him | -0.000 |
Chick | -0.000 |
bo | -0.000 |
B | -0.000 |
head | -0.000 |
Token | make |
Token ID | 787 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
coc | +0.010 |
notebook | +0.009 |
goals | +0.009 |
goal | +0.009 |
trove | +0.008 |
Neg logit contributions | |
Chick | -0.009 |
bo | -0.009 |
Ch | -0.009 |
E | -0.009 |
head | -0.008 |
Token | mistakes |
Token ID | 10135 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
notebook | +0.009 |
coc | +0.009 |
trove | +0.009 |
packs | +0.008 |
stash | +0.008 |
Neg logit contributions | |
Chick | -0.009 |
him | -0.009 |
bo | -0.009 |
E | -0.009 |
B | -0.008 |
Token | as |
Token ID | 355 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
coc | +0.020 |
notebook | +0.019 |
tal | +0.018 |
net | +0.018 |
ocket | +0.017 |
Neg logit contributions | |
him | -0.009 |
Chick | -0.007 |
bo | -0.007 |
head | -0.007 |
B | -0.007 |
Token | long |
Token ID | 890 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
Chick | +0.065 |
him | +0.063 |
B | +0.062 |
E | +0.059 |
B | +0.057 |
Neg logit contributions | |
notebook | -0.055 |
coc | -0.053 |
trove | -0.051 |
stash | -0.050 |
adow | -0.050 |
Token | as |
Token ID | 355 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
Chick | +0.069 |
him | +0.067 |
bo | +0.064 |
B | +0.061 |
head | +0.060 |
Neg logit contributions | |
coc | -0.138 |
notebook | -0.137 |
trove | -0.124 |
adow | -0.124 |
stash | -0.124 |
Token | you |
Token ID | 345 |
Feature activation | -2.73e-02 |
Pos logit contributions | |
Chick | +0.058 |
him | +0.056 |
B | +0.054 |
bo | +0.053 |
E | +0.051 |
Neg logit contributions | |
coc | -0.065 |
notebook | -0.065 |
trove | -0.059 |
adow | -0.059 |
stash | -0.058 |
Token | learn |
Token ID | 2193 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
him | +0.000 |
bo | +0.000 |
care | +0.000 |
B | +0.000 |
Chick | +0.000 |
Neg logit contributions | |
coc | -0.001 |
notebook | -0.001 |
trove | -0.001 |
pleased | -0.001 |
tal | -0.001 |
Token | from |
Token ID | 422 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
him | +0.008 |
them | +0.007 |
B | +0.005 |
care | +0.004 |
when | +0.004 |
Neg logit contributions | |
sed | -0.024 |
ses | -0.023 |
trove | -0.023 |
ocket | -0.023 |
notebook | -0.023 |
Token | them |
Token ID | 606 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
coc | +0.017 |
notebook | +0.017 |
trove | +0.016 |
adow | +0.016 |
stash | +0.016 |
Neg logit contributions | |
him | -0.012 |
Chick | -0.010 |
them | -0.009 |
hey | -0.009 |
B | -0.009 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
Chick | +0.017 |
bo | +0.016 |
Ch | +0.016 |
head | +0.016 |
E | +0.016 |
Neg logit contributions | |
coc | -0.010 |
notebook | -0.009 |
goals | -0.009 |
goal | -0.008 |
book | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +5.92e-02 |
Pos logit contributions | |
coc | +0.005 |
notebook | +0.004 |
goals | +0.004 |
trove | +0.004 |
goal | +0.004 |
Neg logit contributions | |
Chick | -0.005 |
bo | -0.004 |
him | -0.004 |
Ch | -0.004 |
B | -0.004 |
Token | make |
Token ID | 787 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
coc | +0.001 |
mistake | +0.001 |
promise | +0.001 |
goal | +0.001 |
notebook | +0.001 |
Neg logit contributions | |
head | -0.002 |
Ch | -0.002 |
bo | -0.002 |
Chick | -0.002 |
E | -0.002 |
Token | mistakes |
Token ID | 10135 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
coc | +0.007 |
notebook | +0.007 |
goals | +0.006 |
goal | +0.006 |
book | +0.005 |
Neg logit contributions | |
Chick | -0.018 |
bo | -0.018 |
Ch | -0.018 |
E | -0.017 |
him | -0.017 |
Token | as |
Token ID | 355 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
coc | +0.018 |
notebook | +0.017 |
tal | +0.016 |
Statue | +0.016 |
trove | +0.015 |
Neg logit contributions | |
him | -0.013 |
Chick | -0.013 |
bo | -0.012 |
head | -0.012 |
Ch | -0.012 |
Token | long |
Token ID | 890 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
Chick | +0.058 |
him | +0.053 |
E | +0.052 |
B | +0.052 |
bo | +0.052 |
Neg logit contributions | |
notebook | -0.048 |
coc | -0.048 |
trove | -0.044 |
goals | -0.043 |
goal | -0.043 |
Token | as |
Token ID | 355 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Chick | +0.077 |
bo | +0.072 |
him | +0.070 |
Ch | +0.067 |
head | +0.067 |
Neg logit contributions | |
coc | -0.129 |
notebook | -0.127 |
goals | -0.117 |
trove | -0.116 |
goal | -0.116 |
Token | you |
Token ID | 345 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
Chick | +0.053 |
him | +0.050 |
B | +0.048 |
hey | +0.046 |
Baby | +0.046 |
Neg logit contributions | |
coc | -0.054 |
notebook | -0.054 |
trove | -0.051 |
goal | -0.050 |
adow | -0.050 |
Token | try |
Token ID | 1949 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
coc | +0.004 |
notebook | +0.004 |
trove | +0.004 |
book | +0.004 |
tal | +0.004 |
Neg logit contributions | |
bo | -0.002 |
him | -0.002 |
Chick | -0.002 |
B | -0.002 |
care | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -3.22e-01 |
Pos logit contributions | |
him | +0.002 |
them | +0.002 |
Chick | +0.002 |
B | +0.002 |
Teddy | +0.002 |
Neg logit contributions | |
Statue | -0.004 |
trove | -0.004 |
ocket | -0.004 |
sed | -0.004 |
ses | -0.004 |
Token | fix |
Token ID | 4259 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
Chick | +0.008 |
bo | +0.007 |
Ch | +0.007 |
E | +0.007 |
head | +0.007 |
Neg logit contributions | |
coc | -0.009 |
notebook | -0.009 |
goals | -0.008 |
goal | -0.008 |
book | -0.008 |
Token | okay |
Token ID | 8788 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
Chick | +0.018 |
bo | +0.017 |
him | +0.016 |
E | +0.016 |
B | +0.016 |
Neg logit contributions | |
coc | -0.014 |
notebook | -0.014 |
trove | -0.012 |
goals | -0.012 |
goal | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +9.19e-02 |
Pos logit contributions | |
coc | +0.002 |
notebook | +0.002 |
goals | +0.001 |
trove | +0.001 |
goal | +0.001 |
Neg logit contributions | |
Chick | -0.001 |
bo | -0.001 |
him | -0.001 |
B | -0.001 |
hey | -0.001 |
Token | make |
Token ID | 787 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
coc | +0.002 |
mistake | +0.002 |
promise | +0.002 |
notebook | +0.002 |
goal | +0.002 |
Neg logit contributions | |
head | -0.002 |
Ch | -0.002 |
bo | -0.002 |
E | -0.002 |
lon | -0.002 |
Token | mistakes |
Token ID | 10135 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
coc | +0.007 |
notebook | +0.007 |
goals | +0.006 |
trove | +0.006 |
goal | +0.006 |
Neg logit contributions | |
Chick | -0.010 |
bo | -0.010 |
him | -0.010 |
E | -0.010 |
Ch | -0.010 |
Token | as |
Token ID | 355 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
coc | +0.025 |
notebook | +0.025 |
tal | +0.024 |
ocket | +0.023 |
stash | +0.023 |
Neg logit contributions | |
him | -0.014 |
Chick | -0.013 |
head | -0.012 |
bo | -0.012 |
B | -0.012 |
Token | long |
Token ID | 890 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
Chick | +0.056 |
B | +0.051 |
Baby | +0.049 |
him | +0.048 |
E | +0.047 |
Neg logit contributions | |
notebook | -0.061 |
trove | -0.059 |
pad | -0.059 |
adow | -0.058 |
Statue | -0.057 |
Token | as |
Token ID | 355 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Chick | +0.067 |
him | +0.062 |
head | +0.058 |
B | +0.057 |
bo | +0.057 |
Neg logit contributions | |
notebook | -0.143 |
coc | -0.142 |
trove | -0.133 |
adow | -0.130 |
goal | -0.130 |
Token | we |
Token ID | 356 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
Chick | +0.052 |
B | +0.047 |
Baby | +0.046 |
him | +0.045 |
head | +0.042 |
Neg logit contributions | |
notebook | -0.070 |
trove | -0.069 |
pad | -0.069 |
adow | -0.068 |
Statue | -0.068 |
Token | learn |
Token ID | 2193 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.001 |
trove | +0.001 |
goals | +0.001 |
Statue | +0.001 |
Neg logit contributions | |
bo | -0.001 |
Chick | -0.001 |
him | -0.000 |
B | -0.000 |
care | -0.000 |
Token | from |
Token ID | 422 |
Feature activation | +5.13e-01 |
Pos logit contributions | |
them | +0.006 |
him | +0.006 |
Chick | +0.005 |
B | +0.005 |
cl | +0.005 |
Neg logit contributions | |
trove | -0.017 |
notebook | -0.017 |
Statue | -0.016 |
pad | -0.016 |
sed | -0.016 |
Token | them |
Token ID | 606 |
Feature activation | -7.88e-01 |
Pos logit contributions | |
notebook | +0.015 |
coc | +0.015 |
trove | +0.014 |
goal | +0.014 |
adow | +0.014 |
Neg logit contributions | |
Chick | -0.012 |
him | -0.011 |
hey | -0.010 |
bo | -0.010 |
B | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
coc | +0.023 |
notebook | +0.023 |
goals | +0.021 |
adow | +0.021 |
goal | +0.021 |
Neg logit contributions | |
Chick | -0.021 |
bo | -0.020 |
him | -0.020 |
Ch | -0.019 |
head | -0.019 |
Token | way |
Token ID | 835 |
Feature activation | -5.95e-02 |
Pos logit contributions | |
coc | +0.003 |
notebook | +0.003 |
goals | +0.002 |
trove | +0.002 |
pleased | +0.002 |
Neg logit contributions | |
bo | -0.003 |
Chick | -0.003 |
Ch | -0.003 |
him | -0.003 |
head | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -2.48e-01 |
Pos logit contributions | |
bo | +0.001 |
Chick | +0.001 |
him | +0.001 |
B | +0.001 |
head | +0.001 |
Neg logit contributions | |
coc | -0.002 |
notebook | -0.002 |
goals | -0.002 |
pleased | -0.002 |
impressed | -0.002 |
Token | lamp |
Token ID | 20450 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Chick | +0.005 |
him | +0.005 |
B | +0.005 |
hey | +0.005 |
head | +0.005 |
Neg logit contributions | |
coc | -0.008 |
notebook | -0.008 |
stash | -0.007 |
packs | -0.007 |
goals | -0.007 |
Token | - |
Token ID | 12 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
bo | +0.053 |
Chick | +0.049 |
head | +0.047 |
him | +0.046 |
Ch | +0.044 |
Neg logit contributions | |
coc | -0.065 |
notebook | -0.061 |
pleased | -0.055 |
goals | -0.054 |
impressed | -0.054 |
Token | head |
Token ID | 2256 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
Baby | +0.023 |
Junior | +0.023 |
lon | +0.023 |
Chick | +0.023 |
Ethan | +0.022 |
Neg logit contributions | |
coc | -0.035 |
notebook | -0.033 |
book | -0.033 |
packs | -0.031 |
statue | -0.031 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
Chick | +0.128 |
bo | +0.127 |
him | +0.123 |
head | +0.120 |
Ch | +0.119 |
Neg logit contributions | |
coc | -0.078 |
notebook | -0.075 |
goals | -0.067 |
goal | -0.064 |
trove | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -4.00e-01 |
Pos logit contributions | |
Chick | +0.005 |
bo | +0.004 |
him | +0.004 |
E | +0.004 |
Ch | +0.004 |
Neg logit contributions | |
coc | -0.006 |
notebook | -0.006 |
goals | -0.006 |
trove | -0.006 |
goal | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -7.48e-01 |
Pos logit contributions | |
Chick | +0.010 |
bo | +0.010 |
Ch | +0.009 |
hey | +0.009 |
head | +0.009 |
Neg logit contributions | |
coc | -0.010 |
notebook | -0.010 |
goals | -0.009 |
goal | -0.009 |
book | -0.009 |
Token | Jen |
Token ID | 44875 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
Chick | +0.016 |
bo | +0.015 |
him | +0.014 |
head | +0.014 |
Ch | +0.014 |
Neg logit contributions | |
coc | -0.022 |
notebook | -0.022 |
goals | -0.020 |
goal | -0.020 |
packs | -0.020 |
Token | gigg |
Token ID | 30442 |
Feature activation | +9.31e-01 |
Pos logit contributions | |
bo | +0.013 |
Ch | +0.012 |
Chick | +0.012 |
him | +0.012 |
cl | +0.011 |
Neg logit contributions | |
coc | -0.015 |
notebook | -0.014 |
ours | -0.014 |
goals | -0.013 |
culture | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | -3.94e-02 |
Pos logit contributions | |
notebook | +0.012 |
coc | +0.011 |
poem | +0.011 |
packs | +0.011 |
pad | +0.010 |
Neg logit contributions | |
Chick | -0.009 |
him | -0.008 |
bo | -0.008 |
B | -0.008 |
head | -0.008 |
Token | stays |
Token ID | 14768 |
Feature activation | +2.17e-01 |
Pos logit contributions | |
bo | +0.001 |
Chick | +0.001 |
him | +0.001 |
head | +0.001 |
B | +0.001 |
Neg logit contributions | |
coc | -0.001 |
notebook | -0.001 |
poem | -0.001 |
culture | -0.001 |
goals | -0.001 |
Token | safe |
Token ID | 3338 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
Statue | +0.007 |
oral | +0.007 |
languages | +0.007 |
coc | +0.007 |
facts | +0.007 |
Neg logit contributions | |
him | -0.004 |
Chick | -0.004 |
bo | -0.004 |
B | -0.003 |
Baby | -0.003 |
Token | for |
Token ID | 329 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
notebook | +0.020 |
coc | +0.019 |
oral | +0.019 |
poem | +0.018 |
ey | +0.018 |
Neg logit contributions | |
him | -0.011 |
head | -0.010 |
bo | -0.009 |
Chick | -0.009 |
B | -0.009 |
Token | as |
Token ID | 355 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
notebook | +0.014 |
packs | +0.013 |
goal | +0.013 |
coc | +0.013 |
pad | +0.013 |
Neg logit contributions | |
him | -0.009 |
Chick | -0.009 |
B | -0.008 |
Baby | -0.008 |
bo | -0.007 |
Token | long |
Token ID | 890 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
Chick | +0.037 |
him | +0.036 |
B | +0.035 |
Baby | +0.034 |
head | +0.031 |
Neg logit contributions | |
languages | -0.065 |
notebook | -0.065 |
Statue | -0.065 |
wrist | -0.063 |
agrees | -0.063 |
Token | as |
Token ID | 355 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
Chick | +0.079 |
him | +0.075 |
bo | +0.074 |
head | +0.070 |
B | +0.070 |
Neg logit contributions | |
notebook | -0.126 |
coc | -0.124 |
Statue | -0.115 |
goal | -0.115 |
poem | -0.115 |
Token | possible |
Token ID | 1744 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
Chick | +0.040 |
him | +0.038 |
B | +0.037 |
Baby | +0.036 |
head | +0.034 |
Neg logit contributions | |
notebook | -0.070 |
languages | -0.068 |
wrist | -0.067 |
Statue | -0.067 |
coc | -0.067 |
Token | ." |
Token ID | 526 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
him | +0.009 |
bo | +0.008 |
head | +0.008 |
Chick | +0.007 |
care | +0.007 |
Neg logit contributions | |
impressed | -0.013 |
notebook | -0.013 |
coc | -0.013 |
pleased | -0.013 |
ey | -0.012 |
Token | |
Token ID | 220 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
coc | +0.008 |
notebook | +0.008 |
goals | +0.008 |
trove | +0.008 |
culture | +0.008 |
Neg logit contributions | |
Chick | -0.004 |
him | -0.004 |
B | -0.004 |
bo | -0.004 |
Baby | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
coc | +0.003 |
notebook | +0.003 |
trove | +0.003 |
culture | +0.003 |
goals | +0.003 |
Neg logit contributions | |
Chick | -0.002 |
bo | -0.002 |
him | -0.002 |
E | -0.002 |
Ch | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
notebook | +0.022 |
adow | +0.021 |
coc | +0.021 |
pad | +0.021 |
agrees | +0.021 |
Neg logit contributions | |
him | -0.011 |
Chick | -0.011 |
B | -0.010 |
E | -0.010 |
Baby | -0.009 |
Token | same |
Token ID | 976 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
packs | +0.004 |
coc | +0.004 |
notebook | +0.004 |
impressed | +0.004 |
goals | +0.004 |
Neg logit contributions | |
bo | -0.005 |
Chick | -0.005 |
him | -0.005 |
Ch | -0.005 |
E | -0.005 |
Token | place |
Token ID | 1295 |
Feature activation | +4.43e-01 |
Pos logit contributions | |
bo | +0.007 |
Chick | +0.006 |
E | +0.006 |
head | +0.006 |
B | +0.006 |
Neg logit contributions | |
impressed | -0.006 |
ses | -0.006 |
ours | -0.005 |
pleased | -0.005 |
culture | -0.005 |
Token | for |
Token ID | 329 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
coc | +0.016 |
tal | +0.015 |
goals | +0.015 |
poem | +0.014 |
Statue | +0.014 |
Neg logit contributions | |
him | -0.007 |
head | -0.006 |
Chick | -0.006 |
ick | -0.006 |
B | -0.006 |
Token | as |
Token ID | 355 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
notebook | +0.012 |
coc | +0.012 |
goal | +0.011 |
goals | +0.011 |
trove | +0.011 |
Neg logit contributions | |
Chick | -0.009 |
him | -0.009 |
B | -0.009 |
E | -0.008 |
Ch | -0.008 |
Token | long |
Token ID | 890 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
Chick | +0.038 |
him | +0.035 |
B | +0.034 |
E | +0.033 |
Ch | +0.032 |
Neg logit contributions | |
coc | -0.058 |
notebook | -0.057 |
trove | -0.055 |
goals | -0.054 |
goal | -0.054 |
Token | as |
Token ID | 355 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
bo | +0.103 |
E | +0.098 |
Chick | +0.098 |
hey | +0.095 |
Ch | +0.094 |
Neg logit contributions | |
coc | -0.102 |
notebook | -0.096 |
goals | -0.093 |
packs | -0.089 |
reading | -0.089 |
Token | anyone |
Token ID | 2687 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
Chick | +0.031 |
him | +0.028 |
B | +0.026 |
bo | +0.025 |
Ch | +0.025 |
Neg logit contributions | |
coc | -0.074 |
notebook | -0.072 |
goals | -0.070 |
goal | -0.070 |
trove | -0.069 |
Token | could |
Token ID | 714 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Chick | +0.013 |
bo | +0.013 |
him | +0.013 |
B | +0.012 |
Ch | +0.012 |
Neg logit contributions | |
coc | -0.017 |
notebook | -0.016 |
goals | -0.016 |
goal | -0.015 |
trove | -0.015 |
Token | remember |
Token ID | 3505 |
Feature activation | -7.02e-01 |
Pos logit contributions | |
him | +0.021 |
Chick | +0.019 |
bo | +0.019 |
B | +0.017 |
cl | +0.016 |
Neg logit contributions | |
coc | -0.041 |
notebook | -0.040 |
goals | -0.039 |
ours | -0.038 |
culture | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
him | +0.011 |
them | +0.009 |
Chick | +0.009 |
B | +0.009 |
Baby | +0.007 |
Neg logit contributions | |
coc | -0.027 |
slaves | -0.027 |
notebook | -0.027 |
goal | -0.026 |
Statue | -0.026 |
Token | can |
Token ID | 460 |
Feature activation | -1.10e-01 |
Pos logit contributions | |
coc | +0.024 |
notebook | +0.024 |
goals | +0.022 |
packs | +0.021 |
poem | +0.021 |
Neg logit contributions | |
bo | -0.021 |
Chick | -0.021 |
him | -0.020 |
hey | -0.019 |
B | -0.019 |
Token | stay |
Token ID | 2652 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Chick | +0.003 |
head | +0.003 |
Ch | +0.003 |
E | +0.003 |
bo | +0.003 |
Neg logit contributions | |
coc | -0.003 |
goal | -0.002 |
notebook | -0.002 |
goals | -0.002 |
adow | -0.002 |
Token | with |
Token ID | 351 |
Feature activation | -3.80e-02 |
Pos logit contributions | |
coc | +0.010 |
notebook | +0.010 |
Statue | +0.009 |
dictionary | +0.009 |
goals | +0.009 |
Neg logit contributions | |
him | -0.007 |
Chick | -0.007 |
bo | -0.007 |
B | -0.006 |
hey | -0.006 |
Token | us |
Token ID | 514 |
Feature activation | -6.75e-01 |
Pos logit contributions | |
him | +0.001 |
Chick | +0.001 |
bo | +0.001 |
hey | +0.001 |
B | +0.001 |
Neg logit contributions | |
coc | -0.001 |
notebook | -0.001 |
trove | -0.001 |
goal | -0.001 |
goals | -0.001 |
Token | as |
Token ID | 355 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
him | +0.012 |
Chick | +0.010 |
B | +0.009 |
bo | +0.009 |
them | +0.008 |
Neg logit contributions | |
ey | -0.026 |
notebook | -0.025 |
coc | -0.025 |
tal | -0.024 |
endant | -0.024 |
Token | long |
Token ID | 890 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
Chick | +0.043 |
B | +0.040 |
him | +0.039 |
head | +0.035 |
Baby | +0.035 |
Neg logit contributions | |
notebook | -0.067 |
trove | -0.065 |
coc | -0.065 |
stash | -0.063 |
pad | -0.063 |
Token | as |
Token ID | 355 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
Chick | +0.082 |
bo | +0.080 |
him | +0.075 |
Ch | +0.074 |
E | +0.073 |
Neg logit contributions | |
coc | -0.121 |
notebook | -0.118 |
goals | -0.110 |
goal | -0.107 |
trove | -0.106 |
Token | you |
Token ID | 345 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Chick | +0.043 |
him | +0.043 |
B | +0.040 |
head | +0.037 |
Baby | +0.037 |
Neg logit contributions | |
notebook | -0.073 |
coc | -0.072 |
trove | -0.069 |
stash | -0.068 |
pad | -0.068 |
Token | want |
Token ID | 765 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
bo | +0.003 |
him | +0.002 |
care | +0.002 |
B | +0.002 |
Chick | +0.002 |
Neg logit contributions | |
coc | -0.005 |
notebook | -0.005 |
impressed | -0.005 |
pleased | -0.004 |
trove | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -8.09e-01 |
Pos logit contributions | |
him | +0.023 |
Chick | +0.019 |
B | +0.018 |
them | +0.017 |
head | +0.017 |
Neg logit contributions | |
notebook | -0.034 |
trove | -0.032 |
coc | -0.032 |
stash | -0.031 |
Statue | -0.031 |
Token | We |
Token ID | 775 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
bo | +0.021 |
Chick | +0.021 |
E | +0.020 |
head | +0.020 |
cl | +0.020 |
Neg logit contributions | |
goals | -0.018 |
coc | -0.017 |
notebook | -0.016 |
goal | -0.016 |
hasn | -0.016 |
Token | join |
Token ID | 4654 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
him | +0.001 |
B | +0.001 |
them | +0.001 |
Baby | +0.001 |
Chick | +0.001 |
Neg logit contributions | |
goals | -0.004 |
endant | -0.004 |
coc | -0.004 |
tal | -0.004 |
ymes | -0.004 |
Token | them |
Token ID | 606 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
coc | +0.045 |
trove | +0.045 |
notebook | +0.044 |
stash | +0.044 |
pleased | +0.044 |
Neg logit contributions | |
him | -0.009 |
them | -0.004 |
Chick | -0.003 |
B | -0.003 |
bo | -0.003 |
Token | again |
Token ID | 757 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
him | +0.011 |
Chick | +0.009 |
B | +0.008 |
bo | +0.007 |
Teddy | +0.007 |
Neg logit contributions | |
ey | -0.027 |
hasn | -0.027 |
tal | -0.027 |
coc | -0.027 |
Statue | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
endant | +0.024 |
ey | +0.023 |
ses | +0.023 |
Statue | +0.023 |
sed | +0.022 |
Neg logit contributions | |
him | -0.004 |
Chick | -0.004 |
when | -0.003 |
while | -0.003 |
B | -0.003 |
Token | as |
Token ID | 355 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
coc | +0.009 |
notebook | +0.008 |
goals | +0.008 |
trove | +0.008 |
tal | +0.008 |
Neg logit contributions | |
him | -0.006 |
Chick | -0.006 |
B | -0.005 |
Baby | -0.005 |
hey | -0.005 |
Token | long |
Token ID | 890 |
Feature activation | -3.96e+00 |
Pos logit contributions | |
Chick | +0.032 |
him | +0.030 |
B | +0.028 |
Baby | +0.027 |
E | +0.026 |
Neg logit contributions | |
coc | -0.052 |
notebook | -0.051 |
trove | -0.049 |
adow | -0.048 |
goals | -0.048 |
Token | as |
Token ID | 355 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
Chick | +0.093 |
bo | +0.092 |
E | +0.089 |
Ch | +0.088 |
hey | +0.084 |
Neg logit contributions | |
coc | -0.108 |
notebook | -0.103 |
goals | -0.100 |
packs | -0.094 |
book | -0.093 |
Token | he |
Token ID | 339 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
Chick | +0.037 |
him | +0.035 |
bo | +0.034 |
B | +0.032 |
head | +0.032 |
Neg logit contributions | |
coc | -0.070 |
notebook | -0.068 |
goals | -0.064 |
trove | -0.063 |
goal | -0.063 |
Token | kept |
Token ID | 4030 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
Chick | +0.009 |
bo | +0.009 |
Ch | +0.008 |
him | +0.008 |
B | +0.008 |
Neg logit contributions | |
coc | -0.013 |
notebook | -0.012 |
ours | -0.012 |
goals | -0.012 |
goal | -0.012 |
Token | his |
Token ID | 465 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
him | +0.025 |
Chick | +0.025 |
bo | +0.023 |
B | +0.021 |
Baby | +0.021 |
Neg logit contributions | |
coc | -0.042 |
notebook | -0.040 |
trove | -0.039 |
goals | -0.038 |
adow | -0.038 |
Token | promise |
Token ID | 6991 |
Feature activation | +6.77e-01 |
Pos logit contributions | |
wash | +0.006 |
Chick | +0.005 |
ick | +0.005 |
help | +0.005 |
Baby | +0.005 |
Neg logit contributions | |
trove | -0.007 |
Statue | -0.007 |
coc | -0.007 |
impressed | -0.007 |
Congratulations | -0.007 |
Token | hold |
Token ID | 1745 |
Feature activation | -6.60e-01 |
Pos logit contributions | |
coc | +0.033 |
notebook | +0.032 |
goals | +0.031 |
trove | +0.030 |
packs | +0.030 |
Neg logit contributions | |
Chick | -0.018 |
bo | -0.018 |
him | -0.017 |
Ch | -0.016 |
B | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
hey | +0.023 |
Chick | +0.022 |
E | +0.021 |
bo | +0.021 |
Ch | +0.021 |
Neg logit contributions | |
coc | -0.012 |
notebook | -0.011 |
goals | -0.010 |
book | -0.010 |
packs | -0.009 |
Token | breath |
Token ID | 8033 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
bo | +0.017 |
Chick | +0.017 |
him | +0.016 |
B | +0.016 |
Baby | +0.015 |
Neg logit contributions | |
trove | -0.015 |
coc | -0.015 |
impressed | -0.014 |
notebook | -0.014 |
pleased | -0.014 |
Token | for |
Token ID | 329 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.000 |
goals | +0.000 |
goal | +0.000 |
trove | +0.000 |
Neg logit contributions | |
Chick | -0.000 |
bo | -0.000 |
Ch | -0.000 |
E | -0.000 |
him | -0.000 |
Token | as |
Token ID | 355 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
bo | +0.012 |
lon | +0.011 |
Chick | +0.010 |
hey | +0.010 |
Ch | +0.010 |
Neg logit contributions | |
coc | -0.009 |
goals | -0.008 |
friends | -0.007 |
notebook | -0.007 |
skills | -0.007 |
Token | long |
Token ID | 890 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
bo | +0.040 |
Chick | +0.038 |
E | +0.036 |
hey | +0.036 |
Ch | +0.035 |
Neg logit contributions | |
coc | -0.057 |
notebook | -0.056 |
goals | -0.054 |
goal | -0.051 |
book | -0.051 |
Token | as |
Token ID | 355 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
E | +0.122 |
bo | +0.120 |
hey | +0.120 |
Chick | +0.115 |
lon | +0.115 |
Neg logit contributions | |
coc | -0.081 |
goals | -0.077 |
notebook | -0.067 |
net | -0.066 |
reading | -0.066 |
Token | he |
Token ID | 339 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
bo | +0.039 |
Chick | +0.037 |
E | +0.036 |
Ch | +0.035 |
hey | +0.034 |
Neg logit contributions | |
coc | -0.064 |
notebook | -0.063 |
goals | -0.059 |
packs | -0.057 |
book | -0.056 |
Token | could |
Token ID | 714 |
Feature activation | -9.34e-01 |
Pos logit contributions | |
Chick | +0.017 |
bo | +0.016 |
hey | +0.016 |
E | +0.016 |
head | +0.015 |
Neg logit contributions | |
coc | -0.013 |
notebook | -0.013 |
goals | -0.012 |
goal | -0.012 |
stash | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
Chick | +0.019 |
bo | +0.018 |
him | +0.017 |
Ch | +0.017 |
E | +0.016 |
Neg logit contributions | |
coc | -0.029 |
notebook | -0.028 |
goals | -0.026 |
trove | -0.026 |
book | -0.025 |
Token | One |
Token ID | 1881 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
coc | +0.010 |
notebook | +0.009 |
goal | +0.009 |
goals | +0.009 |
book | +0.009 |
Neg logit contributions | |
bo | -0.010 |
hey | -0.010 |
Chick | -0.010 |
head | -0.009 |
E | -0.009 |
Token | you |
Token ID | 345 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
Chick | +0.010 |
B | +0.010 |
him | +0.009 |
hey | +0.009 |
Baby | +0.009 |
Neg logit contributions | |
coc | -0.013 |
notebook | -0.013 |
goals | -0.012 |
packs | -0.012 |
stash | -0.012 |
Token | can |
Token ID | 460 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
coc | +0.026 |
notebook | +0.026 |
packs | +0.024 |
goals | +0.024 |
poem | +0.023 |
Neg logit contributions | |
Chick | -0.022 |
bo | -0.022 |
him | -0.021 |
B | -0.021 |
hey | -0.020 |
Token | stay |
Token ID | 2652 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
coc | +0.008 |
notebook | +0.007 |
goals | +0.007 |
goal | +0.007 |
book | +0.007 |
Neg logit contributions | |
Chick | -0.005 |
bo | -0.005 |
Ch | -0.005 |
E | -0.005 |
head | -0.005 |
Token | here |
Token ID | 994 |
Feature activation | +8.31e-01 |
Pos logit contributions | |
coc | +0.016 |
notebook | +0.016 |
goals | +0.015 |
Statue | +0.015 |
dictionary | +0.015 |
Neg logit contributions | |
bo | -0.011 |
Chick | -0.011 |
him | -0.011 |
B | -0.010 |
Baby | -0.009 |
Token | as |
Token ID | 355 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ey | +0.031 |
notebook | +0.030 |
Statue | +0.029 |
ses | +0.029 |
coc | +0.029 |
Neg logit contributions | |
him | -0.014 |
Chick | -0.011 |
bo | -0.011 |
B | -0.010 |
them | -0.010 |
Token | long |
Token ID | 890 |
Feature activation | -3.93e+00 |
Pos logit contributions | |
Chick | +0.028 |
B | +0.026 |
him | +0.026 |
Baby | +0.023 |
head | +0.022 |
Neg logit contributions | |
trove | -0.053 |
notebook | -0.052 |
Statue | -0.051 |
wrist | -0.051 |
stash | -0.050 |
Token | as |
Token ID | 355 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
Chick | +0.076 |
bo | +0.073 |
him | +0.070 |
head | +0.067 |
Ch | +0.067 |
Neg logit contributions | |
coc | -0.124 |
notebook | -0.123 |
goals | -0.114 |
trove | -0.112 |
goal | -0.112 |
Token | you |
Token ID | 345 |
Feature activation | -8.55e-02 |
Pos logit contributions | |
him | +0.033 |
Chick | +0.033 |
B | +0.030 |
Baby | +0.029 |
head | +0.029 |
Neg logit contributions | |
notebook | -0.066 |
trove | -0.066 |
stash | -0.064 |
coc | -0.064 |
dilemma | -0.064 |
Token | want |
Token ID | 765 |
Feature activation | -7.22e-01 |
Pos logit contributions | |
him | +0.002 |
bo | +0.002 |
B | +0.001 |
care | +0.001 |
Chick | +0.001 |
Neg logit contributions | |
notebook | -0.003 |
coc | -0.003 |
impressed | -0.003 |
pleased | -0.003 |
poem | -0.003 |
Token | ," |
Token ID | 553 |
Feature activation | -5.62e-01 |
Pos logit contributions | |
him | +0.016 |
Chick | +0.013 |
B | +0.012 |
them | +0.012 |
bo | +0.012 |
Neg logit contributions | |
trove | -0.024 |
notebook | -0.024 |
pleased | -0.023 |
impressed | -0.023 |
amaz | -0.022 |
Token | said |
Token ID | 531 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
Chick | +0.012 |
him | +0.011 |
B | +0.011 |
bo | +0.011 |
Baby | +0.010 |
Neg logit contributions | |
trove | -0.018 |
coc | -0.018 |
goals | -0.018 |
notebook | -0.018 |
packs | -0.017 |
Token | would |
Token ID | 561 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
coc | +0.022 |
trove | +0.022 |
notebook | +0.021 |
tal | +0.021 |
goals | +0.021 |
Neg logit contributions | |
Chick | -0.011 |
B | -0.010 |
him | -0.010 |
Baby | -0.009 |
Ch | -0.009 |
Token | be |
Token ID | 307 |
Feature activation | +4.30e-01 |
Pos logit contributions | |
coc | +0.002 |
notebook | +0.002 |
goals | +0.002 |
packs | +0.002 |
adow | +0.002 |
Neg logit contributions | |
Chick | -0.001 |
him | -0.001 |
bo | -0.001 |
B | -0.001 |
Ch | -0.001 |
Token | OK |
Token ID | 7477 |
Feature activation | +3.46e-01 |
Pos logit contributions | |
coc | +0.014 |
Statue | +0.013 |
goal | +0.013 |
notebook | +0.013 |
trove | +0.013 |
Neg logit contributions | |
Chick | -0.008 |
him | -0.008 |
B | -0.008 |
bo | -0.007 |
them | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +4.51e-01 |
Pos logit contributions | |
coc | +0.012 |
tal | +0.012 |
notebook | +0.011 |
goals | +0.011 |
trove | +0.011 |
Neg logit contributions | |
him | -0.006 |
Chick | -0.006 |
bo | -0.006 |
B | -0.006 |
head | -0.005 |
Token | as |
Token ID | 355 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
notebook | +0.013 |
coc | +0.013 |
goals | +0.012 |
goal | +0.012 |
trove | +0.012 |
Neg logit contributions | |
Chick | -0.010 |
him | -0.010 |
B | -0.009 |
bo | -0.009 |
E | -0.009 |
Token | long |
Token ID | 890 |
Feature activation | -3.92e+00 |
Pos logit contributions | |
Chick | +0.029 |
B | +0.026 |
him | +0.026 |
E | +0.025 |
Baby | +0.025 |
Neg logit contributions | |
notebook | -0.042 |
coc | -0.042 |
goals | -0.041 |
goal | -0.039 |
trove | -0.039 |
Token | as |
Token ID | 355 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
bo | +0.114 |
Ch | +0.106 |
Chick | +0.105 |
E | +0.104 |
lon | +0.099 |
Neg logit contributions | |
coc | -0.089 |
notebook | -0.080 |
reading | -0.078 |
goals | -0.078 |
packs | -0.076 |
Token | they |
Token ID | 484 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
Chick | +0.038 |
bo | +0.036 |
him | +0.035 |
E | +0.034 |
Ch | +0.034 |
Neg logit contributions | |
coc | -0.063 |
notebook | -0.062 |
goals | -0.058 |
goal | -0.057 |
trove | -0.056 |
Token | all |
Token ID | 477 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
him | +0.011 |
B | +0.010 |
bo | +0.010 |
care | +0.009 |
Chick | +0.009 |
Neg logit contributions | |
coc | -0.023 |
tal | -0.022 |
notebook | -0.022 |
territory | -0.022 |
web | -0.021 |
Token | ate |
Token ID | 15063 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
care | +0.002 |
him | +0.002 |
B | +0.002 |
bo | +0.002 |
Chick | +0.002 |
Neg logit contributions | |
trove | -0.005 |
coc | -0.005 |
tal | -0.004 |
stash | -0.004 |
lair | -0.004 |
Token | healthy |
Token ID | 5448 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
notebook | +0.007 |
coc | +0.007 |
trove | +0.007 |
lair | +0.007 |
pad | +0.007 |
Neg logit contributions | |
him | -0.004 |
Chick | -0.004 |
B | -0.004 |
Baby | -0.004 |
them | -0.004 |
Token | time |
Token ID | 640 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
packs | +0.018 |
goals | +0.017 |
coc | +0.016 |
ushes | +0.016 |
adow | +0.016 |
Neg logit contributions | |
head | -0.012 |
bo | -0.012 |
Chick | -0.011 |
Baby | -0.011 |
rum | -0.011 |
Token | there |
Token ID | 612 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
him | +0.003 |
B | +0.002 |
head | +0.002 |
B | +0.002 |
hey | +0.002 |
Neg logit contributions | |
coc | -0.005 |
notebook | -0.005 |
rightful | -0.005 |
goals | -0.005 |
poem | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
him | +0.017 |
bo | +0.011 |
B | +0.011 |
them | +0.011 |
Baby | +0.011 |
Neg logit contributions | |
coc | -0.032 |
ours | -0.030 |
goals | -0.029 |
culture | -0.029 |
dictionary | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +5.95e-01 |
Pos logit contributions | |
coc | +0.013 |
notebook | +0.013 |
trove | +0.013 |
stash | +0.012 |
ocket | +0.012 |
Neg logit contributions | |
him | -0.006 |
E | -0.006 |
B | -0.006 |
Chick | -0.006 |
bo | -0.006 |
Token | furry |
Token ID | 40857 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
packs | +0.018 |
goals | +0.017 |
adow | +0.017 |
aces | +0.017 |
coc | +0.017 |
Neg logit contributions | |
Chick | -0.012 |
E | -0.011 |
Baby | -0.011 |
B | -0.011 |
hey | -0.011 |
Token | par |
Token ID | 1582 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
coc | +0.006 |
goals | +0.006 |
packs | +0.006 |
notebook | +0.006 |
impressed | +0.006 |
Neg logit contributions | |
Chick | -0.005 |
B | -0.005 |
bo | -0.005 |
him | -0.005 |
Baby | -0.005 |
Token | rot |
Token ID | 10599 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
coc | +0.039 |
notebook | +0.036 |
goals | +0.034 |
packs | +0.031 |
goal | +0.030 |
Neg logit contributions | |
bo | -0.096 |
Chick | -0.093 |
Ch | -0.091 |
E | -0.090 |
him | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
coc | +0.045 |
goals | +0.044 |
ushes | +0.043 |
amaz | +0.042 |
ey | +0.042 |
Neg logit contributions | |
bo | -0.017 |
Chick | -0.015 |
him | -0.015 |
B | -0.013 |
B | -0.013 |
Token | He |
Token ID | 679 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
coc | +0.006 |
notebook | +0.006 |
mistake | +0.005 |
goals | +0.005 |
packs | +0.005 |
Neg logit contributions | |
B | -0.002 |
Chick | -0.002 |
him | -0.002 |
Pe | -0.002 |
Baby | -0.002 |
Token | liked |
Token ID | 8288 |
Feature activation | -4.77e-02 |
Pos logit contributions | |
coc | +0.007 |
ours | +0.007 |
notebook | +0.007 |
packs | +0.007 |
trove | +0.007 |
Neg logit contributions | |
bo | -0.004 |
Chick | -0.004 |
him | -0.004 |
B | -0.004 |
Ch | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
him | +0.001 |
Chick | +0.001 |
B | +0.001 |
bo | +0.001 |
Baby | +0.001 |
Neg logit contributions | |
trove | -0.001 |
adow | -0.001 |
notebook | -0.001 |
coc | -0.001 |
packs | -0.001 |
Token | I |
Token ID | 314 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
coc | +0.002 |
notebook | +0.002 |
goals | +0.002 |
goal | +0.002 |
book | +0.002 |
Neg logit contributions | |
bo | -0.003 |
Chick | -0.003 |
E | -0.002 |
him | -0.002 |
Ch | -0.002 |
Token | want |
Token ID | 765 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
bo | +0.005 |
Chick | +0.005 |
him | +0.005 |
Ch | +0.005 |
E | +0.005 |
Neg logit contributions | |
coc | -0.007 |
notebook | -0.006 |
goals | -0.006 |
trove | -0.006 |
packs | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
notebook | +0.007 |
coc | +0.007 |
goals | +0.007 |
trove | +0.007 |
goal | +0.006 |
Neg logit contributions | |
Chick | -0.008 |
bo | -0.007 |
him | -0.007 |
E | -0.007 |
Ch | -0.007 |
Token | make |
Token ID | 787 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
Chick | +0.000 |
bo | +0.000 |
Ch | +0.000 |
E | +0.000 |
head | +0.000 |
Neg logit contributions | |
coc | -0.000 |
notebook | -0.000 |
goals | -0.000 |
goal | -0.000 |
book | -0.000 |
Token | another |
Token ID | 1194 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.001 |
goals | +0.001 |
goal | +0.001 |
book | +0.001 |
Neg logit contributions | |
Chick | -0.001 |
bo | -0.001 |
Ch | -0.001 |
E | -0.001 |
him | -0.001 |
Token | muff |
Token ID | 27563 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
notebook | +0.029 |
coc | +0.027 |
trove | +0.027 |
goals | +0.026 |
packs | +0.026 |
Neg logit contributions | |
Chick | -0.016 |
E | -0.016 |
bo | -0.016 |
head | -0.014 |
B | -0.014 |
Token | in |
Token ID | 259 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
coc | +0.080 |
notebook | +0.078 |
goals | +0.073 |
goal | +0.071 |
trove | +0.071 |
Neg logit contributions | |
bo | -0.057 |
Chick | -0.057 |
E | -0.052 |
him | -0.052 |
Ch | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
bo | +0.003 |
Chick | +0.003 |
him | +0.003 |
head | +0.002 |
B | +0.002 |
Neg logit contributions | |
notebook | -0.005 |
coc | -0.005 |
trove | -0.004 |
culture | -0.004 |
tal | -0.004 |
Token | A |
Token ID | 317 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
Chick | +0.021 |
bo | +0.021 |
Ch | +0.020 |
him | +0.020 |
E | +0.020 |
Neg logit contributions | |
coc | -0.020 |
notebook | -0.019 |
goals | -0.018 |
goal | -0.017 |
trove | -0.017 |
Token | bigger |
Token ID | 5749 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
Chick | +0.001 |
E | +0.001 |
bo | +0.001 |
head | +0.001 |
Ch | +0.001 |
Neg logit contributions | |
notebook | -0.001 |
packs | -0.001 |
coc | -0.001 |
goals | -0.001 |
trove | -0.001 |
Token | one |
Token ID | 530 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Chick | +0.004 |
bo | +0.004 |
head | +0.004 |
E | +0.004 |
Pe | +0.004 |
Neg logit contributions | |
notebook | -0.006 |
impressed | -0.006 |
coc | -0.006 |
trove | -0.006 |
pleased | -0.006 |
Token | it |
Token ID | 340 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
coc | +0.007 |
goals | +0.006 |
notebook | +0.006 |
book | +0.005 |
goal | +0.005 |
Neg logit contributions | |
Ch | -0.009 |
bo | -0.009 |
hey | -0.009 |
Chick | -0.009 |
head | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
coc | +0.016 |
notebook | +0.016 |
goals | +0.015 |
culture | +0.014 |
packs | +0.014 |
Neg logit contributions | |
Chick | -0.012 |
him | -0.011 |
bo | -0.011 |
E | -0.010 |
B | -0.010 |
Token | He |
Token ID | 679 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
coc | +0.013 |
notebook | +0.013 |
goals | +0.013 |
goal | +0.012 |
book | +0.012 |
Neg logit contributions | |
Chick | -0.012 |
bo | -0.011 |
Ch | -0.010 |
hey | -0.010 |
E | -0.010 |
Token | opened |
Token ID | 4721 |
Feature activation | +9.32e-02 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.001 |
goals | +0.001 |
packs | +0.001 |
goal | +0.001 |
Neg logit contributions | |
bo | -0.001 |
Chick | -0.001 |
E | -0.001 |
him | -0.001 |
Ch | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
coc | +0.002 |
notebook | +0.002 |
goals | +0.002 |
book | +0.001 |
goal | +0.001 |
Neg logit contributions | |
Ch | -0.003 |
bo | -0.003 |
hey | -0.003 |
Chick | -0.003 |
head | -0.003 |
Token | jar |
Token ID | 17379 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
coc | +0.009 |
notebook | +0.008 |
goals | +0.008 |
packs | +0.007 |
adow | +0.007 |
Neg logit contributions | |
Chick | -0.023 |
bo | -0.023 |
him | -0.022 |
E | -0.022 |
head | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +9.99e-01 |
Pos logit contributions | |
culture | +0.087 |
coc | +0.086 |
goals | +0.081 |
rightful | +0.079 |
slaves | +0.079 |
Neg logit contributions | |
him | -0.052 |
bo | -0.047 |
head | -0.045 |
Chick | -0.042 |
ick | -0.040 |
Token | took |
Token ID | 1718 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
coc | +0.030 |
goals | +0.028 |
notebook | +0.028 |
goal | +0.027 |
trove | +0.026 |
Neg logit contributions | |
Chick | -0.022 |
bo | -0.021 |
him | -0.020 |
E | -0.019 |
hey | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
Ch | +0.033 |
Twe | +0.033 |
hey | +0.032 |
Chick | +0.031 |
B | +0.031 |
Neg logit contributions | |
coc | -0.015 |
notebook | -0.014 |
book | -0.014 |
goals | -0.013 |
speech | -0.013 |
Token | big |
Token ID | 1263 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
Chick | +0.037 |
bo | +0.036 |
hey | +0.035 |
Ch | +0.035 |
him | +0.035 |
Neg logit contributions | |
coc | -0.032 |
notebook | -0.031 |
book | -0.029 |
poem | -0.027 |
goal | -0.027 |
Token | pinch |
Token ID | 25394 |
Feature activation | -3.94e-01 |
Pos logit contributions | |
Ch | +0.025 |
Chick | +0.025 |
bo | +0.024 |
E | +0.024 |
hey | +0.024 |
Neg logit contributions | |
coc | -0.018 |
notebook | -0.018 |
book | -0.017 |
net | -0.016 |
goal | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
bo | +0.007 |
Chick | +0.007 |
E | +0.007 |
Ch | +0.007 |
B | +0.006 |
Neg logit contributions | |
coc | -0.011 |
notebook | -0.011 |
goals | -0.010 |
packs | -0.010 |
trove | -0.010 |
Token | store |
Token ID | 3650 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
coc | +0.013 |
packs | +0.012 |
notebook | +0.012 |
goals | +0.012 |
tal | +0.012 |
Neg logit contributions | |
bo | -0.009 |
E | -0.009 |
hey | -0.009 |
Chick | -0.009 |
Baby | -0.008 |
Token | keeper |
Token ID | 13884 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
bo | +0.001 |
him | +0.001 |
Chick | +0.000 |
B | +0.000 |
cl | +0.000 |
Neg logit contributions | |
coc | -0.001 |
goals | -0.001 |
packs | -0.001 |
notebook | -0.001 |
ours | -0.001 |
Token | put |
Token ID | 1234 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
coc | +0.004 |
goals | +0.004 |
notebook | +0.004 |
ours | +0.004 |
packs | +0.004 |
Neg logit contributions | |
bo | -0.003 |
Chick | -0.003 |
him | -0.003 |
B | -0.003 |
Ch | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
Chick | +0.006 |
bo | +0.006 |
Ch | +0.005 |
E | +0.005 |
him | +0.005 |
Neg logit contributions | |
coc | -0.007 |
notebook | -0.007 |
goals | -0.007 |
goal | -0.006 |
trove | -0.006 |
Token | muff |
Token ID | 27563 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
coc | +0.001 |
goals | +0.001 |
tal | +0.001 |
adow | +0.001 |
alk | +0.001 |
Neg logit contributions | |
nurses | -0.001 |
head | -0.001 |
him | -0.001 |
E | -0.001 |
Baby | -0.001 |
Token | in |
Token ID | 259 |
Feature activation | +6.84e-01 |
Pos logit contributions | |
coc | +0.105 |
notebook | +0.103 |
goal | +0.099 |
goals | +0.098 |
trove | +0.097 |
Neg logit contributions | |
bo | -0.059 |
Chick | -0.055 |
E | -0.051 |
him | -0.051 |
head | -0.049 |
Token | back |
Token ID | 736 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
coc | +0.022 |
notebook | +0.020 |
culture | +0.020 |
trove | +0.020 |
goals | +0.020 |
Neg logit contributions | |
bo | -0.016 |
Chick | -0.014 |
him | -0.014 |
B | -0.012 |
head | -0.012 |
Token | on |
Token ID | 319 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
coc | +0.044 |
poem | +0.038 |
Statue | +0.038 |
goal | +0.037 |
notebook | +0.036 |
Neg logit contributions | |
him | -0.020 |
bo | -0.017 |
B | -0.015 |
Chick | -0.014 |
Baby | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
coc | +0.013 |
notebook | +0.013 |
adow | +0.012 |
goals | +0.012 |
trove | +0.012 |
Neg logit contributions | |
Chick | -0.010 |
him | -0.009 |
bo | -0.009 |
E | -0.009 |
B | -0.009 |
Token | scale |
Token ID | 5046 |
Feature activation | -5.28e-02 |
Pos logit contributions | |
Baby | +0.016 |
bo | +0.016 |
Chick | +0.016 |
cash | +0.015 |
E | +0.015 |
Neg logit contributions | |
packs | -0.025 |
adow | -0.024 |
coc | -0.023 |
impressed | -0.023 |
goals | -0.023 |
Token | her |
Token ID | 607 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
coc | +0.000 |
notebook | +0.000 |
book | +0.000 |
packs | +0.000 |
goals | +0.000 |
Neg logit contributions | |
Chick | -0.000 |
Ch | -0.000 |
bo | -0.000 |
hey | -0.000 |
lon | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | -6.31e-01 |
Pos logit contributions | |
Chick | +0.007 |
him | +0.007 |
bo | +0.007 |
B | +0.007 |
Baby | +0.007 |
Neg logit contributions | |
coc | -0.012 |
trove | -0.012 |
goals | -0.011 |
culture | -0.011 |
Statue | -0.011 |
Token | box |
Token ID | 3091 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
Chick | +0.014 |
Baby | +0.014 |
bo | +0.014 |
B | +0.013 |
E | +0.013 |
Neg logit contributions | |
goals | -0.016 |
coc | -0.016 |
packs | -0.015 |
trove | -0.015 |
languages | -0.015 |
Token | of |
Token ID | 286 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
Chick | +0.007 |
bo | +0.007 |
him | +0.006 |
Ch | +0.006 |
head | +0.006 |
Neg logit contributions | |
coc | -0.007 |
goals | -0.007 |
notebook | -0.007 |
goal | -0.006 |
culture | -0.006 |
Token | ch |
Token ID | 442 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
coc | +0.004 |
adow | +0.004 |
trove | +0.004 |
goals | +0.004 |
Statue | +0.004 |
Neg logit contributions | |
him | -0.004 |
Chick | -0.004 |
B | -0.003 |
Baby | -0.003 |
E | -0.003 |
Token | ocol |
Token ID | 4668 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
coc | +0.011 |
notebook | +0.010 |
goals | +0.010 |
adow | +0.008 |
packs | +0.008 |
Neg logit contributions | |
Chick | -0.016 |
Ch | -0.015 |
E | -0.015 |
bo | -0.014 |
hey | -0.014 |
Token | ates |
Token ID | 689 |
Feature activation | +4.90e-01 |
Pos logit contributions | |
coc | +0.034 |
notebook | +0.032 |
packs | +0.028 |
goals | +0.026 |
adow | +0.025 |
Neg logit contributions | |
Chick | -0.119 |
E | -0.116 |
hey | -0.114 |
head | -0.114 |
bo | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
goals | +0.020 |
coc | +0.019 |
goal | +0.019 |
maze | +0.019 |
Statue | +0.019 |
Neg logit contributions | |
him | -0.008 |
B | -0.005 |
bo | -0.005 |
Chick | -0.005 |
them | -0.005 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
Chick | +0.004 |
bo | +0.003 |
E | +0.003 |
Ch | +0.003 |
him | +0.003 |
Neg logit contributions | |
coc | -0.006 |
notebook | -0.006 |
goals | -0.006 |
trove | -0.006 |
packs | -0.006 |
Token | opened |
Token ID | 4721 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
coc | +0.021 |
notebook | +0.020 |
goals | +0.019 |
goal | +0.018 |
trove | +0.018 |
Neg logit contributions | |
Chick | -0.018 |
bo | -0.018 |
Ch | -0.017 |
him | -0.016 |
E | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
bo | +0.010 |
Chick | +0.010 |
Ch | +0.009 |
hey | +0.009 |
head | +0.009 |
Neg logit contributions | |
coc | -0.009 |
notebook | -0.009 |
goals | -0.008 |
book | -0.008 |
goal | -0.008 |
Token | But |
Token ID | 1537 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
Chick | +0.012 |
bo | +0.011 |
him | +0.010 |
Baby | +0.010 |
head | +0.010 |
Neg logit contributions | |
coc | -0.014 |
notebook | -0.014 |
goals | -0.013 |
goal | -0.013 |
book | -0.013 |
Token | you |
Token ID | 345 |
Feature activation | +4.44e-01 |
Pos logit contributions | |
Chick | +0.005 |
him | +0.005 |
hey | +0.005 |
bo | +0.005 |
B | +0.005 |
Neg logit contributions | |
coc | -0.006 |
notebook | -0.006 |
goals | -0.006 |
packs | -0.006 |
goal | -0.006 |
Token | have |
Token ID | 423 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
notebook | +0.013 |
coc | +0.013 |
goals | +0.012 |
packs | +0.012 |
pleased | +0.012 |
Neg logit contributions | |
Chick | -0.010 |
bo | -0.009 |
him | -0.009 |
B | -0.009 |
hey | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
trove | +0.043 |
adow | +0.040 |
kins | +0.040 |
eway | +0.039 |
oon | +0.039 |
Neg logit contributions | |
him | -0.014 |
B | -0.012 |
Woo | -0.012 |
bo | -0.012 |
care | -0.011 |
Token | call |
Token ID | 869 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
coc | +0.005 |
notebook | +0.005 |
goals | +0.005 |
trove | +0.004 |
goal | +0.004 |
Neg logit contributions | |
Chick | -0.005 |
bo | -0.005 |
him | -0.005 |
Ch | -0.005 |
E | -0.005 |
Token | me |
Token ID | 502 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
coc | +0.009 |
trove | +0.009 |
stash | +0.009 |
notebook | +0.009 |
adow | +0.009 |
Neg logit contributions | |
him | -0.005 |
Chick | -0.004 |
them | -0.004 |
B | -0.004 |
bo | -0.003 |
Token | Queen |
Token ID | 7542 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
coc | +0.035 |
pleased | +0.033 |
notebook | +0.033 |
tal | +0.032 |
impressed | +0.032 |
Neg logit contributions | |
him | -0.023 |
Chick | -0.021 |
B | -0.020 |
bo | -0.019 |
them | -0.018 |
Token | Ruby |
Token ID | 10888 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
Chick | +0.009 |
him | +0.008 |
bo | +0.008 |
B | +0.008 |
head | +0.007 |
Neg logit contributions | |
coc | -0.012 |
notebook | -0.011 |
tal | -0.011 |
pleased | -0.011 |
goal | -0.011 |
Token | and |
Token ID | 290 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
ey | +0.020 |
coc | +0.019 |
amaz | +0.018 |
tal | +0.018 |
notebook | +0.018 |
Neg logit contributions | |
Chick | -0.006 |
bo | -0.006 |
him | -0.006 |
them | -0.005 |
B | -0.005 |
Token | him |
Token ID | 683 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
him | +0.013 |
Chick | +0.010 |
care | +0.010 |
hey | +0.010 |
bo | +0.010 |
Neg logit contributions | |
coc | -0.021 |
trove | -0.021 |
stash | -0.020 |
pleased | -0.020 |
adow | -0.020 |
Token | King |
Token ID | 2677 |
Feature activation | -1.71e+00 |
Pos logit contributions | |
him | +0.024 |
bo | +0.022 |
Chick | +0.019 |
Snow | +0.018 |
B | +0.018 |
Neg logit contributions | |
coc | -0.051 |
ey | -0.049 |
impressed | -0.046 |
tal | -0.045 |
pleased | -0.044 |
Token | any |
Token ID | 597 |
Feature activation | +6.74e-02 |
Pos logit contributions | |
Chick | +0.022 |
bo | +0.021 |
Ch | +0.020 |
E | +0.020 |
head | +0.020 |
Neg logit contributions | |
coc | -0.021 |
notebook | -0.020 |
goals | -0.019 |
goal | -0.018 |
book | -0.018 |
Token | fear |
Token ID | 3252 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
coc | +0.002 |
trove | +0.002 |
adow | +0.002 |
notebook | +0.002 |
Statue | +0.002 |
Neg logit contributions | |
him | -0.002 |
bo | -0.002 |
hey | -0.001 |
care | -0.001 |
head | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +2.92e-02 |
Pos logit contributions | |
bo | +0.023 |
him | +0.022 |
Chick | +0.022 |
head | +0.021 |
Ch | +0.020 |
Neg logit contributions | |
coc | -0.031 |
notebook | -0.030 |
goals | -0.027 |
trove | -0.027 |
goal | -0.027 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.001 |
goals | +0.001 |
goal | +0.001 |
book | +0.001 |
Neg logit contributions | |
bo | -0.001 |
Chick | -0.001 |
hey | -0.001 |
head | -0.001 |
Ch | -0.001 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.76e-02 |
Pos logit contributions | |
coc | +0.000 |
notebook | +0.000 |
goals | +0.000 |
goal | +0.000 |
book | +0.000 |
Neg logit contributions | |
Chick | -0.000 |
bo | -0.000 |
Ch | -0.000 |
hey | -0.000 |
E | -0.000 |
Token | upon |
Token ID | 2402 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
coc | +0.000 |
notebook | +0.000 |
goals | +0.000 |
goal | +0.000 |
trove | +0.000 |
Neg logit contributions | |
Chick | -0.001 |
bo | -0.001 |
Ch | -0.001 |
him | -0.001 |
E | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
coc | +0.007 |
notebook | +0.007 |
goals | +0.006 |
goal | +0.006 |
book | +0.006 |
Neg logit contributions | |
Chick | -0.009 |
bo | -0.008 |
hey | -0.008 |
Ch | -0.008 |
head | -0.008 |
Token | time |
Token ID | 640 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
Chick | +0.013 |
bo | +0.012 |
head | +0.012 |
hey | +0.011 |
B | +0.011 |
Neg logit contributions | |
coc | -0.009 |
notebook | -0.009 |
goal | -0.009 |
goals | -0.008 |
adow | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
coc | +0.023 |
notebook | +0.022 |
goals | +0.021 |
goal | +0.020 |
book | +0.020 |
Neg logit contributions | |
Chick | -0.021 |
bo | -0.021 |
Ch | -0.020 |
E | -0.019 |
hey | -0.019 |
Token | there |
Token ID | 612 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
coc | +0.019 |
notebook | +0.019 |
goals | +0.017 |
goal | +0.016 |
book | +0.016 |
Neg logit contributions | |
Chick | -0.030 |
bo | -0.030 |
Ch | -0.029 |
E | -0.028 |
hey | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
Chick | +0.023 |
bo | +0.023 |
Ch | +0.022 |
hey | +0.021 |
E | +0.021 |
Neg logit contributions | |
coc | -0.016 |
notebook | -0.015 |
goals | -0.014 |
goal | -0.014 |
book | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -4.68e-02 |
Pos logit contributions | |
Chick | +0.012 |
bo | +0.010 |
E | +0.010 |
Ch | +0.010 |
B | +0.010 |
Neg logit contributions | |
coc | -0.018 |
notebook | -0.017 |
trove | -0.016 |
stash | -0.016 |
goals | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
Chick | +0.001 |
E | +0.001 |
bo | +0.001 |
Ch | +0.001 |
him | +0.001 |
Neg logit contributions | |
notebook | -0.001 |
coc | -0.001 |
trove | -0.001 |
goals | -0.001 |
stash | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
Chick | +0.009 |
bo | +0.009 |
Ch | +0.009 |
E | +0.009 |
B | +0.008 |
Neg logit contributions | |
coc | -0.020 |
notebook | -0.020 |
goals | -0.019 |
trove | -0.018 |
stash | -0.018 |
Token | Wow |
Token ID | 22017 |
Feature activation | +4.86e-02 |
Pos logit contributions | |
Chick | +0.023 |
bo | +0.022 |
him | +0.021 |
hey | +0.020 |
lon | +0.020 |
Neg logit contributions | |
coc | -0.033 |
notebook | -0.031 |
goals | -0.030 |
poem | -0.030 |
goal | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.001 |
goals | +0.001 |
culture | +0.001 |
poem | +0.001 |
Neg logit contributions | |
Chick | -0.001 |
bo | -0.001 |
him | -0.001 |
hey | -0.001 |
head | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
Chick | +0.004 |
bo | +0.004 |
him | +0.004 |
hey | +0.004 |
E | +0.004 |
Neg logit contributions | |
coc | -0.006 |
notebook | -0.005 |
goals | -0.005 |
packs | -0.005 |
trove | -0.005 |
Token | sing |
Token ID | 1702 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
notebook | +0.039 |
coc | +0.039 |
packs | +0.038 |
stash | +0.037 |
goals | +0.036 |
Neg logit contributions | |
bo | -0.031 |
Chick | -0.031 |
hey | -0.029 |
Ch | -0.029 |
B | -0.029 |
Token | very |
Token ID | 845 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
stash | +0.020 |
trove | +0.019 |
rightful | +0.018 |
notebook | +0.018 |
ey | +0.018 |
Neg logit contributions | |
him | -0.008 |
them | -0.008 |
bo | -0.007 |
cl | -0.006 |
head | -0.006 |
Token | well |
Token ID | 880 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
notebook | +0.034 |
trove | +0.033 |
stash | +0.033 |
packs | +0.033 |
pad | +0.032 |
Neg logit contributions | |
bo | -0.022 |
E | -0.021 |
Chick | -0.021 |
him | -0.020 |
cl | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -3.34e-01 |
Pos logit contributions | |
bo | +0.011 |
head | +0.011 |
le | +0.010 |
him | +0.010 |
ly | +0.010 |
Neg logit contributions | |
ey | -0.023 |
notebook | -0.022 |
trove | -0.022 |
stash | -0.022 |
coc | -0.021 |
Token | Bird |
Token ID | 14506 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
B | +0.004 |
Chick | +0.003 |
him | +0.003 |
Baby | +0.003 |
Will | +0.003 |
Neg logit contributions | |
packs | -0.015 |
stash | -0.014 |
trove | -0.014 |
tal | -0.014 |
notebook | -0.014 |
Token | ! |
Token ID | 0 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
oral | +0.018 |
poem | +0.018 |
impressed | +0.018 |
culture | +0.018 |
coc | +0.018 |
Neg logit contributions | |
him | -0.012 |
bo | -0.011 |
B | -0.010 |
head | -0.009 |
Chick | -0.009 |
Token | รข |
Token ID | 22940 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
coc | +0.004 |
notebook | +0.004 |
goals | +0.004 |
book | +0.004 |
poem | +0.004 |
Neg logit contributions | |
Chick | -0.004 |
bo | -0.004 |
E | -0.003 |
B | -0.003 |
him | -0.003 |
Token | โฌ |
Token ID | 26391 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
coc | +0.032 |
notebook | +0.030 |
goals | +0.028 |
adow | +0.028 |
goal | +0.028 |
Neg logit contributions | |
Chick | -0.033 |
bo | -0.030 |
Ch | -0.030 |
E | -0.030 |
him | -0.030 |
Token | Joey |
Token ID | 26154 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
coc | +0.040 |
notebook | +0.039 |
goals | +0.036 |
poem | +0.035 |
culture | +0.034 |
Neg logit contributions | |
Chick | -0.038 |
bo | -0.038 |
B | -0.035 |
head | -0.035 |
him | -0.035 |
Token | said |
Token ID | 531 |
Feature activation | +6.17e-01 |
Pos logit contributions | |
bo | +0.001 |
Chick | +0.001 |
him | +0.001 |
B | +0.001 |
Baby | +0.001 |
Neg logit contributions | |
coc | -0.001 |
notebook | -0.001 |
packs | -0.001 |
culture | -0.001 |
goals | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
coc | +0.021 |
notebook | +0.020 |
packs | +0.019 |
trove | +0.019 |
goals | +0.019 |
Neg logit contributions | |
him | -0.012 |
Chick | -0.012 |
bo | -0.012 |
B | -0.012 |
Baby | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
coc | +0.018 |
notebook | +0.018 |
goals | +0.017 |
goal | +0.016 |
poem | +0.016 |
Neg logit contributions | |
Chick | -0.011 |
bo | -0.010 |
E | -0.009 |
B | -0.009 |
him | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
coc | +0.006 |
notebook | +0.005 |
goals | +0.005 |
goal | +0.005 |
trove | +0.005 |
Neg logit contributions | |
Chick | -0.005 |
bo | -0.005 |
Ch | -0.005 |
him | -0.005 |
E | -0.005 |
Token | His |
Token ID | 6653 |
Feature activation | +1.82e-03 |
Pos logit contributions | |
Chick | +0.003 |
bo | +0.003 |
Ch | +0.002 |
E | +0.002 |
him | +0.002 |
Neg logit contributions | |
coc | -0.004 |
notebook | -0.004 |
goals | -0.004 |
goal | -0.004 |
trove | -0.004 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
trove | +0.000 |
coc | +0.000 |
ours | +0.000 |
culture | +0.000 |
adow | +0.000 |
Neg logit contributions | |
Chick | -0.000 |
bo | -0.000 |
Baby | -0.000 |
him | -0.000 |
B | -0.000 |
Token | came |
Token ID | 1625 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
coc | +0.010 |
notebook | +0.010 |
goals | +0.009 |
goal | +0.009 |
packs | +0.009 |
Neg logit contributions | |
Chick | -0.010 |
bo | -0.010 |
Ch | -0.009 |
him | -0.009 |
E | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
him | +0.004 |
B | +0.003 |
bo | +0.003 |
them | +0.003 |
Chick | +0.003 |
Neg logit contributions | |
coc | -0.011 |
notebook | -0.010 |
ey | -0.010 |
tal | -0.010 |
culture | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Chick | +0.007 |
bo | +0.007 |
him | +0.007 |
Ch | +0.007 |
E | +0.007 |
Neg logit contributions | |
coc | -0.015 |
notebook | -0.015 |
goals | -0.014 |
trove | -0.013 |
poem | -0.013 |
Token | said |
Token ID | 531 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
him | +0.005 |
Chick | +0.005 |
B | +0.005 |
bo | +0.004 |
Ch | +0.004 |
Neg logit contributions | |
coc | -0.009 |
goals | -0.009 |
tal | -0.009 |
notebook | -0.009 |
goal | -0.008 |
Token | she |
Token ID | 673 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
coc | +0.011 |
trove | +0.011 |
notebook | +0.011 |
packs | +0.011 |
adow | +0.010 |
Neg logit contributions | |
him | -0.006 |
Chick | -0.006 |
B | -0.005 |
Baby | -0.005 |
head | -0.005 |
Token | should |
Token ID | 815 |
Feature activation | -8.62e-02 |
Pos logit contributions | |
coc | +0.012 |
notebook | +0.011 |
goals | +0.011 |
goal | +0.010 |
trove | +0.010 |
Neg logit contributions | |
bo | -0.010 |
Chick | -0.010 |
him | -0.010 |
Ch | -0.009 |
B | -0.009 |
Token | leave |
Token ID | 2666 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
Chick | +0.002 |
bo | +0.002 |
him | +0.002 |
Ch | +0.002 |
E | +0.002 |
Neg logit contributions | |
coc | -0.003 |
notebook | -0.002 |
goals | -0.002 |
trove | -0.002 |
goal | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
coc | +0.014 |
notebook | +0.013 |
goals | +0.013 |
goal | +0.013 |
poem | +0.013 |
Neg logit contributions | |
him | -0.007 |
Chick | -0.006 |
B | -0.006 |
bo | -0.006 |
Baby | -0.006 |
Token | wouldn |
Token ID | 3636 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
him | +0.003 |
Chick | +0.002 |
hey | +0.002 |
care | +0.002 |
Baby | +0.002 |
Neg logit contributions | |
coc | -0.007 |
trove | -0.006 |
goals | -0.006 |
tal | -0.006 |
notebook | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | +8.10e-01 |
Pos logit contributions | |
coc | +0.028 |
goal | +0.026 |
notebook | +0.026 |
goals | +0.025 |
speech | +0.025 |
Neg logit contributions | |
Chick | -0.014 |
bo | -0.013 |
Ch | -0.013 |
hey | -0.013 |
E | -0.012 |
Token | let |
Token ID | 1309 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
coc | +0.021 |
notebook | +0.020 |
goal | +0.019 |
statue | +0.018 |
goals | +0.018 |
Neg logit contributions | |
Chick | -0.021 |
Ch | -0.020 |
E | -0.019 |
bo | -0.018 |
lon | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
Chick | +0.022 |
bo | +0.022 |
Ch | +0.022 |
E | +0.021 |
head | +0.020 |
Neg logit contributions | |
coc | -0.034 |
notebook | -0.033 |
goals | -0.031 |
book | -0.031 |
goal | -0.030 |
Token | flying |
Token ID | 7348 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
him | +0.012 |
bo | +0.012 |
B | +0.011 |
Chick | +0.010 |
cl | +0.010 |
Neg logit contributions | |
notebook | -0.019 |
coc | -0.018 |
poem | -0.017 |
dictionary | -0.017 |
culture | -0.016 |
Token | across |
Token ID | 1973 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.001 |
ocket | +0.001 |
poem | +0.001 |
packs | +0.001 |
Neg logit contributions | |
him | -0.001 |
bo | -0.000 |
B | -0.000 |
head | -0.000 |
cl | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
coc | +0.048 |
notebook | +0.048 |
wrist | +0.045 |
ours | +0.045 |
goals | +0.045 |
Neg logit contributions | |
him | -0.029 |
B | -0.025 |
Chick | -0.024 |
head | -0.024 |
bo | -0.024 |
Token | waves |
Token ID | 9813 |
Feature activation | +6.76e-02 |
Pos logit contributions | |
notebook | +0.006 |
coc | +0.006 |
packs | +0.006 |
trove | +0.006 |
stash | +0.005 |
Neg logit contributions | |
bo | -0.006 |
Chick | -0.005 |
head | -0.005 |
him | -0.005 |
B | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
coc | +0.002 |
notebook | +0.002 |
goals | +0.002 |
culture | +0.002 |
packs | +0.002 |
Neg logit contributions | |
bo | -0.001 |
him | -0.001 |
Chick | -0.001 |
head | -0.001 |
B | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | -7.23e-02 |
Pos logit contributions | |
coc | +0.011 |
notebook | +0.010 |
culture | +0.010 |
trove | +0.010 |
poem | +0.010 |
Neg logit contributions | |
him | -0.004 |
Chick | -0.004 |
Baby | -0.004 |
bo | -0.003 |
B | -0.003 |
Token | felt |
Token ID | 2936 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
bo | +0.001 |
him | +0.001 |
B | +0.001 |
Ch | +0.001 |
cl | +0.001 |
Neg logit contributions | |
notebook | -0.003 |
coc | -0.002 |
ours | -0.002 |
dictionary | -0.002 |
journal | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
Chick | +0.009 |
bo | +0.009 |
him | +0.009 |
E | +0.009 |
Ch | +0.009 |
Neg logit contributions | |
coc | -0.010 |
notebook | -0.010 |
goals | -0.009 |
packs | -0.009 |
trove | -0.009 |
Token | happy |
Token ID | 3772 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
coc | +0.015 |
notebook | +0.015 |
goals | +0.013 |
book | +0.013 |
trove | +0.013 |
Neg logit contributions | |
bo | -0.018 |
Chick | -0.018 |
him | -0.017 |
E | -0.017 |
Ch | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
coc | +0.013 |
notebook | +0.013 |
goals | +0.013 |
packs | +0.012 |
goal | +0.012 |
Neg logit contributions | |
him | -0.009 |
head | -0.008 |
B | -0.008 |
Chick | -0.008 |
bo | -0.007 |
Token | faster |
Token ID | 5443 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
coc | +0.019 |
packs | +0.019 |
notebook | +0.019 |
stash | +0.018 |
ymes | +0.018 |
Neg logit contributions | |
him | -0.007 |
B | -0.006 |
Chick | -0.005 |
Baby | -0.005 |
Ethan | -0.005 |
Token | more |
Token ID | 517 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
notebook | +0.041 |
coc | +0.040 |
oral | +0.040 |
Statue | +0.039 |
trove | +0.038 |
Neg logit contributions | |
bo | -0.024 |
him | -0.023 |
care | -0.022 |
Chick | -0.022 |
B | -0.020 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
notebook | +0.034 |
Statue | +0.032 |
coc | +0.031 |
trove | +0.031 |
endant | +0.031 |
Neg logit contributions | |
Chick | -0.020 |
care | -0.019 |
him | -0.019 |
bo | -0.018 |
B | -0.018 |
Token | !" |
Token ID | 2474 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
him | +0.004 |
head | +0.003 |
when | +0.003 |
them | +0.002 |
sometimes | +0.002 |
Neg logit contributions | |
notebook | -0.010 |
ocket | -0.009 |
coc | -0.009 |
endant | -0.009 |
tal | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
coc | +0.015 |
trove | +0.015 |
goals | +0.015 |
stash | +0.015 |
notebook | +0.015 |
Neg logit contributions | |
him | -0.009 |
Chick | -0.008 |
bo | -0.008 |
B | -0.008 |
Baby | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -1.20e-01 |
Pos logit contributions | |
coc | +0.007 |
notebook | +0.007 |
trove | +0.006 |
goals | +0.006 |
packs | +0.006 |
Neg logit contributions | |
Chick | -0.004 |
bo | -0.004 |
him | -0.004 |
E | -0.004 |
Ch | -0.004 |
Token | Joe |
Token ID | 19585 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
E | +0.002 |
Ch | +0.002 |
B | +0.002 |
bo | +0.002 |
Chick | +0.002 |
Neg logit contributions | |
coc | -0.004 |
notebook | -0.004 |
goals | -0.004 |
packs | -0.004 |
stash | -0.004 |
Token | agreed |
Token ID | 4987 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
bo | +0.010 |
him | +0.008 |
cl | +0.008 |
Ch | +0.007 |
ny | +0.007 |
Neg logit contributions | |
coc | -0.013 |
ours | -0.013 |
notebook | -0.012 |
trove | -0.012 |
stash | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
coc | +0.044 |
notebook | +0.042 |
packs | +0.041 |
goals | +0.041 |
ours | +0.039 |
Neg logit contributions | |
him | -0.031 |
bo | -0.029 |
Chick | -0.028 |
B | -0.027 |
cl | -0.027 |
Token | so |
Token ID | 523 |
Feature activation | +3.78e-01 |
Pos logit contributions | |
coc | +0.041 |
notebook | +0.041 |
goals | +0.041 |
packs | +0.041 |
stash | +0.039 |
Neg logit contributions | |
B | -0.028 |
Baby | -0.028 |
Chick | -0.027 |
him | -0.027 |
bo | -0.026 |
Token | they |
Token ID | 484 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
coc | +0.016 |
notebook | +0.016 |
trove | +0.015 |
pad | +0.015 |
packs | +0.015 |
Neg logit contributions | |
him | -0.004 |
Chick | -0.004 |
bo | -0.003 |
B | -0.003 |
Baby | -0.003 |
Token | played |
Token ID | 2826 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
coc | +0.012 |
notebook | +0.012 |
goals | +0.012 |
goal | +0.011 |
territory | +0.011 |
Neg logit contributions | |
bo | -0.007 |
Chick | -0.007 |
him | -0.006 |
Ch | -0.006 |
B | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +2.00e-01 |
Pos logit contributions | |
Chick | +0.017 |
bo | +0.017 |
hey | +0.016 |
Ch | +0.016 |
E | +0.016 |
Neg logit contributions | |
coc | -0.011 |
notebook | -0.011 |
goals | -0.010 |
goal | -0.010 |
book | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +7.60e-01 |
Pos logit contributions | |
coc | +0.004 |
notebook | +0.004 |
goals | +0.004 |
goal | +0.004 |
book | +0.004 |
Neg logit contributions | |
bo | -0.006 |
Chick | -0.006 |
hey | -0.006 |
Ch | -0.006 |
head | -0.005 |
Token | little |
Token ID | 1310 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
coc | +0.017 |
notebook | +0.016 |
book | +0.015 |
statue | +0.015 |
goal | +0.014 |
Neg logit contributions | |
bo | -0.022 |
him | -0.022 |
Chick | -0.021 |
Ch | -0.020 |
hey | -0.020 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.61e-02 |
Pos logit contributions | |
bo | +0.003 |
Chick | +0.003 |
him | +0.003 |
Ch | +0.003 |
hey | +0.003 |
Neg logit contributions | |
coc | -0.002 |
notebook | -0.002 |
book | -0.002 |
statue | -0.002 |
goal | -0.001 |
Token | named |
Token ID | 3706 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
E | +0.001 |
hey | +0.001 |
head | +0.001 |
him | +0.001 |
Ethan | +0.001 |
Neg logit contributions | |
notebook | -0.001 |
coc | -0.001 |
book | -0.001 |
reading | -0.001 |
adow | -0.001 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
coc | +0.006 |
notebook | +0.005 |
goals | +0.005 |
book | +0.005 |
goal | +0.005 |
Neg logit contributions | |
bo | -0.003 |
Chick | -0.003 |
him | -0.003 |
Ch | -0.003 |
E | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
head | +0.006 |
Chick | +0.006 |
hey | +0.006 |
E | +0.006 |
Ch | +0.006 |
Neg logit contributions | |
notebook | -0.004 |
coc | -0.004 |
packs | -0.004 |
adow | -0.004 |
book | -0.004 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
bo | +0.010 |
hey | +0.010 |
lon | +0.009 |
him | +0.009 |
cl | +0.009 |
Neg logit contributions | |
coc | -0.010 |
notebook | -0.009 |
goals | -0.009 |
book | -0.009 |
goal | -0.009 |
Token | loved |
Token ID | 6151 |
Feature activation | -6.44e-01 |
Pos logit contributions | |
coc | +0.015 |
notebook | +0.015 |
goals | +0.014 |
book | +0.013 |
goal | +0.013 |
Neg logit contributions | |
Chick | -0.021 |
bo | -0.020 |
hey | -0.020 |
E | -0.020 |
head | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +2.98e-02 |
Pos logit contributions | |
Chick | +0.017 |
bo | +0.017 |
him | +0.016 |
Ch | +0.016 |
E | +0.016 |
Neg logit contributions | |
coc | -0.015 |
notebook | -0.015 |
goals | -0.014 |
trove | -0.014 |
goal | -0.014 |
Token | play |
Token ID | 711 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.001 |
goal | +0.001 |
poem | +0.001 |
book | +0.001 |
Neg logit contributions | |
bo | -0.001 |
Chick | -0.001 |
hey | -0.001 |
E | -0.001 |
Ch | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -2.01e-02 |
Pos logit contributions | |
bo | +0.001 |
him | +0.001 |
Chick | +0.001 |
B | +0.001 |
Baby | +0.001 |
Neg logit contributions | |
coc | -0.002 |
notebook | -0.002 |
packs | -0.002 |
ours | -0.002 |
trove | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | +5.99e-01 |
Pos logit contributions | |
Chick | +0.000 |
bo | +0.000 |
Ch | +0.000 |
E | +0.000 |
him | +0.000 |
Neg logit contributions | |
coc | -0.001 |
notebook | -0.001 |
goals | -0.001 |
goal | -0.001 |
trove | -0.001 |
Token | goose |
Token ID | 37246 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
notebook | +0.017 |
coc | +0.017 |
packs | +0.017 |
trove | +0.016 |
adow | +0.015 |
Neg logit contributions | |
bo | -0.014 |
him | -0.013 |
E | -0.013 |
Chick | -0.012 |
Baby | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
packs | +0.057 |
ours | +0.056 |
coc | +0.055 |
goals | +0.053 |
notebook | +0.052 |
Neg logit contributions | |
bo | -0.039 |
him | -0.034 |
B | -0.032 |
Chick | -0.031 |
rum | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
coc | +0.004 |
notebook | +0.004 |
goals | +0.003 |
goal | +0.003 |
trove | +0.003 |
Neg logit contributions | |
Chick | -0.003 |
bo | -0.003 |
him | -0.003 |
Ch | -0.003 |
E | -0.003 |
Token | |
Token ID | 220 |
Feature activation | +9.60e-02 |
Pos logit contributions | |
coc | +0.018 |
notebook | +0.017 |
packs | +0.016 |
goals | +0.016 |
goal | +0.015 |
Neg logit contributions | |
Chick | -0.020 |
him | -0.019 |
bo | -0.019 |
B | -0.019 |
Ch | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
notebook | +0.003 |
coc | +0.003 |
trove | +0.003 |
culture | +0.003 |
statue | +0.003 |
Neg logit contributions | |
him | -0.002 |
Chick | -0.002 |
bo | -0.002 |
B | -0.001 |
E | -0.001 |
Token | It |
Token ID | 1026 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
Chick | +0.014 |
bo | +0.013 |
him | +0.013 |
hey | +0.012 |
Ch | +0.012 |
Neg logit contributions | |
coc | -0.020 |
notebook | -0.020 |
goals | -0.019 |
goal | -0.018 |
poem | -0.018 |
Token | means |
Token ID | 1724 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
bo | +0.008 |
Chick | +0.008 |
him | +0.007 |
B | +0.007 |
hey | +0.006 |
Neg logit contributions | |
coc | -0.012 |
notebook | -0.011 |
trove | -0.010 |
packs | -0.010 |
goals | -0.010 |
Token | that |
Token ID | 326 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
coc | +0.015 |
notebook | +0.015 |
trove | +0.014 |
pad | +0.014 |
packs | +0.014 |
Neg logit contributions | |
him | -0.008 |
B | -0.007 |
Chick | -0.006 |
Baby | -0.006 |
Pe | -0.006 |
Token | we |
Token ID | 356 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
trove | +0.018 |
coc | +0.018 |
notebook | +0.018 |
stash | +0.017 |
endant | +0.017 |
Neg logit contributions | |
him | -0.010 |
B | -0.009 |
Chick | -0.009 |
bo | -0.008 |
Baby | -0.008 |
Token | An |
Token ID | 2025 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Chick | +0.022 |
bo | +0.019 |
him | +0.019 |
hey | +0.019 |
ick | +0.019 |
Neg logit contributions | |
coc | -0.026 |
notebook | -0.026 |
pad | -0.023 |
goal | -0.023 |
trove | -0.023 |
Token | olive |
Token ID | 19450 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
Chick | +0.032 |
bo | +0.031 |
E | +0.031 |
B | +0.030 |
head | +0.029 |
Neg logit contributions | |
coc | -0.019 |
notebook | -0.018 |
packs | -0.017 |
trove | -0.017 |
goals | -0.017 |
Token | in |
Token ID | 287 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
packs | +0.041 |
pleased | +0.041 |
ushes | +0.040 |
impressed | +0.040 |
former | +0.039 |
Neg logit contributions | |
him | -0.025 |
bo | -0.023 |
head | -0.023 |
Chick | -0.022 |
B | -0.022 |
Token | the |
Token ID | 262 |
Feature activation | +3.17e-01 |
Pos logit contributions | |
coc | +0.028 |
notebook | +0.027 |
pad | +0.027 |
goals | +0.027 |
adow | +0.026 |
Neg logit contributions | |
Chick | -0.021 |
him | -0.020 |
bo | -0.020 |
head | -0.019 |
B | -0.019 |
Token | forest |
Token ID | 8222 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
coc | +0.007 |
packs | +0.007 |
goals | +0.006 |
impressed | +0.006 |
notebook | +0.006 |
Neg logit contributions | |
bo | -0.009 |
Chick | -0.009 |
him | -0.009 |
B | -0.008 |
B | -0.008 |
Token | ? |
Token ID | 30 |
Feature activation | -7.74e-02 |
Pos logit contributions | |
him | +0.010 |
head | +0.009 |
B | +0.008 |
hey | +0.008 |
bo | +0.008 |
Neg logit contributions | |
coc | -0.019 |
tal | -0.017 |
notebook | -0.017 |
poem | -0.017 |
bookmark | -0.017 |
Token | That |
Token ID | 1320 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
Chick | +0.002 |
bo | +0.002 |
E | +0.002 |
Ch | +0.002 |
B | +0.002 |
Neg logit contributions | |
coc | -0.002 |
notebook | -0.002 |
goals | -0.002 |
packs | -0.002 |
stash | -0.002 |
Token | 's |
Token ID | 338 |
Feature activation | -3.99e-02 |
Pos logit contributions | |
packs | +0.061 |
pleased | +0.057 |
adow | +0.056 |
aj | +0.056 |
ushes | +0.055 |
Neg logit contributions | |
Chick | -0.047 |
bo | -0.047 |
B | -0.047 |
him | -0.047 |
Mitt | -0.042 |
Token | so |
Token ID | 523 |
Feature activation | +9.86e-01 |
Pos logit contributions | |
Chick | +0.001 |
him | +0.001 |
B | +0.001 |
bo | +0.001 |
Pe | +0.001 |
Neg logit contributions | |
packs | -0.001 |
coc | -0.001 |
notebook | -0.001 |
goal | -0.001 |
goals | -0.001 |
Token | unusual |
Token ID | 8468 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
coc | +0.023 |
notebook | +0.022 |
packs | +0.020 |
goals | +0.020 |
trove | +0.019 |
Neg logit contributions | |
Chick | -0.027 |
bo | -0.027 |
E | -0.026 |
him | -0.026 |
Ch | -0.025 |
Token | !" |
Token ID | 2474 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
coc | +0.008 |
notebook | +0.008 |
packs | +0.008 |
wrist | +0.008 |
pleased | +0.008 |
Neg logit contributions | |
him | -0.007 |
head | -0.006 |
Chick | -0.006 |
B | -0.006 |
Bobby | -0.006 |
Token | o |
Token ID | 267 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
bo | +0.006 |
him | +0.006 |
B | +0.005 |
B | +0.005 |
cl | +0.005 |
Neg logit contributions | |
coc | -0.007 |
packs | -0.007 |
notebook | -0.007 |
trove | -0.007 |
ocket | -0.007 |
Token | asis |
Token ID | 17765 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
coc | +0.033 |
notebook | +0.031 |
goals | +0.029 |
goal | +0.027 |
poem | +0.027 |
Neg logit contributions | |
bo | -0.042 |
Chick | -0.040 |
Ch | -0.038 |
him | -0.038 |
head | -0.038 |
Token | until |
Token ID | 1566 |
Feature activation | -9.00e-01 |
Pos logit contributions | |
coc | +0.022 |
notebook | +0.020 |
poem | +0.020 |
dictionary | +0.020 |
bookmark | +0.019 |
Neg logit contributions | |
him | -0.009 |
bo | -0.008 |
cl | -0.007 |
head | -0.007 |
ick | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
him | +0.014 |
B | +0.012 |
Chick | +0.011 |
bo | +0.011 |
Baby | +0.011 |
Neg logit contributions | |
coc | -0.034 |
notebook | -0.033 |
goals | -0.033 |
poem | -0.032 |
trove | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -5.85e-01 |
Pos logit contributions | |
bo | +0.023 |
Chick | +0.020 |
him | +0.020 |
cl | +0.019 |
B | +0.019 |
Neg logit contributions | |
coc | -0.035 |
notebook | -0.035 |
ours | -0.034 |
dictionary | -0.033 |
goals | -0.033 |
Token | time |
Token ID | 640 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
him | +0.009 |
Chick | +0.009 |
bo | +0.008 |
Baby | +0.008 |
B | +0.008 |
Neg logit contributions | |
notebook | -0.021 |
coc | -0.020 |
Statue | -0.020 |
dictionary | -0.020 |
wrist | -0.020 |
Token | for |
Token ID | 329 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
him | +0.033 |
them | +0.022 |
B | +0.019 |
bo | +0.019 |
ick | +0.019 |
Neg logit contributions | |
coc | -0.080 |
Statue | -0.076 |
goals | -0.075 |
languages | -0.074 |
ymes | -0.073 |
Token | her |
Token ID | 607 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
him | +0.003 |
Chick | +0.003 |
B | +0.003 |
Baby | +0.003 |
bo | +0.002 |
Neg logit contributions | |
notebook | -0.004 |
coc | -0.004 |
goals | -0.004 |
packs | -0.004 |
goal | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
him | +0.031 |
Chick | +0.029 |
B | +0.028 |
Baby | +0.028 |
bo | +0.028 |
Neg logit contributions | |
trove | -0.042 |
goals | -0.042 |
coc | -0.041 |
ey | -0.041 |
ushes | -0.040 |
Token | go |
Token ID | 467 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
him | +0.005 |
bo | +0.005 |
Chick | +0.004 |
B | +0.004 |
Baby | +0.004 |
Neg logit contributions | |
coc | -0.014 |
notebook | -0.014 |
goals | -0.013 |
culture | -0.013 |
trove | -0.013 |
Token | home |
Token ID | 1363 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
Chick | +0.014 |
bo | +0.014 |
him | +0.013 |
B | +0.013 |
Ch | +0.013 |
Neg logit contributions | |
coc | -0.009 |
notebook | -0.008 |
goals | -0.008 |
goal | -0.007 |
poem | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
coc | +0.035 |
notebook | +0.034 |
goals | +0.032 |
goal | +0.031 |
book | +0.030 |
Neg logit contributions | |
Chick | -0.037 |
bo | -0.037 |
Ch | -0.035 |
E | -0.035 |
him | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
bo | +0.066 |
E | +0.064 |
Ch | +0.063 |
Chick | +0.063 |
Wh | +0.061 |
Neg logit contributions | |
book | -0.021 |
notebook | -0.020 |
reading | -0.018 |
goal | -0.018 |
friends | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.05e-02 |
Pos logit contributions | |
notebook | +0.012 |
coc | +0.012 |
book | +0.011 |
goals | +0.011 |
goal | +0.011 |
Neg logit contributions | |
bo | -0.014 |
Chick | -0.013 |
Ch | -0.012 |
E | -0.012 |
hey | -0.012 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
notebook | +0.000 |
coc | +0.000 |
goals | +0.000 |
book | +0.000 |
goal | +0.000 |
Neg logit contributions | |
Chick | -0.000 |
bo | -0.000 |
Ch | -0.000 |
E | -0.000 |
him | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -6.67e-01 |
Pos logit contributions | |
bo | +0.002 |
Chick | +0.002 |
him | +0.002 |
B | +0.002 |
head | +0.002 |
Neg logit contributions | |
coc | -0.003 |
goals | -0.003 |
notebook | -0.003 |
goal | -0.003 |
trove | -0.003 |
Token | dad |
Token ID | 9955 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
bo | +0.024 |
Chick | +0.023 |
Ch | +0.022 |
E | +0.022 |
cl | +0.021 |
Neg logit contributions | |
notebook | -0.011 |
coc | -0.010 |
book | -0.009 |
goals | -0.009 |
backpack | -0.009 |
Token | were |
Token ID | 547 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
Chick | +0.041 |
bo | +0.041 |
him | +0.037 |
Ch | +0.037 |
E | +0.037 |
Neg logit contributions | |
coc | -0.068 |
notebook | -0.066 |
goals | -0.062 |
goal | -0.060 |
trove | -0.060 |
Token | very |
Token ID | 845 |
Feature activation | +7.34e-01 |
Pos logit contributions | |
Chick | +0.028 |
bo | +0.027 |
him | +0.026 |
hey | +0.026 |
Ch | +0.026 |
Neg logit contributions | |
coc | -0.028 |
notebook | -0.027 |
goals | -0.025 |
goal | -0.024 |
trove | -0.024 |
Token | angry |
Token ID | 7954 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
coc | +0.016 |
notebook | +0.016 |
goals | +0.014 |
goal | +0.014 |
trove | +0.014 |
Neg logit contributions | |
Chick | -0.021 |
bo | -0.021 |
Ch | -0.020 |
him | -0.020 |
E | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | -3.49e-01 |
Pos logit contributions | |
coc | +0.017 |
notebook | +0.016 |
trove | +0.015 |
stash | +0.015 |
goal | +0.015 |
Neg logit contributions | |
him | -0.011 |
Chick | -0.010 |
bo | -0.010 |
head | -0.010 |
B | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -9.67e-01 |
Pos logit contributions | |
bo | +0.010 |
Chick | +0.009 |
Ch | +0.009 |
E | +0.009 |
head | +0.009 |
Neg logit contributions | |
coc | -0.008 |
notebook | -0.008 |
goals | -0.008 |
book | -0.007 |
ours | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -9.43e-01 |
Pos logit contributions | |
coc | +0.044 |
trove | +0.043 |
notebook | +0.043 |
Statue | +0.042 |
adow | +0.042 |
Neg logit contributions | |
him | -0.027 |
bo | -0.023 |
Chick | -0.022 |
B | -0.022 |
care | -0.021 |
Token | frown |
Token ID | 22002 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
Chick | +0.020 |
bo | +0.018 |
Baby | +0.018 |
B | +0.018 |
bang | +0.017 |
Neg logit contributions | |
adow | -0.026 |
coc | -0.026 |
goals | -0.025 |
packs | -0.025 |
aces | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
coc | +0.005 |
notebook | +0.004 |
culture | +0.004 |
goals | +0.004 |
trove | +0.004 |
Neg logit contributions | |
him | -0.003 |
bo | -0.003 |
head | -0.003 |
Chick | -0.003 |
B | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
him | +0.004 |
Chick | +0.004 |
B | +0.004 |
bo | +0.003 |
Baby | +0.003 |
Neg logit contributions | |
coc | -0.009 |
adow | -0.008 |
trove | -0.008 |
oral | -0.008 |
goals | -0.008 |
Token | loud |
Token ID | 7812 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
Chick | +0.010 |
bo | +0.010 |
Ch | +0.009 |
numb | +0.009 |
B | +0.009 |
Neg logit contributions | |
adow | -0.014 |
goals | -0.014 |
coc | -0.013 |
packs | -0.013 |
ours | -0.013 |
Token | voice |
Token ID | 3809 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
bo | +0.012 |
Chick | +0.012 |
him | +0.012 |
head | +0.011 |
Ch | +0.011 |
Neg logit contributions | |
coc | -0.014 |
notebook | -0.013 |
goals | -0.013 |
packs | -0.012 |
trove | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
bo | +0.067 |
Chick | +0.066 |
him | +0.063 |
Ch | +0.061 |
head | +0.060 |
Neg logit contributions | |
coc | -0.090 |
notebook | -0.086 |
goals | -0.081 |
goal | -0.079 |
trove | -0.077 |
Token |
|
Token ID | 198 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
Chick | +0.017 |
bo | +0.017 |
him | +0.016 |
Ch | +0.016 |
E | +0.016 |
Neg logit contributions | |
coc | -0.027 |
notebook | -0.026 |
goals | -0.024 |
trove | -0.024 |
goal | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -4.98e-01 |
Pos logit contributions | |
coc | +0.001 |
notebook | +0.000 |
goals | +0.000 |
goal | +0.000 |
book | +0.000 |
Neg logit contributions | |
Chick | -0.001 |
bo | -0.001 |
hey | -0.001 |
head | -0.001 |
Ch | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | -9.63e-01 |
Pos logit contributions | |
Chick | +0.016 |
bo | +0.016 |
him | +0.015 |
hey | +0.015 |
Baby | +0.015 |
Neg logit contributions | |
coc | -0.009 |
notebook | -0.008 |
goals | -0.007 |
book | -0.007 |
goal | -0.007 |
Token | What |
Token ID | 2061 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
Chick | +0.018 |
bo | +0.017 |
him | +0.015 |
ick | +0.015 |
Baby | +0.015 |
Neg logit contributions | |
coc | -0.031 |
notebook | -0.030 |
goals | -0.028 |
statue | -0.028 |
book | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
coc | +0.026 |
notebook | +0.026 |
trove | +0.025 |
goals | +0.024 |
stash | +0.024 |
Neg logit contributions | |
Chick | -0.020 |
bo | -0.019 |
him | -0.019 |
Ch | -0.019 |
E | -0.019 |
Token | big |
Token ID | 1263 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
Chick | +0.017 |
B | +0.015 |
Baby | +0.015 |
E | +0.014 |
bo | +0.014 |
Neg logit contributions | |
coc | -0.020 |
packs | -0.020 |
goals | -0.019 |
trove | -0.019 |
adow | -0.019 |
Token | heart |
Token ID | 2612 |
Feature activation | -7.33e-01 |
Pos logit contributions | |
B | +0.005 |
Baby | +0.005 |
him | +0.005 |
Chick | +0.005 |
rum | +0.005 |
Neg logit contributions | |
ushes | -0.007 |
ymes | -0.007 |
shadow | -0.007 |
impressed | -0.007 |
coc | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
bo | +0.011 |
Chick | +0.011 |
head | +0.009 |
cl | +0.009 |
Ch | +0.009 |
Neg logit contributions | |
coc | -0.026 |
goals | -0.025 |
ours | -0.024 |
Statue | -0.024 |
hasn | -0.024 |
Token | Every |
Token ID | 3887 |
Feature activation | -9.02e-03 |
Pos logit contributions | |
coc | +0.003 |
notebook | +0.003 |
goals | +0.003 |
book | +0.003 |
packs | +0.003 |
Neg logit contributions | |
bo | -0.003 |
Chick | -0.003 |
hey | -0.003 |
head | -0.002 |
E | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
bo | +0.000 |
Chick | +0.000 |
him | +0.000 |
head | +0.000 |
Ch | +0.000 |
Neg logit contributions | |
coc | -0.000 |
trove | -0.000 |
notebook | -0.000 |
goals | -0.000 |
ours | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
bo | +0.091 |
E | +0.085 |
lon | +0.085 |
hey | +0.081 |
B | +0.080 |
Neg logit contributions | |
book | -0.032 |
notebook | -0.026 |
packs | -0.025 |
reading | -0.025 |
gate | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
notebook | +0.007 |
coc | +0.007 |
book | +0.007 |
packs | +0.006 |
goals | +0.006 |
Neg logit contributions | |
bo | -0.007 |
Chick | -0.006 |
E | -0.006 |
hey | -0.006 |
lon | -0.006 |
Token | would |
Token ID | 561 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
coc | +0.007 |
notebook | +0.007 |
goals | +0.006 |
trove | +0.006 |
goal | +0.006 |
Neg logit contributions | |
Chick | -0.005 |
bo | -0.005 |
Ch | -0.004 |
him | -0.004 |
B | -0.004 |
Token | sing |
Token ID | 1702 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
coc | +0.026 |
notebook | +0.025 |
goals | +0.024 |
trove | +0.024 |
packs | +0.023 |
Neg logit contributions | |
Chick | -0.012 |
bo | -0.012 |
him | -0.011 |
Ch | -0.011 |
hey | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
coc | +0.007 |
stash | +0.007 |
trove | +0.007 |
tal | +0.007 |
notebook | +0.007 |
Neg logit contributions | |
him | -0.004 |
Chick | -0.003 |
Ch | -0.003 |
them | -0.003 |
B | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -5.48e-02 |
Pos logit contributions | |
coc | +0.008 |
notebook | +0.008 |
goals | +0.008 |
goal | +0.007 |
packs | +0.007 |
Neg logit contributions | |
bo | -0.006 |
Chick | -0.005 |
him | -0.005 |
head | -0.005 |
Ch | -0.005 |
Token | made |
Token ID | 925 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
Chick | +0.001 |
him | +0.001 |
B | +0.001 |
Baby | +0.001 |
head | +0.001 |
Neg logit contributions | |
coc | -0.002 |
adow | -0.002 |
goal | -0.002 |
trove | -0.002 |
goals | -0.002 |
Token | z |
Token ID | 1976 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
Chick | +0.024 |
bo | +0.024 |
Ch | +0.023 |
E | +0.022 |
him | +0.022 |
Neg logit contributions | |
coc | -0.024 |
notebook | -0.023 |
goals | -0.022 |
goal | -0.021 |
book | -0.020 |
Token | ooming |
Token ID | 30602 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
notebook | +0.019 |
coc | +0.019 |
goals | +0.018 |
adow | +0.017 |
packs | +0.017 |
Neg logit contributions | |
Chick | -0.022 |
bo | -0.021 |
E | -0.020 |
Ch | -0.020 |
B | -0.020 |
Token | noises |
Token ID | 26782 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
him | +0.042 |
Chick | +0.041 |
bo | +0.041 |
head | +0.038 |
Ch | +0.038 |
Neg logit contributions | |
notebook | -0.051 |
coc | -0.051 |
trove | -0.047 |
adow | -0.046 |
stash | -0.046 |
Token | as |
Token ID | 355 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
Chick | +0.063 |
bo | +0.062 |
E | +0.059 |
Ch | +0.058 |
hey | +0.057 |
Neg logit contributions | |
coc | -0.064 |
notebook | -0.061 |
goals | -0.058 |
book | -0.056 |
goal | -0.055 |
Token | she |
Token ID | 673 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
Chick | +0.039 |
him | +0.034 |
head | +0.033 |
Ch | +0.033 |
B | +0.032 |
Neg logit contributions | |
coc | -0.069 |
notebook | -0.066 |
tal | -0.065 |
goal | -0.064 |
trove | -0.064 |
Token | moved |
Token ID | 3888 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
coc | +0.006 |
notebook | +0.006 |
goals | +0.006 |
ours | +0.006 |
goal | +0.006 |
Neg logit contributions | |
Chick | -0.004 |
bo | -0.004 |
Ch | -0.004 |
him | -0.004 |
B | -0.004 |
Token | it |
Token ID | 340 |
Feature activation | -3.87e-01 |
Pos logit contributions | |
him | +0.025 |
Chick | +0.025 |
bo | +0.025 |
B | +0.023 |
Ch | +0.023 |
Neg logit contributions | |
coc | -0.036 |
notebook | -0.036 |
trove | -0.034 |
goals | -0.033 |
stash | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | +3.09e-01 |
Pos logit contributions | |
him | +0.007 |
bo | +0.007 |
Chick | +0.006 |
Ch | +0.006 |
cl | +0.006 |
Neg logit contributions | |
coc | -0.013 |
notebook | -0.012 |
Statue | -0.012 |
culture | -0.012 |
pleased | -0.012 |
Token | their |
Token ID | 511 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
notebook | +0.010 |
coc | +0.010 |
packs | +0.009 |
trove | +0.009 |
pleased | +0.009 |
Neg logit contributions | |
him | -0.006 |
Chick | -0.006 |
B | -0.005 |
Ch | -0.005 |
bo | -0.005 |