TOP ACTIVATIONS
MAX = 3.847

closer and closer , but the fog was too thick .
. Suddenly , the fog began to move away
thought , and then the organized friend had an idea .
Ben agreed and soon the two of them were walking
! He even showed his new friends how to do them
was surprised and wondered how the all igator could talk .
of them . The fog was gone , and
! The new all igator said , "
nodded and watched carefully as the grown up stretched her arms
a little girl named Lu . She was three years old
Can I use it ?" asked Lucy . "
bright fan . Joe wanted the fan too , and so
today ?" Mr . Sun smiled and said ,
was excited to have a new one . " I hope
. " Do you like the stairs ?" "
Sam and Lucy . Sam and Lucy loved to play together
able . And they liked the fog . It made their
One day , Sam and Lucy went to the park
curious little cat named Kitty . Kitty loved to play and
happy that he had a new bed to sleep in .

MIN ACTIVATIONS
MIN = -4.363

a nap . One day , Gro ver decided he wanted
found a brilliant skirt in Lily 's closet . It was
the beach . But first , he had to pack !
what to do . But then , a kind
pumpkin friends . One day , a big , mean squash
a fair peanut . It looked so tasty that a lion
big ocean . One day , P inch y met a
eating bamboo . One day , P andy met a rabbit
every day . One day , while Av a was playing
to eat . One day , P ingu was feeling tired
saw a new toy in Lily 's part . It was
From that day on , Jolly and his friends were
make funny noises . So , he kept rubbing and rubbing
a break . One day , his friend Sammy came over
was a big card with a picture of a rainbow .
chase Jolly and his friends . They were scared and didn
's purse . It has a picture of his mom and
card on the floor . The card had a big ,
a big ice cream in Ben 's hand and a new
puts a shiny sticker on Ben 's folder . Ben feels

INTERVAL 1.794 - 3.847
CONTAINS 0.519%

itty never delayed playing with the jar again . <|endoftext|> Once
big bathroom . A family of ducks lived in this house
steep . They try to go up the hill . But
So , Sophia and Mom my went home . The
him scared . He quickly went back inside and wrapped himself

INTERVAL -0.258 - 1.794
CONTAINS 63.946%

for the fun afternoon . He then bid farewell to all
Mom my said , " No , it 's
, I can see something shiny on the other side ."
The laser hits the cat . The cat makes a loud
as fun as the old one . They learned that sometimes

INTERVAL -2.311 - -0.258
CONTAINS 35.381%

cup ine !" said Lily . The por cup ine said
of the visit , the doctor opened two pieces of paper
touch it or it will break ." M ia
adventure . He found a peaceful case deep in the woods
. He asked what they were having for dinner and Lily

INTERVAL -4.363 - -2.311
CONTAINS 0.154%

up the mess they made . The boys
was going away . At first , Ben was
. It made the salad look wet , but it tasted
She picks a card with a cat on it . She
of fun . Rachel was so happy that
Token closer
Token ID5699
Feature activation+7.71e-01

Pos logit contributions
 Lu+0.073
Ann+0.067
Lu+0.065
 angels+0.065
 pastor+0.063
Neg logit contributions
ret-0.044
orse-0.040
ets-0.040
 peanut-0.038
sel-0.037
Token and
Token ID290
Feature activation-5.65e-01

Pos logit contributions
 Lu+0.042
Ann+0.035
Lu+0.035
 firefighters+0.035
 angels+0.035
Neg logit contributions
ret-0.025
orse-0.025
orses-0.022
ets-0.021
 peanut-0.020
Token closer
Token ID5699
Feature activation+2.46e-01

Pos logit contributions
ret+0.026
orse+0.026
orses+0.025
 peanut+0.023
ets+0.022
Neg logit contributions
 Lu-0.025
 angels-0.019
Ann-0.019
Lu-0.019
 firefighters-0.018
Token,
Token ID11
Feature activation-4.63e-01

Pos logit contributions
 Lu+0.013
 angels+0.010
Ann+0.010
Lu+0.010
 firefighters+0.010
Neg logit contributions
ret-0.009
orse-0.009
orses-0.008
 peanut-0.008
ets-0.007
Token but
Token ID475
Feature activation+2.52e-01

Pos logit contributions
ret+0.020
orse+0.020
orses+0.019
 peanut+0.018
ets+0.017
Neg logit contributions
 Lu-0.021
 angels-0.017
Ann-0.016
 firefighters-0.016
Lu-0.016
Token the
Token ID262
Feature activation+3.85e+00

Pos logit contributions
 Lu+0.013
 angels+0.011
Ann+0.011
Lu+0.011
 firefighters+0.011
Neg logit contributions
ret-0.009
orse-0.008
orses-0.008
 peanut-0.007
ets-0.007
Token fog
Token ID19558
Feature activation+6.82e-01

Pos logit contributions
ussy+0.175
whe+0.175
ators+0.165
jack+0.160
beh+0.160
Neg logit contributions
 holes-0.099
 middle-0.086
 long-0.086
 it-0.083
 shell-0.083
Token was
Token ID373
Feature activation+2.17e+00

Pos logit contributions
 Lu+0.035
 angels+0.029
 youths+0.029
Lu+0.028
Ann+0.028
Neg logit contributions
ret-0.025
orse-0.025
orses-0.022
ork-0.021
 peanut-0.021
Token too
Token ID1165
Feature activation+1.13e+00

Pos logit contributions
 Lu+0.108
 youths+0.096
Ann+0.094
 angels+0.094
 Taxi+0.092
Neg logit contributions
orse-0.066
 peanut-0.065
ret-0.062
ifying-0.060
 accidentally-0.058
Token thick
Token ID6546
Feature activation+2.94e-01

Pos logit contributions
 Lu+0.062
 angels+0.055
Ann+0.052
 youths+0.051
ators+0.050
Neg logit contributions
ret-0.035
orse-0.034
 peanut-0.031
orses-0.030
ork-0.030
Token.
Token ID13
Feature activation+1.59e-01

Pos logit contributions
 Lu+0.015
 angels+0.012
Ann+0.012
Lu+0.012
 firefighters+0.012
Neg logit contributions
ret-0.011
orse-0.011
orses-0.010
ets-0.009
 peanut-0.009
Token.
Token ID13
Feature activation+1.68e-01

Pos logit contributions
ret+0.005
orse+0.004
orses+0.004
 peanut+0.004
ets+0.004
Neg logit contributions
 Lu-0.005
 angels-0.004
Ann-0.004
Lu-0.004
 firefighters-0.004
Token
Token ID198
Feature activation+6.73e-01

Pos logit contributions
 Lu+0.009
 angels+0.007
Ann+0.007
Lu+0.007
 firefighters+0.007
Neg logit contributions
ret-0.006
orse-0.006
orses-0.006
 peanut-0.005
ets-0.005
Token
Token ID198
Feature activation+2.22e-01

Pos logit contributions
 Lu+0.035
 angels+0.031
 firefighters+0.030
 youths+0.029
Ann+0.028
Neg logit contributions
ret-0.023
orse-0.023
orses-0.021
ork-0.019
 peanut-0.018
TokenSuddenly
Token ID38582
Feature activation+7.72e-01

Pos logit contributions
 Lu+0.012
 angels+0.010
 firefighters+0.009
Ann+0.009
 youths+0.009
Neg logit contributions
ret-0.008
orse-0.008
orses-0.007
 peanut-0.007
ets-0.006
Token,
Token ID11
Feature activation+8.56e-01

Pos logit contributions
 Lu+0.045
Ann+0.039
Lu+0.038
 angels+0.038
co+0.038
Neg logit contributions
ret-0.022
orse-0.021
orses-0.019
 peanut-0.017
ork-0.016
Token the
Token ID262
Feature activation+3.82e+00

Pos logit contributions
 Lu+0.046
Ann+0.040
co+0.040
 angels+0.039
Lu+0.039
Neg logit contributions
ret-0.026
orse-0.025
orses-0.022
 peanut-0.022
sel-0.020
Token fog
Token ID19558
Feature activation+3.00e-01

Pos logit contributions
ussy+0.178
whe+0.174
beh+0.165
 Lu+0.162
ators+0.160
Neg logit contributions
 holes-0.085
 long-0.080
 sudden-0.078
 middle-0.078
 shell-0.077
Token began
Token ID2540
Feature activation+5.82e-01

Pos logit contributions
 Lu+0.016
 angels+0.013
Ann+0.013
Lu+0.013
 youths+0.013
Neg logit contributions
orse-0.011
ret-0.011
orses-0.010
 peanut-0.009
ets-0.009
Token to
Token ID284
Feature activation+1.61e+00

Pos logit contributions
 Lu+0.029
Ann+0.024
Lu+0.024
 angels+0.024
 youths+0.023
Neg logit contributions
orse-0.022
ret-0.021
orses-0.020
 peanut-0.019
ork-0.018
Token move
Token ID1445
Feature activation+1.03e+00

Pos logit contributions
 Lu+0.083
Ann+0.072
 youths+0.072
Lu+0.072
 Barber+0.069
Neg logit contributions
orse-0.052
ret-0.047
 peanut-0.046
orses-0.045
sel-0.040
Token away
Token ID1497
Feature activation+1.02e+00

Pos logit contributions
 Lu+0.055
 angels+0.047
Ann+0.046
Lu+0.045
 Barber+0.045
Neg logit contributions
ret-0.033
orse-0.030
ets-0.028
orses-0.028
ork-0.027
Token thought
Token ID1807
Feature activation-5.56e-01

Pos logit contributions
ret+0.002
orse+0.002
orses+0.001
 peanut+0.001
ets+0.001
Neg logit contributions
 Lu-0.002
 angels-0.002
Ann-0.001
Lu-0.001
 firefighters-0.001
Token,
Token ID11
Feature activation-5.68e-01

Pos logit contributions
ret+0.024
orse+0.023
orses+0.022
 peanut+0.021
ets+0.020
Neg logit contributions
 Lu-0.026
 angels-0.021
 firefighters-0.020
Lu-0.019
Ann-0.019
Token and
Token ID290
Feature activation-2.92e-01

Pos logit contributions
ret+0.025
orse+0.025
orses+0.023
 peanut+0.022
ocket+0.022
Neg logit contributions
 Lu-0.026
 angels-0.021
 firefighters-0.020
Ann-0.020
Lu-0.020
Token then
Token ID788
Feature activation+1.80e-01

Pos logit contributions
ret+0.013
orse+0.012
orses+0.012
ets+0.011
 peanut+0.011
Neg logit contributions
 Lu-0.013
 angels-0.011
 firefighters-0.010
Ann-0.010
Lu-0.010
Token the
Token ID262
Feature activation+2.72e+00

Pos logit contributions
 Lu+0.010
 angels+0.008
Ann+0.008
Lu+0.008
 firefighters+0.008
Neg logit contributions
ret-0.006
orse-0.006
orses-0.006
 peanut-0.005
ets-0.005
Token organized
Token ID8389
Feature activation+3.66e+00

Pos logit contributions
 Lu+0.140
ators+0.119
Ann+0.116
 Stev+0.115
lo+0.113
Neg logit contributions
 peanut-0.088
 tomato-0.079
orse-0.076
 pen-0.074
 mouth-0.072
Token friend
Token ID1545
Feature activation-6.25e-01

Pos logit contributions
 Lu+0.153
Michael+0.153
Mark+0.152
 mercy+0.150
Ann+0.150
Neg logit contributions
's-0.102
 tomato-0.097
 mouth-0.092
 peanut-0.090
 picture-0.089
Token had
Token ID550
Feature activation-8.01e-02

Pos logit contributions
ret+0.025
orse+0.024
orses+0.023
ets+0.021
 peanut+0.020
Neg logit contributions
 Lu-0.031
 angels-0.025
Lu-0.025
Ann-0.025
 firefighters-0.025
Token an
Token ID281
Feature activation+1.81e+00

Pos logit contributions
ret+0.003
orse+0.003
orses+0.003
 peanut+0.003
ets+0.003
Neg logit contributions
 Lu-0.004
 angels-0.003
Ann-0.003
Lu-0.003
 firefighters-0.003
Token idea
Token ID2126
Feature activation+2.33e-01

Pos logit contributions
 Lu+0.080
Ann+0.072
 angels+0.069
Lu+0.068
Michael+0.063
Neg logit contributions
ret-0.076
orse-0.075
 peanut-0.071
ets-0.067
ocket-0.065
Token.
Token ID13
Feature activation-2.25e-01

Pos logit contributions
 Lu+0.012
 angels+0.010
Ann+0.009
Lu+0.009
 firefighters+0.009
Neg logit contributions
ret-0.009
orse-0.009
orses-0.008
 peanut-0.008
ets-0.007
Token
Token ID198
Feature activation-9.85e-01

Pos logit contributions
ret+0.034
orse+0.033
orses+0.031
ets+0.031
 peanut+0.031
Neg logit contributions
 Lu-0.031
Ann-0.025
Lu-0.025
 angels-0.024
 youths-0.023
TokenBen
Token ID11696
Feature activation+1.69e+00

Pos logit contributions
ret+0.045
orse+0.042
ocket+0.038
orses+0.038
 peanut+0.037
Neg logit contributions
 Lu-0.045
Lu-0.039
Ann-0.038
 youths-0.036
 angels-0.035
Token agreed
Token ID4987
Feature activation-1.73e-02

Pos logit contributions
 Lu+0.086
 angels+0.079
 firefighters+0.075
 Taxi+0.074
 taxis+0.073
Neg logit contributions
orse-0.060
ret-0.056
orses-0.051
 peanut-0.050
's-0.050
Token and
Token ID290
Feature activation+1.02e-01

Pos logit contributions
ret+0.001
orse+0.001
orses+0.001
 peanut+0.001
ets+0.001
Neg logit contributions
 Lu-0.001
 angels-0.001
Ann-0.001
Lu-0.001
 firefighters-0.001
Token soon
Token ID2582
Feature activation-7.15e-01

Pos logit contributions
 Lu+0.006
 angels+0.005
Ann+0.005
Lu+0.005
 firefighters+0.005
Neg logit contributions
ret-0.003
orse-0.003
orses-0.003
 peanut-0.003
ets-0.003
Token the
Token ID262
Feature activation+3.61e+00

Pos logit contributions
ret+0.027
orse+0.026
orses+0.025
ets+0.022
ocket+0.022
Neg logit contributions
 Lu-0.037
 angels-0.030
Ann-0.029
Lu-0.029
 youths-0.028
Token two
Token ID734
Feature activation+3.17e+00

Pos logit contributions
 Lu+0.146
Ann+0.142
 Kitty+0.136
 Tit+0.134
Lu+0.134
Neg logit contributions
 picture-0.106
 drawing-0.103
's-0.099
 ink-0.097
 face-0.096
Token of
Token ID286
Feature activation+9.13e-01

Pos logit contributions
 Lu+0.144
iger+0.142
 Amen+0.133
 Johnson+0.132
jack+0.132
Neg logit contributions
's-0.097
s-0.095
orse-0.091
orses-0.090
bs-0.089
Token them
Token ID606
Feature activation+1.27e+00

Pos logit contributions
 Lu+0.050
jack+0.043
 angels+0.043
 attendant+0.043
 Taxi+0.042
Neg logit contributions
orse-0.028
ret-0.028
orses-0.026
 peanut-0.024
 notebooks-0.022
Token were
Token ID547
Feature activation+1.56e+00

Pos logit contributions
 Lu+0.067
 angels+0.058
Ann+0.057
Lu+0.057
 youths+0.056
Neg logit contributions
orse-0.042
ret-0.040
orses-0.039
ets-0.037
 peanut-0.034
Token walking
Token ID6155
Feature activation+1.70e+00

Pos logit contributions
 Lu+0.075
jack+0.066
Ann+0.066
Lu+0.066
 attendant+0.063
Neg logit contributions
orse-0.056
orses-0.053
ret-0.047
 peanut-0.045
ets-0.045
Token!
Token ID0
Feature activation-2.16e-01

Pos logit contributions
ret+0.011
orse+0.011
orses+0.010
 peanut+0.009
ets+0.009
Neg logit contributions
 Lu-0.013
 angels-0.011
Ann-0.010
Lu-0.010
 firefighters-0.010
Token He
Token ID679
Feature activation+1.08e+00

Pos logit contributions
ret+0.009
orse+0.009
orses+0.009
 peanut+0.008
ets+0.008
Neg logit contributions
 Lu-0.010
 angels-0.008
Ann-0.008
Lu-0.008
 firefighters-0.008
Token even
Token ID772
Feature activation+2.72e-01

Pos logit contributions
 Lu+0.058
 angels+0.051
 firefighters+0.049
 Taxi+0.049
 attendant+0.048
Neg logit contributions
orse-0.037
ret-0.034
orses-0.034
 peanut-0.031
ets-0.030
Token showed
Token ID3751
Feature activation-5.00e-01

Pos logit contributions
 Lu+0.014
 angels+0.012
Ann+0.011
Lu+0.011
 firefighters+0.011
Neg logit contributions
orse-0.010
ret-0.010
orses-0.009
 peanut-0.009
ets-0.008
Token his
Token ID465
Feature activation+2.24e+00

Pos logit contributions
orse+0.023
ret+0.023
orses+0.022
 peanut+0.020
ets+0.019
Neg logit contributions
 Lu-0.022
 angels-0.017
Ann-0.017
 firefighters-0.017
Lu-0.016
Token new
Token ID649
Feature activation+3.61e+00

Pos logit contributions
 Lu+0.107
Lu+0.093
Ann+0.088
ators+0.088
guard+0.085
Neg logit contributions
orse-0.079
 mouth-0.077
orses-0.076
 peanut-0.073
ret-0.072
Token friends
Token ID2460
Feature activation-5.80e-01

Pos logit contributions
 Lu+0.167
Ann+0.154
Lu+0.150
K+0.144
guard+0.142
Neg logit contributions
 drawing-0.112
 mouth-0.111
 tomato-0.110
's-0.109
orse-0.103
Token how
Token ID703
Feature activation+7.30e-01

Pos logit contributions
ret+0.027
orse+0.027
orses+0.025
 peanut+0.023
ets+0.023
Neg logit contributions
 Lu-0.025
 angels-0.019
Ann-0.018
Lu-0.018
 youths-0.018
Token to
Token ID284
Feature activation+2.61e+00

Pos logit contributions
 Lu+0.037
Ann+0.031
 angels+0.030
 attendant+0.030
Lu+0.030
Neg logit contributions
orse-0.027
ret-0.027
orses-0.025
 peanut-0.022
ets-0.022
Token do
Token ID466
Feature activation+3.83e-01

Pos logit contributions
 Lu+0.139
 firefighters+0.127
 angels+0.126
 Taxi+0.124
 attendant+0.124
Neg logit contributions
orse-0.078
orses-0.069
ret-0.063
ets-0.063
 scored-0.054
Token them
Token ID606
Feature activation+1.64e+00

Pos logit contributions
 Lu+0.021
 angels+0.017
Ann+0.017
Lu+0.017
 firefighters+0.017
Neg logit contributions
ret-0.013
orse-0.013
orses-0.012
 peanut-0.011
ets-0.011
Token was
Token ID373
Feature activation+1.53e+00

Pos logit contributions
 Lu+0.041
 angels+0.036
 youths+0.034
Ann+0.034
 firefighters+0.034
Neg logit contributions
orse-0.028
ret-0.028
orses-0.025
 peanut-0.024
sel-0.022
Token surprised
Token ID6655
Feature activation-2.20e-01

Pos logit contributions
 Lu+0.082
 angels+0.074
ators+0.073
Ann+0.072
lo+0.072
Neg logit contributions
orse-0.047
ret-0.039
orses-0.038
 peanut-0.038
's-0.037
Token and
Token ID290
Feature activation-1.96e-01

Pos logit contributions
ret+0.009
orse+0.009
orses+0.009
 peanut+0.008
ets+0.008
Neg logit contributions
 Lu-0.010
 angels-0.008
Lu-0.008
Ann-0.008
 firefighters-0.008
Token wondered
Token ID14028
Feature activation+1.05e+00

Pos logit contributions
ret+0.009
orse+0.008
orses+0.008
 peanut+0.007
ets+0.007
Neg logit contributions
 Lu-0.009
 angels-0.007
Ann-0.007
Lu-0.007
 firefighters-0.007
Token how
Token ID703
Feature activation+7.63e-01

Pos logit contributions
 Lu+0.057
Ann+0.051
Lu+0.049
 youths+0.048
 angels+0.048
Neg logit contributions
ret-0.033
orse-0.032
orses-0.028
 peanut-0.025
ocket-0.025
Token the
Token ID262
Feature activation+3.61e+00

Pos logit contributions
 Lu+0.038
Ann+0.032
 angels+0.032
co+0.031
 attendant+0.030
Neg logit contributions
ret-0.028
orse-0.027
orses-0.026
 peanut-0.024
ets-0.023
Token all
Token ID477
Feature activation+2.75e+00

Pos logit contributions
 Lu+0.184
Ann+0.183
co+0.173
Michael+0.171
Kim+0.166
Neg logit contributions
 peanut-0.082
 photos-0.078
 shrimp-0.077
 bean-0.068
 photo-0.068
Tokenigator
Token ID23823
Feature activation+6.00e-01

Pos logit contributions
 Lu+0.101
co+0.096
Michael+0.087
 Barber+0.085
 angels+0.084
Neg logit contributions
's-0.109
 peanut-0.108
ets-0.105
ret-0.105
s-0.101
Token could
Token ID714
Feature activation+1.54e+00

Pos logit contributions
 Lu+0.030
 angels+0.025
Ann+0.025
Lu+0.025
 firefighters+0.024
Neg logit contributions
ret-0.022
orse-0.022
orses-0.020
 peanut-0.019
ets-0.019
Token talk
Token ID1561
Feature activation+6.81e-01

Pos logit contributions
 Lu+0.083
Ann+0.068
Lu+0.068
 youths+0.068
 angels+0.067
Neg logit contributions
orse-0.053
ret-0.049
orses-0.046
 peanut-0.043
ork-0.043
Token.
Token ID13
Feature activation+2.04e-01

Pos logit contributions
 Lu+0.035
Ann+0.029
 angels+0.028
Lu+0.028
 firefighters+0.027
Neg logit contributions
ret-0.025
orse-0.024
orses-0.022
ets-0.022
 peanut-0.021
Token of
Token ID286
Feature activation+4.08e-01

Pos logit contributions
 Lu+0.058
 angels+0.048
Lu+0.047
Ann+0.047
 Stev+0.045
Neg logit contributions
orse-0.048
ret-0.047
orses-0.045
ets-0.044
 peanut-0.042
Token them
Token ID606
Feature activation-1.50e-01

Pos logit contributions
 Lu+0.020
Ann+0.016
 angels+0.016
Lu+0.016
 youths+0.016
Neg logit contributions
ret-0.016
orse-0.015
orses-0.014
 peanut-0.013
ets-0.013
Token.
Token ID13
Feature activation-4.32e-02

Pos logit contributions
ret+0.006
orse+0.006
orses+0.006
 peanut+0.005
ets+0.005
Neg logit contributions
 Lu-0.007
 angels-0.006
Ann-0.006
Lu-0.006
 firefighters-0.006
Token
Token ID198
Feature activation+7.30e-01

Pos logit contributions
ret+0.002
orse+0.002
orses+0.001
 peanut+0.001
ets+0.001
Neg logit contributions
 Lu-0.002
 angels-0.002
Ann-0.002
Lu-0.002
 firefighters-0.002
Token
Token ID198
Feature activation+4.07e-01

Pos logit contributions
 Lu+0.038
 angels+0.034
 firefighters+0.032
 youths+0.032
Ann+0.031
Neg logit contributions
orse-0.025
ret-0.024
orses-0.023
ork-0.020
 peanut-0.019
TokenThe
Token ID464
Feature activation+3.59e+00

Pos logit contributions
 Lu+0.021
 angels+0.017
 firefighters+0.016
 youths+0.016
Ann+0.016
Neg logit contributions
orse-0.015
ret-0.015
orses-0.014
ork-0.012
ets-0.012
Token fog
Token ID19558
Feature activation+9.94e-01

Pos logit contributions
whe+0.156
ussy+0.153
 Lu+0.149
wood+0.144
Ann+0.142
Neg logit contributions
 wishes-0.086
 wish-0.084
 bad-0.080
 dream-0.079
 holes-0.079
Token was
Token ID373
Feature activation+1.35e+00

Pos logit contributions
 Lu+0.051
Lu+0.042
 youths+0.042
Ann+0.041
 angels+0.041
Neg logit contributions
orse-0.036
ret-0.035
orses-0.033
ork-0.030
 peanut-0.030
Token gone
Token ID3750
Feature activation+1.71e-01

Pos logit contributions
 Lu+0.071
Ann+0.062
 youths+0.061
 angels+0.061
Lu+0.059
Neg logit contributions
orse-0.043
ret-0.040
 peanut-0.039
orses-0.038
ets-0.035
Token,
Token ID11
Feature activation-2.34e-01

Pos logit contributions
 Lu+0.009
 angels+0.007
Ann+0.007
Lu+0.007
 firefighters+0.007
Neg logit contributions
ret-0.006
orse-0.006
orses-0.006
 peanut-0.005
ets-0.005
Token and
Token ID290
Feature activation+3.67e-01

Pos logit contributions
ret+0.010
orse+0.010
orses+0.009
 peanut+0.008
ets+0.008
Neg logit contributions
 Lu-0.011
 angels-0.009
Ann-0.009
Lu-0.009
 firefighters-0.009
Token!
Token ID0
Feature activation-7.99e-01

Pos logit contributions
ret+0.013
orse+0.013
orses+0.012
 peanut+0.011
ets+0.011
Neg logit contributions
 Lu-0.013
 angels-0.011
Ann-0.011
Lu-0.010
 firefighters-0.010
Token
Token ID220
Feature activation+1.36e-01

Pos logit contributions
ret+0.031
orse+0.031
orses+0.029
ets+0.027
 peanut+0.026
Neg logit contributions
 Lu-0.041
Lu-0.032
 Lucy-0.032
Ann-0.032
 attendant-0.032
Token
Token ID198
Feature activation-1.09e-02

Pos logit contributions
 Lu+0.007
 angels+0.006
Ann+0.005
Lu+0.005
 firefighters+0.005
Neg logit contributions
ret-0.005
orse-0.005
orses-0.005
 peanut-0.004
ets-0.004
Token
Token ID198
Feature activation-3.07e-01

Pos logit contributions
ret+0.000
orse+0.000
orses+0.000
 peanut+0.000
ets+0.000
Neg logit contributions
 Lu-0.001
 angels-0.000
Ann-0.000
Lu-0.000
 firefighters-0.000
TokenThe
Token ID464
Feature activation+2.76e+00

Pos logit contributions
ret+0.013
orse+0.013
orses+0.012
 peanut+0.011
ets+0.011
Neg logit contributions
 Lu-0.014
Lu-0.012
Ann-0.012
 angels-0.011
 firefighters-0.011
Token new
Token ID649
Feature activation+3.58e+00

Pos logit contributions
 Lu+0.154
Ann+0.151
Michael+0.136
co+0.133
Kim+0.133
Neg logit contributions
 peanut-0.066
 shrimp-0.064
 photos-0.057
 bean-0.056
 tomato-0.052
Token all
Token ID477
Feature activation+3.69e-01

Pos logit contributions
Ann+0.190
 Lu+0.187
Michael+0.178
Kim+0.174
co+0.171
Neg logit contributions
 shrimp-0.078
 shell-0.073
 peanut-0.072
s-0.070
 net-0.070
Tokenigator
Token ID23823
Feature activation-1.09e+00

Pos logit contributions
 Lu+0.009
 angels+0.006
Ann+0.006
Lu+0.006
 firefighters+0.005
Neg logit contributions
orse-0.023
ret-0.023
orses-0.022
 peanut-0.021
ets-0.021
Token said
Token ID531
Feature activation+2.77e-02

Pos logit contributions
ret+0.048
orse+0.044
orses+0.043
ets+0.042
 notebooks+0.040
Neg logit contributions
 Lu-0.048
 angels-0.038
 attendant-0.038
 firefighters-0.037
Ann-0.037
Token,
Token ID11
Feature activation-2.34e-01

Pos logit contributions
 Lu+0.001
 angels+0.001
Ann+0.001
Lu+0.001
 firefighters+0.001
Neg logit contributions
ret-0.001
orse-0.001
orses-0.001
 peanut-0.001
ets-0.001
Token "
Token ID366
Feature activation+5.43e-02

Pos logit contributions
ret+0.011
orse+0.010
orses+0.010
 peanut+0.009
ets+0.009
Neg logit contributions
 Lu-0.010
 angels-0.008
Ann-0.008
Lu-0.008
 firefighters-0.008
Token nodded
Token ID14464
Feature activation+1.78e-01

Pos logit contributions
 Lu+0.025
 angels+0.022
 firefighters+0.021
Ann+0.021
Lu+0.021
Neg logit contributions
orse-0.019
ret-0.019
orses-0.017
 peanut-0.016
ets-0.015
Token and
Token ID290
Feature activation+4.59e-01

Pos logit contributions
 Lu+0.009
 angels+0.007
Ann+0.007
Lu+0.007
 firefighters+0.007
Neg logit contributions
ret-0.007
orse-0.007
orses-0.006
 peanut-0.006
ets-0.006
Token watched
Token ID7342
Feature activation-2.12e-01

Pos logit contributions
 Lu+0.022
 angels+0.019
Ann+0.019
Lu+0.018
 youths+0.018
Neg logit contributions
orse-0.018
ret-0.018
orses-0.016
 peanut-0.015
ets-0.014
Token carefully
Token ID7773
Feature activation-2.64e-01

Pos logit contributions
ret+0.008
orse+0.008
orses+0.008
 peanut+0.007
ets+0.007
Neg logit contributions
 Lu-0.011
 angels-0.009
Ann-0.008
Lu-0.008
 firefighters-0.008
Token as
Token ID355
Feature activation+5.04e-01

Pos logit contributions
ret+0.011
orse+0.011
orses+0.010
 peanut+0.009
ets+0.009
Neg logit contributions
 Lu-0.013
 angels-0.010
Ann-0.010
Lu-0.010
 firefighters-0.010
Token the
Token ID262
Feature activation+3.58e+00

Pos logit contributions
 Lu+0.026
Ann+0.022
 angels+0.022
Lu+0.022
co+0.021
Neg logit contributions
ret-0.018
orse-0.018
orses-0.016
 peanut-0.015
ork-0.014
Token grown
Token ID7334
Feature activation+1.31e+00

Pos logit contributions
 Johnson+0.145
 Jenkins+0.140
 Tit+0.140
girls+0.139
 department+0.137
Neg logit contributions
 picture-0.096
's-0.093
 drawing-0.092
 photo-0.088
 it-0.087
Token up
Token ID510
Feature activation+1.09e-01

Pos logit contributions
 Lu+0.066
Ann+0.056
 Taxi+0.055
Lu+0.055
 youths+0.055
Neg logit contributions
ret-0.047
orse-0.044
orses-0.041
sel-0.041
ets-0.039
Token stretched
Token ID19110
Feature activation-3.08e-01

Pos logit contributions
 Lu+0.005
 angels+0.004
Ann+0.004
Lu+0.004
 firefighters+0.004
Neg logit contributions
ret-0.004
orse-0.004
orses-0.004
 peanut-0.004
ets-0.004
Token her
Token ID607
Feature activation+1.06e+00

Pos logit contributions
orse+0.013
ret+0.013
orses+0.012
 peanut+0.011
ets+0.011
Neg logit contributions
 Lu-0.014
 angels-0.012
Ann-0.011
Lu-0.011
 firefighters-0.011
Token arms
Token ID5101
Feature activation-4.15e-01

Pos logit contributions
 Lu+0.056
Ann+0.050
 firefighters+0.049
Lu+0.048
 youths+0.048
Neg logit contributions
ret-0.035
orse-0.033
orses-0.030
ork-0.029
ets-0.028
Token a
Token ID257
Feature activation-2.52e-01

Pos logit contributions
ret+0.008
orse+0.008
orses+0.008
 peanut+0.007
ets+0.007
Neg logit contributions
 Lu-0.009
 angels-0.007
Ann-0.007
Lu-0.007
 firefighters-0.007
Token little
Token ID1310
Feature activation+6.94e-01

Pos logit contributions
ret+0.009
orse+0.009
orses+0.009
ets+0.008
 peanut+0.008
Neg logit contributions
 Lu-0.013
 angels-0.011
Lu-0.011
Ann-0.010
 firefighters-0.010
Token girl
Token ID2576
Feature activation-9.24e-01

Pos logit contributions
 Lu+0.026
Ann+0.021
 angels+0.020
Lu+0.020
 firefighters+0.019
Neg logit contributions
orse-0.034
ret-0.033
 peanut-0.032
orses-0.032
ets-0.029
Token named
Token ID3706
Feature activation-5.17e-01

Pos logit contributions
ret+0.040
orse+0.037
orses+0.036
ets+0.035
sel+0.034
Neg logit contributions
 Lu-0.044
Lu-0.035
Ann-0.034
 angels-0.034
co-0.033
Token Lu
Token ID6026
Feature activation+9.13e-01

Pos logit contributions
orse+0.024
ret+0.024
orses+0.023
 peanut+0.021
sel+0.021
Neg logit contributions
 Lu-0.023
Lu-0.018
Ann-0.018
 angels-0.018
 Lucy-0.017
Token.
Token ID13
Feature activation+3.56e+00

Pos logit contributions
 Lu+0.038
 angels+0.034
 firefighters+0.034
 youths+0.033
 attendant+0.031
Neg logit contributions
orse-0.040
ret-0.039
orses-0.036
 peanut-0.033
ets-0.032
Token She
Token ID1375
Feature activation-5.02e-01

Pos logit contributions
guard+0.204
 helpers+0.197
 mercy+0.196
 firefighters+0.196
 fighters+0.194
Neg logit contributions
 This-0.081
 Its-0.067
 It-0.067
s-0.066
's-0.059
Token was
Token ID373
Feature activation+7.08e-01

Pos logit contributions
ret+0.024
orse+0.023
orses+0.022
ets+0.020
 peanut+0.020
Neg logit contributions
 Lu-0.022
Lu-0.017
Ann-0.017
 angels-0.017
 firefighters-0.016
Token three
Token ID1115
Feature activation+1.02e+00

Pos logit contributions
 Lu+0.036
Ann+0.031
Lu+0.030
 angels+0.030
 attendant+0.029
Neg logit contributions
orse-0.024
ret-0.024
 peanut-0.022
orses-0.022
ocket-0.019
Token years
Token ID812
Feature activation+1.03e+00

Pos logit contributions
 Lu+0.057
 attendant+0.049
 angels+0.048
Ann+0.048
 Taxi+0.047
Neg logit contributions
orse-0.032
ret-0.030
orses-0.029
 peanut-0.028
ets-0.026
Token old
Token ID1468
Feature activation+1.55e+00

Pos logit contributions
 Lu+0.048
Ann+0.042
 angels+0.040
Lu+0.039
Michael+0.038
Neg logit contributions
orse-0.040
ret-0.040
orses-0.037
 peanut-0.037
ork-0.034
TokenCan
Token ID6090
Feature activation+1.04e+00

Pos logit contributions
 Lu+0.080
 angels+0.071
 firefighters+0.067
 youths+0.066
 attendant+0.066
Neg logit contributions
 peanut-0.046
orse-0.045
ret-0.044
orses-0.042
 scored-0.041
Token I
Token ID314
Feature activation+1.03e+00

Pos logit contributions
 Lu+0.067
 firefighters+0.059
 angels+0.059
 youths+0.058
Ann+0.058
Neg logit contributions
ret-0.021
orse-0.021
orses-0.017
 peanut-0.016
ork-0.014
Token use
Token ID779
Feature activation-3.66e-01

Pos logit contributions
 Lu+0.055
 angels+0.049
Ann+0.046
Lu+0.046
 youths+0.046
Neg logit contributions
orse-0.035
ret-0.034
orses-0.031
 peanut-0.030
ets-0.027
Token it
Token ID340
Feature activation+1.00e+00

Pos logit contributions
orse+0.012
ret+0.012
orses+0.011
 peanut+0.010
ets+0.010
Neg logit contributions
 Lu-0.020
 angels-0.017
Ann-0.016
Lu-0.016
 firefighters-0.016
Token?"
Token ID1701
Feature activation+2.02e+00

Pos logit contributions
 Lu+0.052
Ann+0.043
 angels+0.043
Lu+0.042
 youths+0.042
Neg logit contributions
ret-0.036
orse-0.035
 peanut-0.032
orses-0.032
ets-0.030
Token asked
Token ID1965
Feature activation+3.55e+00

Pos logit contributions
ators+0.060
 angels+0.059
 Lu+0.057
co+0.056
 department+0.053
Neg logit contributions
orse-0.096
 peanut-0.090
's-0.088
bs-0.087
 This-0.087
Token Lucy
Token ID22162
Feature activation+6.44e-01

Pos logit contributions
co+0.134
iddle+0.132
ators+0.130
 fighters+0.128
 outage+0.125
Neg logit contributions
's-0.119
 it-0.110
bs-0.108
 peanut-0.108
 accidentally-0.106
Token.
Token ID13
Feature activation+1.31e+00

Pos logit contributions
 Lu+0.033
 angels+0.028
Ann+0.028
 firefighters+0.028
Lu+0.028
Neg logit contributions
orse-0.023
ret-0.023
orses-0.021
 peanut-0.019
ets-0.018
Token
Token ID198
Feature activation+1.13e+00

Pos logit contributions
 Lu+0.074
 angels+0.071
 firefighters+0.068
ators+0.067
 youths+0.067
Neg logit contributions
orse-0.034
ret-0.031
orses-0.028
 This-0.028
ork-0.027
Token
Token ID198
Feature activation+1.49e+00

Pos logit contributions
 Lu+0.062
 angels+0.058
 firefighters+0.057
 youths+0.055
ators+0.054
Neg logit contributions
ret-0.033
orse-0.033
orses-0.029
ork-0.028
 peanut-0.024
Token"
Token ID1
Feature activation+8.24e-01

Pos logit contributions
 Lu+0.088
 angels+0.083
 firefighters+0.081
 youths+0.080
ators+0.079
Neg logit contributions
orse-0.029
ork-0.028
's-0.027
ret-0.026
orses-0.024
Token bright
Token ID6016
Feature activation+1.46e+00

Pos logit contributions
 Lu+0.036
 angels+0.030
Ann+0.030
 youths+0.029
Lu+0.029
Neg logit contributions
orse-0.027
ret-0.026
orses-0.024
 peanut-0.024
ets-0.023
Token fan
Token ID4336
Feature activation+2.80e-01

Pos logit contributions
 Lu+0.075
Ann+0.067
 youths+0.064
 angels+0.064
Lu+0.063
Neg logit contributions
orse-0.049
 peanut-0.047
ret-0.046
orses-0.042
ork-0.040
Token.
Token ID13
Feature activation+1.76e-01

Pos logit contributions
 Lu+0.014
 angels+0.011
Ann+0.011
Lu+0.011
 youths+0.011
Neg logit contributions
orse-0.011
ret-0.011
orses-0.010
 peanut-0.009
ets-0.009
Token Joe
Token ID5689
Feature activation+3.77e-01

Pos logit contributions
 Lu+0.008
 angels+0.007
Ann+0.006
Lu+0.006
 firefighters+0.006
Neg logit contributions
ret-0.007
orse-0.007
orses-0.007
 peanut-0.006
ets-0.006
Token wanted
Token ID2227
Feature activation+1.44e+00

Pos logit contributions
 Lu+0.020
 angels+0.017
Ann+0.016
Lu+0.016
 firefighters+0.016
Neg logit contributions
orse-0.013
ret-0.013
orses-0.012
 peanut-0.011
ets-0.011
Token the
Token ID262
Feature activation+3.55e+00

Pos logit contributions
 Lu+0.079
 youths+0.070
 attendant+0.069
 angels+0.068
Ann+0.068
Neg logit contributions
orse-0.039
 peanut-0.039
ret-0.037
orses-0.034
ork-0.031
Token fan
Token ID4336
Feature activation+1.44e+00

Pos logit contributions
 Lu+0.138
Ann+0.135
jack+0.131
 Jenkins+0.130
Lu+0.128
Neg logit contributions
's-0.117
 picture-0.112
 drawing-0.104
 may-0.101
ret-0.100
Token too
Token ID1165
Feature activation+4.89e-01

Pos logit contributions
 Lu+0.078
Ann+0.068
Lu+0.066
 youths+0.064
 angels+0.064
Neg logit contributions
ret-0.046
orse-0.044
 peanut-0.042
orses-0.040
ets-0.038
Token,
Token ID11
Feature activation-2.35e-01

Pos logit contributions
 Lu+0.027
 angels+0.023
Ann+0.023
Lu+0.023
 firefighters+0.023
Neg logit contributions
ret-0.016
orse-0.015
orses-0.014
 peanut-0.013
ets-0.013
Token and
Token ID290
Feature activation+8.60e-01

Pos logit contributions
ret+0.010
orse+0.010
orses+0.009
 peanut+0.008
ets+0.008
Neg logit contributions
 Lu-0.011
 angels-0.009
Ann-0.009
Lu-0.009
 firefighters-0.008
Token so
Token ID523
Feature activation-1.62e-01

Pos logit contributions
 Lu+0.044
 angels+0.037
Ann+0.036
Lu+0.036
 Taxi+0.036
Neg logit contributions
orse-0.031
ret-0.028
orses-0.028
 peanut-0.026
ets-0.024
Token today
Token ID1909
Feature activation+5.32e-01

Pos logit contributions
ret+0.026
orse+0.025
orses+0.024
ets+0.022
 peanut+0.022
Neg logit contributions
 Lu-0.020
 angels-0.016
 firefighters-0.015
Ann-0.015
Lu-0.015
Token?"
Token ID1701
Feature activation+2.22e-01

Pos logit contributions
 Lu+0.024
 angels+0.019
Ann+0.019
Lu+0.019
 firefighters+0.019
Neg logit contributions
orse-0.023
ret-0.022
orses-0.021
 peanut-0.020
ets-0.019
Token
Token ID198
Feature activation+3.02e-01

Pos logit contributions
 Lu+0.011
 angels+0.010
Ann+0.009
 firefighters+0.009
Lu+0.009
Neg logit contributions
orse-0.008
ret-0.008
orses-0.007
 peanut-0.007
ets-0.006
Token
Token ID198
Feature activation+5.08e-02

Pos logit contributions
 Lu+0.015
 angels+0.013
Ann+0.012
 firefighters+0.012
Lu+0.012
Neg logit contributions
ret-0.011
orse-0.011
orses-0.010
 peanut-0.010
ork-0.009
TokenMr
Token ID5246
Feature activation+2.40e+00

Pos logit contributions
 Lu+0.003
 angels+0.002
Ann+0.002
Lu+0.002
 firefighters+0.002
Neg logit contributions
ret-0.002
orse-0.002
orses-0.002
 peanut-0.002
ets-0.002
Token.
Token ID13
Feature activation+3.54e+00

Pos logit contributions
 Lu+0.140
 youths+0.123
Ann+0.123
Michael+0.122
Lu+0.122
Neg logit contributions
orse-0.058
ret-0.055
 peanut-0.049
orses-0.049
ork-0.046
Token Sun
Token ID3825
Feature activation+1.87e+00

Pos logit contributions
aid+0.116
guard+0.116
 youths+0.115
co+0.112
 mercy+0.109
Neg logit contributions
orse-0.142
 T-0.140
 This-0.138
orses-0.129
ret-0.122
Token smiled
Token ID13541
Feature activation+5.62e-01

Pos logit contributions
 Lu+0.095
 youths+0.084
 firefighters+0.082
 angels+0.082
Ann+0.082
Neg logit contributions
orse-0.066
ret-0.058
orses-0.058
 peanut-0.056
's-0.050
Token and
Token ID290
Feature activation+5.48e-01

Pos logit contributions
 Lu+0.031
Ann+0.027
Lu+0.026
 angels+0.026
 firefighters+0.025
Neg logit contributions
orse-0.018
ret-0.018
orses-0.016
 peanut-0.016
ets-0.015
Token said
Token ID531
Feature activation+3.70e-01

Pos logit contributions
 Lu+0.029
 angels+0.025
Ann+0.025
Lu+0.024
 firefighters+0.024
Neg logit contributions
orse-0.019
ret-0.018
orses-0.017
 peanut-0.016
ets-0.015
Token,
Token ID11
Feature activation-1.26e-01

Pos logit contributions
 Lu+0.021
Ann+0.018
 angels+0.017
Lu+0.017
 firefighters+0.017
Neg logit contributions
ret-0.012
orse-0.012
orses-0.011
 peanut-0.010
ets-0.009
Token was
Token ID373
Feature activation+1.58e+00

Pos logit contributions
 Lu+0.012
 angels+0.010
Ann+0.010
 firefighters+0.010
Lu+0.010
Neg logit contributions
orse-0.008
ret-0.008
orses-0.007
 peanut-0.007
ets-0.006
Token excited
Token ID6568
Feature activation-3.90e-01

Pos logit contributions
 Lu+0.089
Ann+0.082
lo+0.079
 angels+0.079
co+0.078
Neg logit contributions
orse-0.049
ret-0.041
 peanut-0.038
orses-0.038
ocket-0.035
Token to
Token ID284
Feature activation+6.45e-01

Pos logit contributions
ret+0.018
orse+0.018
orses+0.017
 peanut+0.016
ocket+0.015
Neg logit contributions
 Lu-0.017
 angels-0.013
Lu-0.013
 firefighters-0.013
Ann-0.013
Token have
Token ID423
Feature activation+1.90e-01

Pos logit contributions
 Lu+0.035
 angels+0.030
Ann+0.030
Lu+0.030
 youths+0.029
Neg logit contributions
orse-0.022
ret-0.020
orses-0.019
 peanut-0.017
ets-0.016
Token a
Token ID257
Feature activation+1.56e+00

Pos logit contributions
 Lu+0.009
 angels+0.008
Ann+0.007
Lu+0.007
 youths+0.007
Neg logit contributions
orse-0.008
ret-0.008
orses-0.007
 peanut-0.007
ets-0.006
Token new
Token ID649
Feature activation+3.54e+00

Pos logit contributions
 Lu+0.087
Ann+0.081
lo+0.077
co+0.077
ators+0.076
Neg logit contributions
orse-0.042
 peanut-0.042
ret-0.041
ork-0.038
orses-0.035
Token one
Token ID530
Feature activation+6.23e-01

Pos logit contributions
Ann+0.179
lo+0.175
Andy+0.167
 Lu+0.167
co+0.164
Neg logit contributions
's-0.094
 folder-0.093
 pen-0.092
 notebook-0.091
 peanut-0.087
Token.
Token ID13
Feature activation-4.44e-02

Pos logit contributions
 Lu+0.033
Ann+0.028
 angels+0.028
Lu+0.027
 firefighters+0.027
Neg logit contributions
orse-0.021
ret-0.021
orses-0.019
 peanut-0.019
ets-0.018
Token "
Token ID366
Feature activation+2.10e-01

Pos logit contributions
ret+0.002
orse+0.002
orses+0.002
 peanut+0.002
ets+0.002
Neg logit contributions
 Lu-0.002
 angels-0.002
Ann-0.002
Lu-0.002
 firefighters-0.002
TokenI
Token ID40
Feature activation-8.61e-02

Pos logit contributions
 Lu+0.008
 angels+0.007
Ann+0.006
 firefighters+0.006
 youths+0.006
Neg logit contributions
ret-0.010
orse-0.010
orses-0.009
 peanut-0.009
ets-0.009
Token hope
Token ID2911
Feature activation-7.76e-02

Pos logit contributions
ret+0.003
orse+0.003
orses+0.003
 peanut+0.003
ets+0.003
Neg logit contributions
 Lu-0.004
 angels-0.003
Ann-0.003
Lu-0.003
 firefighters-0.003
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
 Lu+0.022
Ann+0.018
Lu+0.018
 angels+0.018
 firefighters+0.018
Neg logit contributions
ret-0.016
orse-0.015
orses-0.014
ets-0.013
 peanut-0.013
Token "
Token ID366
Feature activation-1.34e-01

Pos logit contributions
 Lu+0.053
 angels+0.046
ators+0.046
Ann+0.045
co+0.044
Neg logit contributions
orse-0.032
ret-0.030
orses-0.028
 peanut-0.027
ork-0.027
TokenDo
Token ID5211
Feature activation-1.16e+00

Pos logit contributions
ret+0.006
orse+0.006
orses+0.006
 peanut+0.005
ets+0.005
Neg logit contributions
 Lu-0.006
 angels-0.005
Ann-0.004
Lu-0.004
 firefighters-0.004
Token you
Token ID345
Feature activation-2.34e-01

Pos logit contributions
ret+0.035
orse+0.035
orses+0.030
sel+0.030
 peanut+0.029
Neg logit contributions
 Lu-0.067
 angels-0.060
Ann-0.059
Lu-0.057
 Lucy-0.055
Token like
Token ID588
Feature activation+1.58e+00

Pos logit contributions
ret+0.009
orse+0.009
orses+0.008
 peanut+0.008
ork+0.007
Neg logit contributions
 Lu-0.012
 angels-0.010
Ann-0.010
Lu-0.009
 firefighters-0.009
Token the
Token ID262
Feature activation+3.53e+00

Pos logit contributions
 Lu+0.094
jack+0.091
 attendant+0.086
Ann+0.082
 firefighters+0.081
Neg logit contributions
ret-0.032
 peanut-0.029
orse-0.029
orses-0.028
 drawing-0.027
Token stairs
Token ID16046
Feature activation+5.70e-01

Pos logit contributions
Andy+0.177
 Lu+0.169
jack+0.166
Michael+0.164
co+0.159
Neg logit contributions
 folder-0.098
 notebook-0.094
 picture-0.090
 drawing-0.086
 photos-0.082
Token?"
Token ID1701
Feature activation+5.04e-01

Pos logit contributions
 Lu+0.026
 angels+0.021
Lu+0.021
Ann+0.021
 firefighters+0.020
Neg logit contributions
ret-0.024
orse-0.023
orses-0.022
ets-0.021
 peanut-0.021
Token
Token ID198
Feature activation+4.52e-01

Pos logit contributions
 Lu+0.026
 angels+0.022
 firefighters+0.022
Lu+0.022
Ann+0.021
Neg logit contributions
orse-0.017
ret-0.017
orses-0.016
 peanut-0.014
ets-0.014
Token
Token ID198
Feature activation+2.80e-01

Pos logit contributions
 Lu+0.024
 angels+0.020
 firefighters+0.019
 youths+0.019
Ann+0.019
Neg logit contributions
ret-0.016
orse-0.016
orses-0.015
ork-0.013
 peanut-0.013
Token"
Token ID1
Feature activation+1.49e+00

Pos logit contributions
 Lu+0.013
 angels+0.011
 firefighters+0.010
 youths+0.010
Ann+0.010
Neg logit contributions
ret-0.011
orse-0.011
orses-0.011
 peanut-0.010
ets-0.010
Token Sam
Token ID3409
Feature activation-4.34e-01

Pos logit contributions
 Lu+0.036
 angels+0.031
Ann+0.030
 attendant+0.029
co+0.029
Neg logit contributions
orse-0.027
ret-0.025
orses-0.024
 peanut-0.023
sel-0.020
Token and
Token ID290
Feature activation+1.42e+00

Pos logit contributions
ret+0.019
orse+0.018
orses+0.017
 peanut+0.016
ets+0.016
Neg logit contributions
 Lu-0.020
 angels-0.016
Lu-0.015
Ann-0.015
 firefighters-0.015
Token Lucy
Token ID22162
Feature activation+4.60e-01

Pos logit contributions
 Lu+0.070
 attendant+0.062
ators+0.061
 angels+0.061
co+0.060
Neg logit contributions
orse-0.051
 peanut-0.045
orses-0.045
ret-0.045
 T-0.038
Token.
Token ID13
Feature activation+8.86e-01

Pos logit contributions
 Lu+0.024
Ann+0.020
 angels+0.020
Lu+0.019
 firefighters+0.019
Neg logit contributions
orse-0.017
ret-0.017
orses-0.015
 peanut-0.014
ets-0.014
Token Sam
Token ID3409
Feature activation-2.98e-01

Pos logit contributions
 Lu+0.051
 angels+0.044
 attendant+0.043
guard+0.043
Lu+0.042
Neg logit contributions
orse-0.024
orses-0.023
ret-0.023
 peanut-0.021
ets-0.020
Token and
Token ID290
Feature activation+3.51e+00

Pos logit contributions
ret+0.012
orse+0.011
orses+0.011
 peanut+0.010
ets+0.010
Neg logit contributions
 Lu-0.015
 angels-0.012
Ann-0.012
Lu-0.012
 firefighters-0.012
Token Lucy
Token ID22162
Feature activation+3.42e-01

Pos logit contributions
 attendant+0.133
iddle+0.133
 ambulance+0.128
pr+0.124
ators+0.122
Neg logit contributions
 This-0.126
 T-0.121
's-0.121
 Po-0.115
 peanut-0.112
Token loved
Token ID6151
Feature activation+1.36e+00

Pos logit contributions
 Lu+0.017
 angels+0.014
Ann+0.014
Lu+0.014
 firefighters+0.014
Neg logit contributions
orse-0.013
ret-0.013
orses-0.012
 peanut-0.011
ets-0.011
Token to
Token ID284
Feature activation+8.52e-01

Pos logit contributions
 Lu+0.074
Ann+0.067
 attendant+0.067
Lu+0.064
Michael+0.062
Neg logit contributions
 peanut-0.041
orse-0.041
orses-0.038
 notebooks-0.037
 ol-0.036
Token play
Token ID711
Feature activation+7.57e-01

Pos logit contributions
 Lu+0.048
Ann+0.041
Lu+0.040
 attendant+0.040
 angels+0.039
Neg logit contributions
orse-0.029
orses-0.026
ret-0.025
 peanut-0.024
 notebooks-0.021
Token together
Token ID1978
Feature activation+4.15e-01

Pos logit contributions
 Lu+0.040
Ann+0.033
 Taxi+0.032
 attendant+0.032
Lu+0.031
Neg logit contributions
orse-0.026
ret-0.025
orses-0.024
 peanut-0.023
ets-0.022
Tokenable
Token ID540
Feature activation+7.97e-01

Pos logit contributions
orse+0.026
ret+0.026
orses+0.025
 peanut+0.023
ocket+0.022
Neg logit contributions
 Lu-0.022
Ann-0.018
Lu-0.017
 angels-0.017
 youths-0.017
Token.
Token ID13
Feature activation-3.15e-01

Pos logit contributions
 Lu+0.043
Ann+0.036
Lu+0.036
 angels+0.035
 firefighters+0.034
Neg logit contributions
ret-0.027
orse-0.026
orses-0.024
ets-0.023
 peanut-0.023
Token And
Token ID843
Feature activation-7.07e-01

Pos logit contributions
ret+0.013
orse+0.013
orses+0.012
 peanut+0.011
ets+0.011
Neg logit contributions
 Lu-0.015
 angels-0.012
Ann-0.012
Lu-0.012
 firefighters-0.012
Token they
Token ID484
Feature activation+1.39e+00

Pos logit contributions
ret+0.028
orse+0.026
orses+0.024
ork+0.023
ets+0.022
Neg logit contributions
 Lu-0.037
 angels-0.031
 firefighters-0.029
 youths-0.029
 Lucy-0.029
Token liked
Token ID8288
Feature activation+5.38e-01

Pos logit contributions
 Lu+0.077
 angels+0.067
Ann+0.065
 firefighters+0.064
 taxis+0.064
Neg logit contributions
orse-0.043
ret-0.043
ets-0.038
 peanut-0.038
orses-0.038
Token the
Token ID262
Feature activation+3.51e+00

Pos logit contributions
 Lu+0.026
Ann+0.022
Lu+0.021
 angels+0.021
 attendant+0.021
Neg logit contributions
orse-0.021
ret-0.021
orses-0.019
 peanut-0.019
 notebooks-0.017
Token fog
Token ID19558
Feature activation+1.31e+00

Pos logit contributions
Andy+0.153
Lu+0.150
Ann+0.147
jack+0.145
 Lu+0.145
Neg logit contributions
 seas-0.102
 shell-0.101
 picture-0.093
 photo-0.092
 photos-0.090
Token.
Token ID13
Feature activation-7.66e-01

Pos logit contributions
 Lu+0.070
Lu+0.059
Ann+0.059
Michael+0.056
 youths+0.056
Neg logit contributions
ret-0.045
orse-0.044
orses-0.041
ets-0.040
 peanut-0.038
Token It
Token ID632
Feature activation+1.74e+00

Pos logit contributions
ret+0.035
orse+0.033
orses+0.031
ets+0.029
 peanut+0.029
Neg logit contributions
 Lu-0.035
 firefighters-0.027
 youths-0.027
 angels-0.026
Ann-0.026
Token made
Token ID925
Feature activation-7.28e-01

Pos logit contributions
 Lu+0.101
 youths+0.091
 Taxi+0.091
 taxis+0.089
 angels+0.088
Neg logit contributions
orse-0.051
ret-0.041
 peanut-0.041
orses-0.041
's-0.040
Token their
Token ID511
Feature activation+5.64e-01

Pos logit contributions
orse+0.034
ret+0.033
orses+0.031
ocket+0.029
 peanut+0.029
Neg logit contributions
 Lu-0.031
 angels-0.026
 firefighters-0.025
Ann-0.023
 youths-0.023
Token
Token ID198
Feature activation+9.94e-01

Pos logit contributions
 Lu+0.075
 angels+0.066
 firefighters+0.065
 youths+0.063
 Taxi+0.061
Neg logit contributions
orse-0.043
ret-0.041
orses-0.038
ork-0.034
 peanut-0.031
TokenOne
Token ID3198
Feature activation+7.08e-02

Pos logit contributions
 Lu+0.049
 angels+0.041
 youths+0.040
 firefighters+0.040
 attendant+0.039
Neg logit contributions
orse-0.038
orses-0.036
ret-0.035
ork-0.031
 peanut-0.031
Token day
Token ID1110
Feature activation+5.37e-02

Pos logit contributions
 Lu+0.003
 angels+0.003
Ann+0.003
Lu+0.003
 firefighters+0.003
Neg logit contributions
ret-0.003
orse-0.003
orses-0.003
 peanut-0.003
ets-0.003
Token,
Token ID11
Feature activation+6.53e-01

Pos logit contributions
 Lu+0.003
 angels+0.002
Ann+0.002
Lu+0.002
 firefighters+0.002
Neg logit contributions
ret-0.002
orse-0.002
orses-0.002
 peanut-0.002
ets-0.002
Token Sam
Token ID3409
Feature activation-6.55e-01

Pos logit contributions
 Lu+0.036
 angels+0.031
co+0.030
Ann+0.030
 attendant+0.030
Neg logit contributions
orse-0.019
ret-0.019
orses-0.017
 peanut-0.016
ets-0.015
Token and
Token ID290
Feature activation+3.50e+00

Pos logit contributions
ret+0.027
orse+0.026
orses+0.024
ocket+0.022
 peanut+0.022
Neg logit contributions
 Lu-0.031
Lu-0.025
Ann-0.025
 angels-0.024
 firefighters-0.024
Token Lucy
Token ID22162
Feature activation-1.00e-01

Pos logit contributions
 attendant+0.126
iddle+0.124
iren+0.120
 ambulance+0.118
 outage+0.118
Neg logit contributions
's-0.116
 Po-0.114
 This-0.114
 T-0.112
 peanut-0.111
Token went
Token ID1816
Feature activation+1.15e+00

Pos logit contributions
ret+0.004
orse+0.004
orses+0.004
 peanut+0.003
ets+0.003
Neg logit contributions
 Lu-0.005
 angels-0.004
Ann-0.004
Lu-0.004
 firefighters-0.004
Token to
Token ID284
Feature activation+8.03e-01

Pos logit contributions
 Lu+0.064
Ann+0.055
Lu+0.054
Michael+0.052
 Stev+0.052
Neg logit contributions
ret-0.035
orse-0.034
ets-0.032
orses-0.032
 peanut-0.031
Token the
Token ID262
Feature activation+3.39e-01

Pos logit contributions
 Lu+0.040
 angels+0.036
Ann+0.035
Lu+0.034
co+0.034
Neg logit contributions
orse-0.027
ret-0.027
orses-0.024
 peanut-0.024
ork-0.021
Token park
Token ID3952
Feature activation+3.84e-02

Pos logit contributions
 Lu+0.014
 angels+0.011
Ann+0.011
Lu+0.011
 firefighters+0.011
Neg logit contributions
ret-0.015
orse-0.015
orses-0.014
 peanut-0.014
ork-0.013
Token curious
Token ID11040
Feature activation+5.85e-01

Pos logit contributions
ret+0.010
orse+0.010
orses+0.009
ets+0.009
 peanut+0.009
Neg logit contributions
 Lu-0.012
 angels-0.010
Lu-0.009
Ann-0.009
 firefighters-0.009
Token little
Token ID1310
Feature activation+9.95e-01

Pos logit contributions
 Lu+0.029
Ann+0.024
 angels+0.024
Lu+0.023
 firefighters+0.022
Neg logit contributions
orse-0.023
ret-0.022
orses-0.021
 peanut-0.020
ets-0.019
Token cat
Token ID3797
Feature activation-4.36e-01

Pos logit contributions
 Lu+0.043
Ann+0.036
 angels+0.033
Lu+0.033
ators+0.033
Neg logit contributions
orse-0.044
 peanut-0.043
ret-0.042
orses-0.040
 notebooks-0.037
Token named
Token ID3706
Feature activation+1.59e-01

Pos logit contributions
ret+0.017
orse+0.016
orses+0.015
ets+0.014
 peanut+0.014
Neg logit contributions
 Lu-0.022
 angels-0.018
Lu-0.018
Ann-0.018
 firefighters-0.018
Token Kitty
Token ID21168
Feature activation+3.47e-01

Pos logit contributions
 Lu+0.006
 angels+0.005
Ann+0.005
 firefighters+0.005
Lu+0.005
Neg logit contributions
ret-0.008
orse-0.008
orses-0.007
 peanut-0.007
ets-0.007
Token.
Token ID13
Feature activation+3.49e+00

Pos logit contributions
 Lu+0.018
 angels+0.015
Ann+0.014
 firefighters+0.014
 youths+0.014
Neg logit contributions
orse-0.013
ret-0.013
orses-0.012
 peanut-0.011
ets-0.011
Token Kitty
Token ID21168
Feature activation+8.35e-01

Pos logit contributions
guard+0.151
ators+0.142
 pastor+0.135
 attendant+0.132
 helpers+0.123
Neg logit contributions
 This-0.148
 Its-0.123
 It-0.120
 The-0.115
 Find-0.113
Token loved
Token ID6151
Feature activation+8.75e-01

Pos logit contributions
 Lu+0.044
 angels+0.039
 attendant+0.038
 firefighters+0.037
 youths+0.037
Neg logit contributions
orse-0.028
ret-0.027
orses-0.025
 peanut-0.024
ets-0.022
Token to
Token ID284
Feature activation+2.58e-01

Pos logit contributions
 Lu+0.045
Ann+0.039
 attendant+0.038
Lu+0.037
 angels+0.036
Neg logit contributions
orse-0.030
 peanut-0.029
ret-0.029
orses-0.028
 notebooks-0.026
Token play
Token ID711
Feature activation+3.36e-01

Pos logit contributions
 Lu+0.013
 angels+0.011
Ann+0.011
Lu+0.011
 firefighters+0.011
Neg logit contributions
orse-0.009
ret-0.009
orses-0.009
 peanut-0.008
ets-0.008
Token and
Token ID290
Feature activation+3.08e-01

Pos logit contributions
 Lu+0.016
Ann+0.013
 angels+0.013
Lu+0.013
 attendant+0.013
Neg logit contributions
orse-0.013
ret-0.013
orses-0.012
 peanut-0.012
ets-0.011
Token happy
Token ID3772
Feature activation-7.74e-02

Pos logit contributions
 Lu+0.017
 angels+0.015
Ann+0.015
Lu+0.014
 youths+0.014
Neg logit contributions
orse-0.012
ret-0.012
orses-0.011
 peanut-0.010
ocket-0.009
Token that
Token ID326
Feature activation+8.67e-01

Pos logit contributions
ret+0.003
orse+0.003
orses+0.003
 peanut+0.003
ets+0.003
Neg logit contributions
 Lu-0.004
 angels-0.003
Ann-0.003
Lu-0.003
 firefighters-0.003
Token he
Token ID339
Feature activation+1.06e-01

Pos logit contributions
 Lu+0.050
co+0.044
Ann+0.044
 youths+0.043
 angels+0.043
Neg logit contributions
orse-0.025
ret-0.023
 peanut-0.022
orses-0.021
 notebooks-0.018
Token had
Token ID550
Feature activation-1.31e-01

Pos logit contributions
 Lu+0.006
 angels+0.005
Ann+0.005
Lu+0.005
 firefighters+0.005
Neg logit contributions
ret-0.003
orse-0.003
orses-0.003
 peanut-0.003
ets-0.003
Token a
Token ID257
Feature activation+1.04e+00

Pos logit contributions
ret+0.006
orse+0.006
orses+0.005
 peanut+0.005
ets+0.005
Neg logit contributions
 Lu-0.006
 angels-0.005
Ann-0.005
Lu-0.005
 firefighters-0.005
Token new
Token ID649
Feature activation+3.49e+00

Pos logit contributions
 Lu+0.055
Ann+0.048
co+0.045
 angels+0.045
 youths+0.045
Neg logit contributions
ret-0.036
orse-0.034
 peanut-0.033
ork-0.031
orses-0.030
Token bed
Token ID3996
Feature activation+1.94e-01

Pos logit contributions
Ann+0.172
lo+0.170
 Lu+0.161
co+0.159
Andy+0.158
Neg logit contributions
 pen-0.102
 folder-0.100
 notebook-0.100
 mouth-0.098
ork-0.096
Token to
Token ID284
Feature activation+5.22e-01

Pos logit contributions
 Lu+0.009
 angels+0.008
Ann+0.008
Lu+0.008
 firefighters+0.007
Neg logit contributions
ret-0.008
orse-0.008
orses-0.007
 peanut-0.007
ets-0.006
Token sleep
Token ID3993
Feature activation+7.15e-02

Pos logit contributions
 Lu+0.026
 angels+0.021
 youths+0.021
Ann+0.021
 firefighters+0.021
Neg logit contributions
orse-0.020
ret-0.020
orses-0.018
 peanut-0.017
ets-0.017
Token in
Token ID287
Feature activation-3.02e-01

Pos logit contributions
 Lu+0.003
 angels+0.003
Ann+0.003
Lu+0.003
 firefighters+0.003
Neg logit contributions
ret-0.003
orse-0.003
orses-0.003
 peanut-0.002
ets-0.002
Token.
Token ID13
Feature activation-4.63e-01

Pos logit contributions
ret+0.013
orse+0.013
orses+0.012
 peanut+0.011
ets+0.011
Neg logit contributions
 Lu-0.014
 angels-0.011
Ann-0.011
Lu-0.011
 firefighters-0.010
Token a
Token ID257
Feature activation-4.97e-01

Pos logit contributions
ret+0.004
orse+0.004
orses+0.004
 peanut+0.004
ets+0.004
Neg logit contributions
 Lu-0.005
 angels-0.004
Ann-0.004
Lu-0.004
 firefighters-0.004
Token nap
Token ID25422
Feature activation+1.57e-01

Pos logit contributions
ret+0.021
orse+0.020
orses+0.019
ets+0.018
sel+0.018
Neg logit contributions
 Lu-0.023
 angels-0.019
Lu-0.018
Ann-0.018
 firefighters-0.017
Token.
Token ID13
Feature activation-1.75e+00

Pos logit contributions
 Lu+0.008
 angels+0.006
Ann+0.006
Lu+0.006
 firefighters+0.006
Neg logit contributions
ret-0.006
orse-0.006
orses-0.006
 peanut-0.005
ets-0.005
Token One
Token ID1881
Feature activation+5.28e-02

Pos logit contributions
ret+0.089
orse+0.088
ocket+0.084
orses+0.084
ocus+0.083
Neg logit contributions
 Lu-0.060
 Taxi-0.042
 Barber-0.042
 Luis-0.039
 taxis-0.039
Token day
Token ID1110
Feature activation-3.20e+00

Pos logit contributions
 Lu+0.002
 angels+0.002
Ann+0.002
Lu+0.002
 firefighters+0.002
Neg logit contributions
ret-0.002
orse-0.002
orses-0.002
 peanut-0.002
ets-0.002
Token,
Token ID11
Feature activation-4.15e+00

Pos logit contributions
ret+0.179
iche+0.176
ets+0.174
orse+0.173
orses+0.172
Neg logit contributions
 Lu-0.082
 angels-0.052
 Dog-0.048
 Taxi-0.048
 youths-0.047
Token Gro
Token ID10299
Feature activation-1.64e+00

Pos logit contributions
iche+0.223
pler+0.219
ocus+0.219
ets+0.217
ulp+0.215
Neg logit contributions
 Lu-0.098
 Squirrel-0.085
 angels-0.080
 Dog-0.080
 Bird-0.079
Tokenver
Token ID332
Feature activation-2.16e+00

Pos logit contributions
orse+0.085
 peanut+0.085
orses+0.080
ret+0.078
 notebooks+0.076
Neg logit contributions
 Lu-0.052
Ann-0.040
 angels-0.039
Lu-0.038
 Taxi-0.037
Token decided
Token ID3066
Feature activation-1.03e+00

Pos logit contributions
iche+0.107
ret+0.104
ork+0.100
ets+0.100
ocket+0.100
Neg logit contributions
 Lu-0.076
 Karen-0.059
 Dog-0.057
 angels-0.056
 Taxi-0.055
Token he
Token ID339
Feature activation+1.15e-01

Pos logit contributions
ret+0.054
orse+0.053
orses+0.051
sel+0.048
ets+0.047
Neg logit contributions
 Lu-0.037
 angels-0.029
 firefighters-0.027
Lu-0.026
 Lucy-0.026
Token wanted
Token ID2227
Feature activation+5.88e-02

Pos logit contributions
 Lu+0.006
 angels+0.005
Ann+0.005
Lu+0.005
 firefighters+0.005
Neg logit contributions
ret-0.004
orse-0.004
orses-0.004
 peanut-0.004
ets-0.004
Token found
Token ID1043
Feature activation-3.98e-01

Pos logit contributions
ret+0.048
orse+0.047
orses+0.045
ocus+0.041
ets+0.040
Neg logit contributions
 Lu-0.045
Lu-0.035
 firefighters-0.034
Ann-0.034
 youths-0.034
Token a
Token ID257
Feature activation-1.32e+00

Pos logit contributions
orse+0.019
ret+0.018
orses+0.018
ets+0.016
 peanut+0.016
Neg logit contributions
 Lu-0.017
 angels-0.014
 firefighters-0.013
Ann-0.013
Lu-0.013
Token brilliant
Token ID10457
Feature activation-7.50e-01

Pos logit contributions
orse+0.061
ret+0.060
orses+0.058
ets+0.055
sel+0.050
Neg logit contributions
 Lu-0.056
 angels-0.046
Lu-0.044
 attendant-0.044
 firefighters-0.043
Token skirt
Token ID23967
Feature activation-7.72e-01

Pos logit contributions
orse+0.031
ret+0.031
orses+0.030
ets+0.027
sel+0.025
Neg logit contributions
 Lu-0.035
 angels-0.029
Lu-0.027
 firefighters-0.027
 attendant-0.027
Token in
Token ID287
Feature activation+4.40e-01

Pos logit contributions
ret+0.037
orse+0.036
orses+0.034
 peanut+0.031
ets+0.030
Neg logit contributions
 Lu-0.031
 angels-0.026
Lu-0.024
 firefighters-0.024
Ann-0.024
Token Lily
Token ID20037
Feature activation-4.15e+00

Pos logit contributions
 Lu+0.022
 angels+0.018
Ann+0.018
Lu+0.017
 youths+0.017
Neg logit contributions
ret-0.016
orse-0.016
orses-0.015
 peanut-0.014
 notebooks-0.013
Token's
Token ID338
Feature activation-1.72e+00

Pos logit contributions
ret+0.188
 AW+0.158
orse+0.157
alks+0.149
eg+0.147
Neg logit contributions
 Lu-0.154
co-0.144
Lu-0.130
 Pen-0.127
my-0.125
Token closet
Token ID21615
Feature activation-9.29e-01

Pos logit contributions
orse+0.096
ret+0.092
orses+0.092
ocus+0.081
sel+0.080
Neg logit contributions
 Lu-0.057
 angels-0.043
 attendant-0.040
Lu-0.040
 Lucy-0.039
Token.
Token ID13
Feature activation-2.43e-01

Pos logit contributions
ret+0.044
orse+0.043
orses+0.041
 peanut+0.037
ets+0.036
Neg logit contributions
 Lu-0.038
 angels-0.031
 attendant-0.030
 firefighters-0.030
Ann-0.029
Token It
Token ID632
Feature activation-8.19e-03

Pos logit contributions
ret+0.011
orse+0.010
orses+0.010
 peanut+0.009
ets+0.009
Neg logit contributions
 Lu-0.011
Ann-0.009
 angels-0.009
Lu-0.009
 firefighters-0.008
Token was
Token ID373
Feature activation-7.09e-01

Pos logit contributions
ret+0.000
orse+0.000
orses+0.000
 peanut+0.000
ets+0.000
Neg logit contributions
 Lu-0.000
 angels-0.000
Ann-0.000
Lu-0.000
 firefighters-0.000
Token the
Token ID262
Feature activation-9.05e-01

Pos logit contributions
ret+0.010
orse+0.010
orses+0.009
ets+0.008
 peanut+0.008
Neg logit contributions
 Lu-0.010
 angels-0.008
Ann-0.008
Lu-0.008
 firefighters-0.008
Token beach
Token ID10481
Feature activation-1.04e+00

Pos logit contributions
ret+0.047
orse+0.047
orses+0.043
ets+0.040
ocket+0.039
Neg logit contributions
 Lu-0.035
 angels-0.028
 firefighters-0.027
Lu-0.026
 attendant-0.026
Token.
Token ID13
Feature activation-3.07e+00

Pos logit contributions
ret+0.048
orse+0.046
orses+0.042
 peanut+0.041
ocket+0.040
Neg logit contributions
 Lu-0.044
 angels-0.037
Ann-0.034
Lu-0.034
 firefighters-0.034
Token But
Token ID887
Feature activation-3.25e+00

Pos logit contributions
orse+0.163
ret+0.160
arding+0.156
orses+0.156
ocus+0.155
Neg logit contributions
 Lu-0.085
 Barber-0.062
 youths-0.059
 Pen-0.056
 Bob-0.053
Token first
Token ID717
Feature activation-3.52e+00

Pos logit contributions
ets+0.161
ret+0.155
ork+0.154
iche+0.154
orses+0.153
Neg logit contributions
 Lu-0.105
 Barber-0.083
 Pen-0.076
 Bob-0.074
tons-0.068
Token,
Token ID11
Feature activation-4.13e+00

Pos logit contributions
iche+0.193
pler+0.187
orse+0.185
orses+0.182
ork+0.181
Neg logit contributions
 Lu-0.083
 helpers-0.062
 Barber-0.062
 youths-0.062
guard-0.060
Token he
Token ID339
Feature activation+1.23e-01

Pos logit contributions
ork+0.191
orse+0.190
ocus+0.189
orses+0.188
pler+0.188
Neg logit contributions
 Lu-0.117
 youths-0.099
 Barber-0.098
 helpers-0.096
 answer-0.092
Token had
Token ID550
Feature activation+1.27e-01

Pos logit contributions
 Lu+0.006
 angels+0.005
Ann+0.005
Lu+0.005
 firefighters+0.005
Neg logit contributions
orse-0.004
ret-0.004
orses-0.004
 peanut-0.004
ets-0.004
Token to
Token ID284
Feature activation+2.43e-02

Pos logit contributions
 Lu+0.006
 angels+0.005
Ann+0.005
Lu+0.005
 firefighters+0.005
Neg logit contributions
ret-0.005
orse-0.005
orses-0.005
 peanut-0.005
ets-0.004
Token pack
Token ID2353
Feature activation-1.00e+00

Pos logit contributions
 Lu+0.001
 angels+0.001
Ann+0.001
Lu+0.001
 firefighters+0.001
Neg logit contributions
ret-0.001
orse-0.001
orses-0.001
 peanut-0.001
ets-0.001
Token!
Token ID0
Feature activation-2.35e+00

Pos logit contributions
orse+0.054
ret+0.052
orses+0.050
pler+0.045
ocus+0.045
Neg logit contributions
 Lu-0.036
 angels-0.028
 firefighters-0.026
Lu-0.026
Ann-0.025
Token what
Token ID644
Feature activation+5.48e-01

Pos logit contributions
ret+0.014
orse+0.014
orses+0.013
ets+0.012
 peanut+0.012
Neg logit contributions
 Lu-0.017
 angels-0.014
 firefighters-0.013
Ann-0.013
Lu-0.013
Token to
Token ID284
Feature activation+9.04e-01

Pos logit contributions
 Lu+0.028
 angels+0.023
Ann+0.023
Lu+0.022
 attendant+0.022
Neg logit contributions
orse-0.021
ret-0.020
orses-0.019
 peanut-0.018
ork-0.017
Token do
Token ID466
Feature activation+1.21e-01

Pos logit contributions
 Lu+0.050
Lu+0.042
 angels+0.042
 firefighters+0.042
Ann+0.041
Neg logit contributions
orse-0.028
ret-0.027
orses-0.026
 peanut-0.025
ets-0.022
Token.
Token ID13
Feature activation-3.52e+00

Pos logit contributions
 Lu+0.006
 angels+0.005
Ann+0.005
Lu+0.005
 firefighters+0.005
Neg logit contributions
ret-0.005
orse-0.005
orses-0.004
 peanut-0.004
ets-0.004
Token
Token ID198
Feature activation-1.55e+00

Pos logit contributions
ifying+0.202
ocket+0.197
ret+0.191
ocus+0.190
ets+0.190
Neg logit contributions
 Lu-0.072
 youths-0.059
 Bob-0.057
 attendant-0.055
 Bird-0.050
Token
Token ID198
Feature activation-4.12e+00

Pos logit contributions
ret+0.075
orse+0.074
ets+0.073
 peanut+0.071
orses+0.070
Neg logit contributions
 Lu-0.058
Ann-0.046
Lu-0.044
 angels-0.043
 attendant-0.041
TokenBut
Token ID1537
Feature activation-3.48e+00

Pos logit contributions
ocket+0.199
ret+0.195
icol+0.193
ifying+0.191
ulp+0.189
Neg logit contributions
Ann-0.087
 youths-0.084
Mark-0.074
Fine-0.073
 attendant-0.072
Token then
Token ID788
Feature activation-2.05e+00

Pos logit contributions
ret+0.191
ork+0.188
ets+0.178
iche+0.177
ables+0.172
Neg logit contributions
 Lu-0.088
 Bob-0.073
 Bird-0.071
 Dog-0.071
 helpers-0.070
Token,
Token ID11
Feature activation-3.72e+00

Pos logit contributions
ret+0.106
ets+0.103
orse+0.097
orses+0.096
ork+0.095
Neg logit contributions
 Lu-0.069
 angels-0.056
 Bird-0.053
 firefighters-0.052
 Lucy-0.052
Token a
Token ID257
Feature activation+4.70e-02

Pos logit contributions
ets+0.218
ret+0.209
ocus+0.206
ard+0.205
orses+0.204
Neg logit contributions
 Lu-0.067
 helpers-0.063
 angels-0.059
 firefighters-0.059
 Bird-0.058
Token kind
Token ID1611
Feature activation-1.23e-02

Pos logit contributions
 Lu+0.002
 angels+0.002
Ann+0.002
Lu+0.002
 firefighters+0.002
Neg logit contributions
ret-0.002
orse-0.002
orses-0.002
 peanut-0.002
ets-0.002
Token pumpkin
Token ID30089
Feature activation-3.44e-01

Pos logit contributions
 Lu+0.007
Ann+0.005
 angels+0.005
Lu+0.005
 firefighters+0.005
Neg logit contributions
orse-0.010
ret-0.010
orses-0.010
 peanut-0.009
ets-0.009
Token friends
Token ID2460
Feature activation+3.49e-01

Pos logit contributions
ret+0.019
orse+0.019
orses+0.018
ets+0.017
 peanut+0.017
Neg logit contributions
 Lu-0.011
 angels-0.009
 firefighters-0.008
Lu-0.008
Ann-0.008
Token.
Token ID13
Feature activation-2.76e+00

Pos logit contributions
 Lu+0.018
Ann+0.015
 angels+0.015
Lu+0.015
 firefighters+0.015
Neg logit contributions
orse-0.013
ret-0.013
orses-0.012
 peanut-0.011
ets-0.010
Token One
Token ID1881
Feature activation-5.01e-01

Pos logit contributions
ret+0.145
ocket+0.141
orse+0.139
ifying+0.139
pler+0.136
Neg logit contributions
 Lu-0.074
 youths-0.059
 attendant-0.053
 Ann-0.053
 Lucy-0.052
Token day
Token ID1110
Feature activation-2.99e+00

Pos logit contributions
ret+0.025
orse+0.023
orses+0.023
ets+0.021
sel+0.021
Neg logit contributions
 Lu-0.020
Lu-0.016
 angels-0.016
Ann-0.015
 firefighters-0.015
Token,
Token ID11
Feature activation-4.07e+00

Pos logit contributions
ret+0.164
ets+0.155
orse+0.155
ocket+0.155
 generation+0.152
Neg logit contributions
 Lu-0.072
 angels-0.060
 youths-0.058
 helpers-0.051
 Lucy-0.046
Token a
Token ID257
Feature activation-9.90e-01

Pos logit contributions
ret+0.180
ets+0.175
pler+0.173
ork+0.173
ocus+0.171
Neg logit contributions
 helpers-0.118
 youths-0.117
 Bob-0.112
 angels-0.110
 Lu-0.105
Token big
Token ID1263
Feature activation-2.64e-01

Pos logit contributions
ret+0.044
orse+0.042
orses+0.040
ets+0.039
ocus+0.037
Neg logit contributions
 Lu-0.044
 angels-0.035
 firefighters-0.035
Lu-0.035
 youths-0.034
Token,
Token ID11
Feature activation-4.26e-02

Pos logit contributions
ret+0.013
orse+0.012
orses+0.012
ets+0.011
 peanut+0.011
Neg logit contributions
 Lu-0.011
 angels-0.008
 firefighters-0.008
Ann-0.008
Lu-0.008
Token mean
Token ID1612
Feature activation-6.79e-01

Pos logit contributions
ret+0.002
orse+0.002
orses+0.002
 peanut+0.002
ets+0.001
Neg logit contributions
 Lu-0.002
 angels-0.002
Ann-0.002
Lu-0.002
 firefighters-0.002
Token squash
Token ID34613
Feature activation-1.16e+00

Pos logit contributions
ret+0.032
orse+0.032
orses+0.031
ets+0.029
ocus+0.027
Neg logit contributions
 Lu-0.027
 angels-0.022
 firefighters-0.021
 youths-0.020
Lu-0.020
Token a
Token ID257
Feature activation-3.55e-01

Pos logit contributions
ret+0.014
orse+0.013
orses+0.013
ets+0.012
 peanut+0.011
Neg logit contributions
 Lu-0.013
 angels-0.010
Lu-0.010
Ann-0.010
 firefighters-0.010
Token fair
Token ID3148
Feature activation-4.63e-02

Pos logit contributions
ret+0.014
orse+0.014
orses+0.013
ets+0.012
 peanut+0.012
Neg logit contributions
 Lu-0.017
 angels-0.014
Lu-0.014
Ann-0.014
 firefighters-0.014
Token peanut
Token ID26636
Feature activation-3.22e-01

Pos logit contributions
ret+0.002
orse+0.002
orses+0.002
 peanut+0.002
ets+0.002
Neg logit contributions
 Lu-0.002
 angels-0.002
Ann-0.002
Lu-0.002
 firefighters-0.001
Token.
Token ID13
Feature activation-2.02e+00

Pos logit contributions
ret+0.014
orse+0.013
orses+0.013
ets+0.012
 peanut+0.012
Neg logit contributions
 Lu-0.015
 angels-0.012
Lu-0.012
Ann-0.011
 firefighters-0.011
Token It
Token ID632
Feature activation-2.27e+00

Pos logit contributions
ret+0.086
orses+0.084
ets+0.083
orse+0.083
pler+0.070
Neg logit contributions
 Lu-0.094
 Lucy-0.084
Lu-0.075
 Stev-0.073
 Kitty-0.073
Token looked
Token ID3114
Feature activation-4.05e+00

Pos logit contributions
ret+0.136
ets+0.129
orses+0.128
arding+0.127
pieces+0.127
Neg logit contributions
 Lu-0.055
Lu-0.041
 Lucy-0.041
jack-0.038
 Bird-0.037
Token so
Token ID523
Feature activation-2.56e+00

Pos logit contributions
orse+0.286
orses+0.275
ork+0.259
pler+0.258
stand+0.253
Neg logit contributions
 Lucy-0.045
 Lu-0.044
 too-0.033
 all-0.032
 along-0.027
Token tasty
Token ID25103
Feature activation-9.12e-02

Pos logit contributions
pler+0.131
ret+0.126
orse+0.125
ork+0.123
ets+0.123
Neg logit contributions
 Lu-0.077
 Lucy-0.067
 angels-0.062
 youths-0.052
Lu-0.051
Token that
Token ID326
Feature activation-1.06e+00

Pos logit contributions
ret+0.003
orse+0.003
orses+0.003
 peanut+0.003
ets+0.003
Neg logit contributions
 Lu-0.005
 angels-0.004
Ann-0.004
Lu-0.004
 firefighters-0.004
Token a
Token ID257
Feature activation-2.02e+00

Pos logit contributions
ret+0.039
orse+0.038
orses+0.036
ets+0.035
ocus+0.033
Neg logit contributions
 Lu-0.055
 angels-0.047
 Lucy-0.044
 firefighters-0.044
Lu-0.043
Token lion
Token ID18744
Feature activation-1.23e+00

Pos logit contributions
ret+0.096
ets+0.091
ocus+0.086
orse+0.085
orses+0.085
Neg logit contributions
 Lu-0.078
 angels-0.067
Lu-0.064
 firefighters-0.064
 firefighter-0.061
Token big
Token ID1263
Feature activation-1.32e+00

Pos logit contributions
ret+0.099
ets+0.092
orse+0.090
sel+0.087
orses+0.087
Neg logit contributions
 Lu-0.060
Lu-0.046
 angels-0.044
 youths-0.043
 firefighters-0.043
Token ocean
Token ID9151
Feature activation-1.31e+00

Pos logit contributions
ret+0.066
orse+0.061
orses+0.058
ets+0.057
sel+0.055
Neg logit contributions
 Lu-0.052
 angels-0.039
 youths-0.039
 Taxi-0.038
 firefighters-0.038
Token.
Token ID13
Feature activation-2.70e+00

Pos logit contributions
ret+0.067
orse+0.061
orses+0.058
ocket+0.055
ets+0.055
Neg logit contributions
 Lu-0.049
 angels-0.041
 firefighters-0.038
 youths-0.038
Lu-0.038
Token One
Token ID1881
Feature activation-8.74e-01

Pos logit contributions
ret+0.146
orse+0.142
pler+0.139
orses+0.139
ocket+0.138
Neg logit contributions
 Lu-0.072
 Lucy-0.051
 Jenkins-0.051
 youths-0.049
 Barber-0.046
Token day
Token ID1110
Feature activation-3.37e+00

Pos logit contributions
ret+0.046
orse+0.042
orses+0.041
sel+0.040
ets+0.040
Neg logit contributions
 Lu-0.032
Lu-0.024
 angels-0.023
Ann-0.023
 firefighters-0.022
Token,
Token ID11
Feature activation-3.93e+00

Pos logit contributions
ret+0.200
 generation+0.193
ocket+0.189
ets+0.188
pieces+0.186
Neg logit contributions
 Lu-0.071
 youths-0.045
 Lucy-0.043
 angels-0.040
 bud-0.039
Token P
Token ID350
Feature activation-2.35e+00

Pos logit contributions
pler+0.207
ret+0.203
ets+0.202
ocket+0.195
ox+0.195
Neg logit contributions
 Lu-0.097
 Bob-0.085
 Squirrel-0.083
 Lucy-0.083
 Beaver-0.082
Tokeninch
Token ID8589
Feature activation-1.89e+00

Pos logit contributions
orse+0.077
orses+0.069
pler+0.063
bs+0.057
ret+0.056
Neg logit contributions
 Lu-0.118
 youths-0.102
 angels-0.102
ators-0.097
Lu-0.097
Tokeny
Token ID88
Feature activation-1.98e+00

Pos logit contributions
ret+0.092
orse+0.091
orses+0.088
ocket+0.085
 peanut+0.083
Neg logit contributions
 Lu-0.059
 angels-0.048
guard-0.045
Lu-0.045
Ann-0.044
Token met
Token ID1138
Feature activation+9.11e-02

Pos logit contributions
ret+0.093
orse+0.082
orses+0.080
ocket+0.079
ifying+0.078
Neg logit contributions
 Lu-0.081
 youths-0.061
Lu-0.061
 firefighters-0.061
Ann-0.060
Token a
Token ID257
Feature activation-5.55e-01

Pos logit contributions
 Lu+0.004
 angels+0.003
Ann+0.003
Lu+0.003
 firefighters+0.003
Neg logit contributions
ret-0.004
orse-0.004
orses-0.003
 peanut-0.003
ets-0.003
Token eating
Token ID6600
Feature activation+1.56e+00

Pos logit contributions
 Lu+0.023
Lu+0.019
Ann+0.019
 firefighters+0.018
 angels+0.018
Neg logit contributions
orse-0.020
ret-0.020
orses-0.019
 peanut-0.018
ets-0.017
Token bamboo
Token ID37252
Feature activation+8.10e-01

Pos logit contributions
 Lu+0.075
 attendant+0.066
Ann+0.065
Michael+0.063
ators+0.061
Neg logit contributions
 peanut-0.058
 ol-0.054
ret-0.052
orse-0.050
orses-0.048
Token.
Token ID13
Feature activation-1.71e+00

Pos logit contributions
 Lu+0.044
Ann+0.036
 firefighters+0.035
Lu+0.035
Michael+0.035
Neg logit contributions
ret-0.027
orse-0.025
orses-0.024
ets-0.024
 peanut-0.023
Token One
Token ID1881
Feature activation+4.30e-01

Pos logit contributions
ret+0.091
orse+0.089
orses+0.086
ocket+0.083
ets+0.083
Neg logit contributions
 Lu-0.060
 Lucy-0.043
Lu-0.041
 Jenkins-0.040
Ann-0.040
Token day
Token ID1110
Feature activation-3.31e+00

Pos logit contributions
 Lu+0.022
 angels+0.018
 firefighters+0.018
Ann+0.017
 youths+0.017
Neg logit contributions
orse-0.016
ret-0.016
orses-0.015
 peanut-0.014
ets-0.013
Token,
Token ID11
Feature activation-3.93e+00

Pos logit contributions
ret+0.200
 generation+0.194
ocket+0.190
ets+0.188
pieces+0.186
Neg logit contributions
 Lu-0.072
 Lucy-0.045
 Olivia-0.043
Lu-0.035
 bud-0.034
Token P
Token ID350
Feature activation-9.92e-01

Pos logit contributions
ret+0.213
ets+0.210
pler+0.204
orses+0.198
ience+0.197
Neg logit contributions
 Lu-0.101
 Lucy-0.094
 Bunny-0.090
 Olivia-0.089
 Squirrel-0.084
Tokenandy
Token ID10757
Feature activation-7.33e-01

Pos logit contributions
orse+0.040
ret+0.038
orses+0.037
 peanut+0.034
ocket+0.032
Neg logit contributions
 Lu-0.047
 angels-0.039
Ann-0.038
Lu-0.037
co-0.036
Token met
Token ID1138
Feature activation+8.24e-01

Pos logit contributions
ret+0.027
orse+0.026
orses+0.024
ocket+0.022
 peanut+0.022
Neg logit contributions
 Lu-0.038
 angels-0.031
Ann-0.031
Lu-0.031
 firefighters-0.030
Token a
Token ID257
Feature activation+1.68e-01

Pos logit contributions
 Lu+0.044
Ann+0.037
 angels+0.037
 attendant+0.036
 firefighters+0.036
Neg logit contributions
ret-0.028
orse-0.028
 peanut-0.026
orses-0.025
ocket-0.022
Token rabbit
Token ID22746
Feature activation-6.26e-01

Pos logit contributions
 Lu+0.008
 angels+0.006
Ann+0.006
Lu+0.006
 firefighters+0.006
Neg logit contributions
orse-0.007
ret-0.007
orses-0.007
 peanut-0.006
ets-0.006
Token every
Token ID790
Feature activation+3.22e-01

Pos logit contributions
 Lu+0.015
Ann+0.012
 angels+0.012
 firefighters+0.012
Lu+0.012
Neg logit contributions
ret-0.011
orse-0.011
orses-0.010
 peanut-0.010
ets-0.010
Token day
Token ID1110
Feature activation-1.21e+00

Pos logit contributions
 Lu+0.016
 angels+0.013
Ann+0.013
Lu+0.013
 firefighters+0.012
Neg logit contributions
orse-0.013
ret-0.012
orses-0.012
 peanut-0.011
ets-0.010
Token.
Token ID13
Feature activation-1.45e+00

Pos logit contributions
ret+0.064
orse+0.060
orses+0.057
 peanut+0.054
sel+0.053
Neg logit contributions
 Lu-0.046
 angels-0.035
Lu-0.034
 Lucy-0.033
 youths-0.032
Token One
Token ID1881
Feature activation-2.25e-01

Pos logit contributions
orse+0.074
orses+0.069
ret+0.069
ets+0.063
ocket+0.063
Neg logit contributions
 Lu-0.057
 angels-0.042
 Lucy-0.042
 youths-0.042
Lu-0.041
Token day
Token ID1110
Feature activation-2.75e+00

Pos logit contributions
ret+0.010
orse+0.010
orses+0.010
ets+0.009
 peanut+0.009
Neg logit contributions
 Lu-0.010
 angels-0.008
Lu-0.008
Ann-0.008
 firefighters-0.007
Token,
Token ID11
Feature activation-3.92e+00

Pos logit contributions
orse+0.158
orses+0.153
ret+0.152
 battlefield+0.148
ets+0.148
Neg logit contributions
 Lu-0.079
 Lucy-0.057
 angels-0.055
 youths-0.048
 Pen-0.048
Token while
Token ID981
Feature activation-1.64e+00

Pos logit contributions
orse+0.198
orses+0.193
oc+0.187
ables+0.174
ets+0.174
Neg logit contributions
 Lu-0.131
 angels-0.123
 Lucy-0.123
 Zoe-0.118
 Megan-0.111
Token Av
Token ID5184
Feature activation-1.91e+00

Pos logit contributions
ret+0.081
ets+0.080
orse+0.072
ocado+0.070
sel+0.070
Neg logit contributions
 Lu-0.068
 angels-0.057
 youths-0.052
 Lucy-0.050
 Barber-0.049
Tokena
Token ID64
Feature activation-3.09e-01

Pos logit contributions
orse+0.082
ret+0.080
 peanut+0.078
orses+0.075
 lens+0.073
Neg logit contributions
 Lu-0.074
Lu-0.061
Ann-0.060
 youths-0.059
 angels-0.059
Token was
Token ID373
Feature activation-2.36e-02

Pos logit contributions
ret+0.014
orse+0.013
orses+0.012
 peanut+0.012
ets+0.011
Neg logit contributions
 Lu-0.014
 angels-0.011
Ann-0.011
Lu-0.011
 firefighters-0.011
Token playing
Token ID2712
Feature activation+8.97e-01

Pos logit contributions
ret+0.001
orse+0.001
orses+0.001
 peanut+0.001
ets+0.001
Neg logit contributions
 Lu-0.001
 angels-0.001
Ann-0.001
Lu-0.001
 firefighters-0.001
Token to
Token ID284
Feature activation-3.44e-01

Pos logit contributions
ret+0.043
orse+0.041
orses+0.038
ocket+0.036
ork+0.036
Neg logit contributions
 Lu-0.036
 angels-0.031
 youths-0.029
 firefighters-0.028
Lu-0.026
Token eat
Token ID4483
Feature activation-4.58e-01

Pos logit contributions
ret+0.015
orse+0.014
orses+0.013
ets+0.012
 peanut+0.012
Neg logit contributions
 Lu-0.016
 angels-0.013
Ann-0.012
 firefighters-0.012
Lu-0.012
Token.
Token ID13
Feature activation-1.37e+00

Pos logit contributions
ret+0.021
orse+0.020
orses+0.019
ets+0.017
ocket+0.017
Neg logit contributions
 Lu-0.020
 angels-0.017
Lu-0.016
 youths-0.015
 firefighters-0.015
Token One
Token ID1881
Feature activation-2.56e-01

Pos logit contributions
orse+0.070
ret+0.069
orses+0.066
ocket+0.065
ocus+0.063
Neg logit contributions
 Lu-0.049
 Barber-0.035
Ann-0.034
 Lucy-0.033
 angels-0.033
Token day
Token ID1110
Feature activation-3.32e+00

Pos logit contributions
ret+0.012
orse+0.011
orses+0.011
ets+0.010
 peanut+0.010
Neg logit contributions
 Lu-0.011
 angels-0.009
Ann-0.009
Lu-0.009
 firefighters-0.008
Token,
Token ID11
Feature activation-3.87e+00

Pos logit contributions
ret+0.193
 generation+0.187
ocket+0.185
orse+0.183
orses+0.182
Neg logit contributions
 Lu-0.077
 youths-0.045
 angels-0.044
 Lucy-0.044
 Olivia-0.043
Token P
Token ID350
Feature activation-2.18e+00

Pos logit contributions
ret+0.204
pler+0.202
ets+0.200
orses+0.197
ocket+0.196
Neg logit contributions
 Lu-0.095
whe-0.076
 Lucy-0.073
 Olivia-0.072
 Squirrel-0.071
Tokeningu
Token ID6680
Feature activation-1.38e+00

Pos logit contributions
orse+0.080
orses+0.069
ret+0.061
pler+0.061
 peanut+0.059
Neg logit contributions
 Lu-0.104
 angels-0.092
 youths-0.088
 Barber-0.088
ators-0.084
Token was
Token ID373
Feature activation-1.36e-01

Pos logit contributions
ret+0.057
orse+0.052
orses+0.049
ocket+0.048
ets+0.047
Neg logit contributions
 Lu-0.063
 angels-0.051
 firefighters-0.051
Lu-0.050
 youths-0.050
Token feeling
Token ID4203
Feature activation-4.63e-01

Pos logit contributions
ret+0.006
orse+0.006
orses+0.005
 peanut+0.005
ets+0.005
Neg logit contributions
 Lu-0.006
 angels-0.005
Ann-0.005
Lu-0.005
 firefighters-0.005
Token tired
Token ID10032
Feature activation-2.85e-01

Pos logit contributions
ret+0.020
orse+0.019
orses+0.018
ets+0.016
ork+0.016
Neg logit contributions
 Lu-0.022
 angels-0.018
 firefighters-0.017
 youths-0.017
Lu-0.017
Token saw
Token ID2497
Feature activation+2.20e-01

Pos logit contributions
ret+0.053
orse+0.049
orses+0.046
ocket+0.043
ifying+0.042
Neg logit contributions
 Lu-0.060
Ann-0.049
Lu-0.048
 firefighters-0.048
 youths-0.047
Token a
Token ID257
Feature activation-4.29e-01

Pos logit contributions
 Lu+0.011
 angels+0.009
Ann+0.009
Lu+0.009
 youths+0.008
Neg logit contributions
orse-0.008
ret-0.008
orses-0.008
 peanut-0.008
ets-0.007
Token new
Token ID649
Feature activation+1.15e+00

Pos logit contributions
ret+0.019
orse+0.019
orses+0.018
ets+0.016
ocket+0.016
Neg logit contributions
 Lu-0.019
 angels-0.015
Lu-0.015
 firefighters-0.015
Ann-0.015
Token toy
Token ID13373
Feature activation-7.51e-01

Pos logit contributions
 Lu+0.054
Ann+0.045
Lu+0.043
Michael+0.043
 angels+0.042
Neg logit contributions
orse-0.046
ret-0.045
 peanut-0.044
ork-0.041
orses-0.040
Token in
Token ID287
Feature activation+5.34e-01

Pos logit contributions
ret+0.034
orse+0.033
orses+0.032
ets+0.029
 peanut+0.028
Neg logit contributions
 Lu-0.032
 angels-0.027
 firefighters-0.026
Ann-0.025
 youths-0.025
Token Lily
Token ID20037
Feature activation-3.86e+00

Pos logit contributions
 Lu+0.026
 angels+0.022
Ann+0.021
Lu+0.021
co+0.021
Neg logit contributions
ret-0.020
orse-0.020
 peanut-0.018
orses-0.018
 notebooks-0.016
Token's
Token ID338
Feature activation-1.23e+00

Pos logit contributions
ret+0.167
orse+0.134
 AW+0.132
sel+0.127
orses+0.126
Neg logit contributions
 Lu-0.154
co-0.140
 Lucy-0.126
 angels-0.125
 Pen-0.125
Token part
Token ID636
Feature activation+1.51e-01

Pos logit contributions
orse+0.073
ret+0.073
orses+0.071
sel+0.065
ets+0.064
Neg logit contributions
 Lu-0.035
 angels-0.025
 firefighters-0.024
 attendant-0.024
 taxis-0.023
Token.
Token ID13
Feature activation-1.24e-01

Pos logit contributions
 Lu+0.006
 angels+0.005
Ann+0.005
Lu+0.005
 firefighters+0.005
Neg logit contributions
ret-0.007
orse-0.007
orses-0.007
 peanut-0.006
ets-0.006
Token It
Token ID632
Feature activation+1.18e-01

Pos logit contributions
ret+0.005
orse+0.005
orses+0.005
 peanut+0.004
ets+0.004
Neg logit contributions
 Lu-0.006
 angels-0.005
Ann-0.005
Lu-0.005
 firefighters-0.005
Token was
Token ID373
Feature activation-6.85e-01

Pos logit contributions
 Lu+0.006
 angels+0.005
Ann+0.004
Lu+0.004
 firefighters+0.004
Neg logit contributions
ret-0.005
orse-0.005
orses-0.004
 peanut-0.004
ets-0.004
Token
Token ID198
Feature activation-3.14e+00

Pos logit contributions
ret+0.077
orse+0.075
ets+0.074
 peanut+0.073
sel+0.072
Neg logit contributions
 Lu-0.058
Ann-0.046
Lu-0.045
 attendant-0.041
 angels-0.041
TokenFrom
Token ID4863
Feature activation-2.09e-01

Pos logit contributions
ret+0.167
orse+0.163
ocket+0.162
 mouths+0.153
ulp+0.152
Neg logit contributions
Ann-0.076
Lu-0.074
 Lu-0.071
 attendant-0.070
 youths-0.067
Token that
Token ID326
Feature activation-4.71e-01

Pos logit contributions
ret+0.006
orse+0.006
orses+0.006
 peanut+0.005
ets+0.005
Neg logit contributions
 Lu-0.012
 angels-0.011
Ann-0.010
Lu-0.010
 firefighters-0.010
Token day
Token ID1110
Feature activation-1.14e+00

Pos logit contributions
ret+0.022
orse+0.022
orses+0.021
ets+0.020
 peanut+0.019
Neg logit contributions
 Lu-0.019
 angels-0.015
Lu-0.015
Ann-0.015
 firefighters-0.014
Token on
Token ID319
Feature activation-1.06e+00

Pos logit contributions
ret+0.060
orse+0.060
orses+0.057
 peanut+0.054
ets+0.053
Neg logit contributions
 Lu-0.039
 angels-0.030
Ann-0.028
Lu-0.027
 youths-0.027
Token,
Token ID11
Feature activation-3.86e+00

Pos logit contributions
ret+0.051
orse+0.050
orses+0.048
ets+0.047
sel+0.046
Neg logit contributions
 Lu-0.042
 angels-0.033
 Lucy-0.032
 Luis-0.031
 firefighters-0.031
Token Jolly
Token ID40276
Feature activation-6.79e-01

Pos logit contributions
ifying+0.154
orse+0.154
ork+0.153
ocket+0.152
ox+0.151
Neg logit contributions
 youths-0.127
 helpers-0.121
 angels-0.116
 Lu-0.114
 Wise-0.111
Token and
Token ID290
Feature activation-1.46e+00

Pos logit contributions
ret+0.028
orse+0.028
orses+0.026
 peanut+0.024
ets+0.023
Neg logit contributions
 Lu-0.031
 angels-0.026
Lu-0.025
Ann-0.025
 firefighters-0.025
Token his
Token ID465
Feature activation+5.83e-01

Pos logit contributions
ret+0.081
orse+0.081
orses+0.078
ocus+0.077
ifying+0.076
Neg logit contributions
 Lu-0.042
 youths-0.034
 firefighters-0.033
 angels-0.033
 Lucy-0.030
Token friends
Token ID2460
Feature activation+1.02e+00

Pos logit contributions
 Lu+0.023
Ann+0.018
Lu+0.016
Michael+0.015
 Taxi+0.015
Neg logit contributions
ret-0.030
orse-0.030
 peanut-0.028
orses-0.028
 notebooks-0.026
Token were
Token ID547
Feature activation+1.14e+00

Pos logit contributions
 Lu+0.056
Ann+0.047
 angels+0.047
Lu+0.046
 attendant+0.046
Neg logit contributions
ret-0.033
orse-0.033
orses-0.030
ets-0.028
 peanut-0.028
Token make
Token ID787
Feature activation-1.27e+00

Pos logit contributions
 Lu+0.004
 angels+0.003
Ann+0.003
Lu+0.003
 firefighters+0.003
Neg logit contributions
ret-0.003
orse-0.003
orses-0.003
 peanut-0.003
ets-0.003
Token funny
Token ID8258
Feature activation-2.71e-01

Pos logit contributions
orse+0.057
ret+0.057
orses+0.053
ocket+0.050
ets+0.049
Neg logit contributions
 Lu-0.055
 angels-0.047
 firefighters-0.042
Ann-0.040
 Lucy-0.039
Token noises
Token ID26782
Feature activation-5.86e-01

Pos logit contributions
ret+0.012
orse+0.012
orses+0.011
 peanut+0.010
ets+0.010
Neg logit contributions
 Lu-0.012
 angels-0.010
Ann-0.009
Lu-0.009
 firefighters-0.009
Token.
Token ID13
Feature activation-2.26e+00

Pos logit contributions
ret+0.026
orse+0.025
orses+0.024
 peanut+0.022
ork+0.021
Neg logit contributions
 Lu-0.026
 angels-0.021
 firefighters-0.020
Ann-0.020
Lu-0.020
Token So
Token ID1406
Feature activation-3.10e+00

Pos logit contributions
orse+0.125
orses+0.119
ret+0.117
 peanut+0.112
ocket+0.112
Neg logit contributions
 Lu-0.074
 attendant-0.052
 firefighters-0.049
 Barber-0.048
 Ann-0.048
Token,
Token ID11
Feature activation-3.85e+00

Pos logit contributions
iche+0.175
orse+0.167
ocado+0.166
orses+0.166
ret+0.162
Neg logit contributions
 Lu-0.084
 attendant-0.061
 helpers-0.061
 Luis-0.058
 Ann-0.055
Token he
Token ID339
Feature activation+5.26e-01

Pos logit contributions
iche+0.203
ocado+0.201
ork+0.194
 peanut+0.192
orse+0.190
Neg logit contributions
 Lu-0.100
 attendant-0.075
 Luis-0.075
 helpers-0.074
 angels-0.069
Token kept
Token ID4030
Feature activation+4.58e-01

Pos logit contributions
 Lu+0.028
 angels+0.023
Ann+0.023
 youths+0.022
 firefighters+0.022
Neg logit contributions
orse-0.019
ret-0.019
orses-0.017
 peanut-0.017
ets-0.016
Token rubbing
Token ID27714
Feature activation-3.17e-01

Pos logit contributions
 Lu+0.022
Ann+0.018
Lu+0.018
 angels+0.018
 firefighters+0.017
Neg logit contributions
orse-0.019
ret-0.018
orses-0.017
 peanut-0.016
ets-0.015
Token and
Token ID290
Feature activation-3.91e-01

Pos logit contributions
ret+0.014
orse+0.014
orses+0.013
 peanut+0.012
ets+0.012
Neg logit contributions
 Lu-0.015
 angels-0.012
Ann-0.011
Lu-0.011
 firefighters-0.011
Token rubbing
Token ID27714
Feature activation-2.79e-01

Pos logit contributions
ret+0.017
orse+0.017
orses+0.016
 peanut+0.015
ets+0.015
Neg logit contributions
 Lu-0.017
 angels-0.014
Ann-0.014
Lu-0.013
 firefighters-0.013
Token a
Token ID257
Feature activation+4.11e-01

Pos logit contributions
 Lu+0.060
Ann+0.053
Lu+0.051
 youths+0.050
 attendant+0.050
Neg logit contributions
orse-0.036
 peanut-0.035
ret-0.035
orses-0.032
ork-0.029
Token break
Token ID2270
Feature activation+1.02e+00

Pos logit contributions
 Lu+0.021
Ann+0.018
 angels+0.017
Lu+0.017
 youths+0.017
Neg logit contributions
orse-0.015
ret-0.015
orses-0.014
 peanut-0.013
ork-0.012
Token.
Token ID13
Feature activation-2.10e+00

Pos logit contributions
 Lu+0.055
Ann+0.048
Lu+0.047
 angels+0.046
 attendant+0.045
Neg logit contributions
ret-0.033
orse-0.031
ets-0.029
orses-0.029
 peanut-0.028
Token One
Token ID1881
Feature activation+4.04e-01

Pos logit contributions
orse+0.109
ets+0.108
ocket+0.107
ret+0.107
orses+0.106
Neg logit contributions
 Lu-0.067
 attendant-0.046
 Jenkins-0.046
 Barber-0.046
 Lucy-0.045
Token day
Token ID1110
Feature activation-3.11e+00

Pos logit contributions
 Lu+0.020
 angels+0.017
Ann+0.017
 youths+0.016
 firefighters+0.016
Neg logit contributions
orse-0.016
ret-0.015
orses-0.014
 peanut-0.014
ork-0.012
Token,
Token ID11
Feature activation-3.85e+00

Pos logit contributions
ret+0.184
ets+0.180
ocket+0.179
 generation+0.176
ocado+0.175
Neg logit contributions
 Lu-0.070
 Olivia-0.040
 Lucy-0.040
 Pupp-0.037
 Dog-0.036
Token his
Token ID465
Feature activation+9.11e-01

Pos logit contributions
ets+0.221
pler+0.208
ocus+0.208
ocket+0.201
ocado+0.201
Neg logit contributions
 Lu-0.085
 Squirrel-0.082
 Bunny-0.074
 his-0.073
 Olivia-0.071
Token friend
Token ID1545
Feature activation-5.50e-01

Pos logit contributions
 Lu+0.037
Lu+0.031
Ann+0.030
 angels+0.027
 Karen+0.027
Neg logit contributions
orse-0.043
ret-0.043
 peanut-0.040
orses-0.040
ork-0.036
Token Sammy
Token ID44067
Feature activation-5.18e-01

Pos logit contributions
ret+0.023
orse+0.022
orses+0.021
ets+0.020
ocket+0.019
Neg logit contributions
 Lu-0.026
Lu-0.021
Ann-0.021
 angels-0.021
 firefighters-0.020
Token came
Token ID1625
Feature activation+1.47e+00

Pos logit contributions
ret+0.020
orse+0.019
orses+0.018
ets+0.017
 peanut+0.016
Neg logit contributions
 Lu-0.026
Lu-0.021
 angels-0.021
Ann-0.021
 firefighters-0.020
Token over
Token ID625
Feature activation+2.54e-01

Pos logit contributions
 Lu+0.074
Ann+0.062
Lu+0.060
 angels+0.060
 pastor+0.059
Neg logit contributions
ret-0.052
orse-0.050
orses-0.046
's-0.045
 peanut-0.045
Token was
Token ID373
Feature activation-1.60e+00

Pos logit contributions
ret+0.048
orse+0.047
orses+0.046
ets+0.044
ocket+0.041
Neg logit contributions
 Lu-0.038
Ann-0.029
Lu-0.029
 angels-0.028
 attendant-0.028
Token a
Token ID257
Feature activation-2.93e+00

Pos logit contributions
ret+0.084
orse+0.084
orses+0.080
ets+0.075
oc+0.071
Neg logit contributions
 Lu-0.057
 firefighters-0.047
 angels-0.046
 attendant-0.043
 Lucy-0.042
Token big
Token ID1263
Feature activation-2.12e+00

Pos logit contributions
ret+0.138
ets+0.131
orses+0.128
orse+0.128
ocus+0.116
Neg logit contributions
 Lu-0.108
 attendant-0.099
 angels-0.098
 firefighter-0.098
 firefighters-0.097
Token card
Token ID2657
Feature activation-1.65e+00

Pos logit contributions
ret+0.098
orse+0.094
orses+0.092
ets+0.083
earing+0.077
Neg logit contributions
 Lu-0.082
 angels-0.072
 attendant-0.070
 angel-0.070
 firefighters-0.070
Token with
Token ID351
Feature activation-3.33e+00

Pos logit contributions
ret+0.081
orse+0.074
orses+0.073
ets+0.066
ocus+0.064
Neg logit contributions
 Lu-0.064
 angels-0.054
 attendant-0.052
 firefighters-0.051
Lu-0.051
Token a
Token ID257
Feature activation-3.83e+00

Pos logit contributions
orse+0.197
ret+0.186
orses+0.179
ossom+0.172
ork+0.171
Neg logit contributions
 Lu-0.085
 angels-0.084
 firefighters-0.082
 Lucy-0.067
 youths-0.065
Token picture
Token ID4286
Feature activation-8.54e-01

Pos logit contributions
ret+0.163
ets+0.147
orse+0.145
orses+0.140
earing+0.136
Neg logit contributions
 Lu-0.146
 angels-0.140
 attendant-0.135
 firefighters-0.132
 firefighter-0.130
Token of
Token ID286
Feature activation-1.55e+00

Pos logit contributions
ret+0.046
orse+0.045
orses+0.043
 peanut+0.040
ets+0.039
Neg logit contributions
 Lu-0.029
 angels-0.023
 firefighters-0.021
Ann-0.021
Lu-0.021
Token a
Token ID257
Feature activation-3.09e+00

Pos logit contributions
ret+0.081
orse+0.080
orses+0.075
ets+0.073
ork+0.070
Neg logit contributions
 Lu-0.056
 angels-0.048
 firefighters-0.046
 Lucy-0.042
 youths-0.041
Token rainbow
Token ID27223
Feature activation-2.28e+00

Pos logit contributions
ret+0.139
orse+0.123
ets+0.121
orses+0.117
earing+0.116
Neg logit contributions
 Lu-0.125
 angels-0.116
 firefighters-0.113
 attendant-0.109
 firefighter-0.108
Token.
Token ID13
Feature activation-2.80e-01

Pos logit contributions
ret+0.118
orse+0.112
orses+0.107
fortable+0.095
ocket+0.094
Neg logit contributions
 Lu-0.078
 angels-0.069
co-0.060
 attendant-0.060
 firefighters-0.060
Token chase
Token ID15505
Feature activation-2.94e+00

Pos logit contributions
 Lu+0.009
 angels+0.008
Ann+0.008
Lu+0.008
 firefighters+0.007
Neg logit contributions
orse-0.007
ret-0.007
orses-0.007
 peanut-0.006
ets-0.006
Token Jolly
Token ID40276
Feature activation-1.35e+00

Pos logit contributions
orse+0.162
ret+0.152
inkle+0.151
ocket+0.149
orses+0.149
Neg logit contributions
 Lu-0.084
 youths-0.078
 firefighters-0.056
lo-0.054
 Bob-0.054
Token and
Token ID290
Feature activation-1.72e+00

Pos logit contributions
orse+0.060
ret+0.059
orses+0.055
 peanut+0.052
ocket+0.051
Neg logit contributions
 Lu-0.058
 angels-0.050
 youths-0.046
Lu-0.045
co-0.045
Token his
Token ID465
Feature activation-2.80e-01

Pos logit contributions
ret+0.086
orse+0.076
orses+0.073
sel+0.072
ocket+0.071
Neg logit contributions
 Lu-0.070
 firefighters-0.060
 angels-0.058
 Lucy-0.056
jack-0.053
Token friends
Token ID2460
Feature activation-5.78e-03

Pos logit contributions
ret+0.016
orse+0.016
orses+0.015
ets+0.015
 peanut+0.014
Neg logit contributions
 Lu-0.008
 angels-0.006
 firefighters-0.006
Lu-0.006
 youths-0.006
Token.
Token ID13
Feature activation-3.83e+00

Pos logit contributions
ret+0.000
orse+0.000
orses+0.000
 peanut+0.000
ets+0.000
Neg logit contributions
 Lu-0.000
 angels-0.000
Ann-0.000
Lu-0.000
 firefighters-0.000
Token They
Token ID1119
Feature activation+7.54e-01

Pos logit contributions
ifying+0.186
ocket+0.184
ret+0.182
orse+0.176
ork+0.170
Neg logit contributions
 Lu-0.102
 youths-0.101
 Bob-0.091
 attendant-0.087
 Beaver-0.082
Token were
Token ID547
Feature activation+5.02e-01

Pos logit contributions
 Lu+0.039
 angels+0.033
Ann+0.033
Lu+0.033
 attendant+0.031
Neg logit contributions
orse-0.026
ret-0.026
orses-0.024
 peanut-0.023
ets-0.022
Token scared
Token ID12008
Feature activation-1.40e-01

Pos logit contributions
 Lu+0.025
Lu+0.020
Ann+0.020
 angels+0.020
 attendant+0.019
Neg logit contributions
orse-0.019
ret-0.019
orses-0.018
 peanut-0.017
ets-0.016
Token and
Token ID290
Feature activation-8.05e-01

Pos logit contributions
ret+0.006
orse+0.006
orses+0.005
 peanut+0.005
ets+0.005
Neg logit contributions
 Lu-0.007
 angels-0.005
Ann-0.005
Lu-0.005
 firefighters-0.005
Token didn
Token ID1422
Feature activation+3.72e-01

Pos logit contributions
ret+0.035
orse+0.033
orses+0.032
ork+0.030
 peanut+0.029
Neg logit contributions
 Lu-0.037
 firefighters-0.030
 angels-0.030
 youths-0.029
Ann-0.028
Token's
Token ID338
Feature activation-2.43e+00

Pos logit contributions
ret+0.106
orse+0.092
ork+0.088
orses+0.087
 AW+0.085
Neg logit contributions
 Lu-0.129
co-0.116
 Lucy-0.113
ma-0.112
Ann-0.111
Token purse
Token ID27517
Feature activation-1.00e+00

Pos logit contributions
orse+0.145
ret+0.140
orses+0.139
plets+0.127
arding+0.123
Neg logit contributions
 Lu-0.059
 firefighters-0.051
 angels-0.051
 helpers-0.050
 ambulance-0.048
Token.
Token ID13
Feature activation-1.18e+00

Pos logit contributions
ret+0.049
orse+0.048
orses+0.046
 peanut+0.041
ets+0.041
Neg logit contributions
 Lu-0.039
 angels-0.031
Ann-0.030
Lu-0.030
 attendant-0.030
Token It
Token ID632
Feature activation-1.64e+00

Pos logit contributions
ret+0.060
orse+0.060
orses+0.059
ets+0.053
ocket+0.051
Neg logit contributions
 Lu-0.047
 youths-0.033
 Lucy-0.033
 Pen-0.032
 firefighters-0.032
Token has
Token ID468
Feature activation-2.29e+00

Pos logit contributions
orse+0.084
ret+0.081
orses+0.080
ets+0.072
alks+0.071
Neg logit contributions
 Lu-0.059
Ann-0.046
 Lucy-0.045
 angels-0.045
 Ann-0.043
Token a
Token ID257
Feature activation-3.81e+00

Pos logit contributions
orse+0.129
ret+0.124
orses+0.119
inkle+0.106
ossom+0.106
Neg logit contributions
 Lu-0.072
 angels-0.064
 firefighters-0.062
 taxis-0.054
Ann-0.053
Token picture
Token ID4286
Feature activation-4.50e-01

Pos logit contributions
ret+0.165
orse+0.155
ets+0.154
orses+0.154
iece+0.139
Neg logit contributions
 Lu-0.131
 angels-0.128
 angel-0.124
 attendant-0.124
 firefighter-0.123
Token of
Token ID286
Feature activation-9.49e-01

Pos logit contributions
ret+0.024
orse+0.024
orses+0.022
 peanut+0.021
ets+0.020
Neg logit contributions
 Lu-0.016
 angels-0.012
Ann-0.012
Lu-0.011
 firefighters-0.011
Token his
Token ID465
Feature activation-2.38e+00

Pos logit contributions
ret+0.046
orse+0.045
orses+0.042
ets+0.040
ork+0.039
Neg logit contributions
 Lu-0.038
 angels-0.032
 firefighters-0.030
 youths-0.028
Ann-0.028
Token mom
Token ID1995
Feature activation-2.62e+00

Pos logit contributions
ret+0.122
orse+0.117
orses+0.111
sel+0.106
ets+0.105
Neg logit contributions
 Lu-0.080
 angels-0.075
 firefighters-0.065
 helpers-0.064
 youths-0.064
Token and
Token ID290
Feature activation-1.16e+00

Pos logit contributions
ret+0.096
orse+0.087
orses+0.081
ork+0.080
ulp+0.076
Neg logit contributions
 Lu-0.127
 Lucy-0.108
Ann-0.105
 Ann-0.105
co-0.104
Token card
Token ID2657
Feature activation-1.34e+00

Pos logit contributions
ret+0.041
orse+0.040
orses+0.039
ets+0.037
ocus+0.034
Neg logit contributions
 Lu-0.039
 angels-0.031
Lu-0.030
 firefighters-0.030
 attendant-0.029
Token on
Token ID319
Feature activation-5.62e-01

Pos logit contributions
ret+0.068
orse+0.063
orses+0.062
ets+0.057
ocus+0.055
Neg logit contributions
 Lu-0.049
 angels-0.041
 firefighters-0.040
Lu-0.039
 attendant-0.039
Token the
Token ID262
Feature activation-2.71e+00

Pos logit contributions
orse+0.027
ret+0.027
orses+0.026
ets+0.024
ocket+0.023
Neg logit contributions
 Lu-0.023
Lu-0.018
Ann-0.018
 angels-0.018
 firefighters-0.017
Token floor
Token ID4314
Feature activation-1.03e+00

Pos logit contributions
orse+0.140
ret+0.138
orses+0.133
bs+0.129
ocus+0.119
Neg logit contributions
 Lu-0.090
 angels-0.087
 attendant-0.087
 firefighters-0.082
 angel-0.077
Token.
Token ID13
Feature activation+4.24e-01

Pos logit contributions
ret+0.050
orse+0.048
orses+0.046
 peanut+0.043
ets+0.042
Neg logit contributions
 Lu-0.040
 angels-0.032
Lu-0.031
Ann-0.031
 firefighters-0.030
Token The
Token ID383
Feature activation-3.81e+00

Pos logit contributions
 Lu+0.024
 angels+0.021
Ann+0.020
Lu+0.020
 youths+0.020
Neg logit contributions
orse-0.013
ret-0.013
orses-0.012
 peanut-0.011
ets-0.010
Token card
Token ID2657
Feature activation-1.46e+00

Pos logit contributions
orse+0.190
ret+0.185
orses+0.183
ience+0.181
ifying+0.176
Neg logit contributions
 lady-0.109
 angels-0.106
 attendant-0.103
 firefighters-0.100
 helpers-0.092
Token had
Token ID550
Feature activation-2.56e+00

Pos logit contributions
ret+0.071
orse+0.068
orses+0.067
ets+0.064
ifying+0.059
Neg logit contributions
 Lu-0.055
 angels-0.046
 attendant-0.043
Lu-0.043
Ann-0.043
Token a
Token ID257
Feature activation-3.25e+00

Pos logit contributions
orse+0.156
orses+0.147
ret+0.145
oppy+0.137
oc+0.136
Neg logit contributions
 firefighters-0.061
 Lu-0.060
 angels-0.060
 taxis-0.044
 Ann-0.043
Token big
Token ID1263
Feature activation-2.57e+00

Pos logit contributions
ret+0.162
ets+0.160
orses+0.159
orse+0.158
iece+0.143
Neg logit contributions
 Lu-0.093
 angels-0.092
 bud-0.087
 attendant-0.085
 firefighters-0.085
Token,
Token ID11
Feature activation-2.09e+00

Pos logit contributions
ret+0.117
orses+0.115
orse+0.113
ets+0.106
pieces+0.098
Neg logit contributions
 Lu-0.086
 bud-0.085
 angels-0.083
 angel-0.079
 firefighters-0.075
Token a
Token ID257
Feature activation-2.34e-01

Pos logit contributions
 Lu+0.034
Lu+0.028
Ann+0.028
 angels+0.027
 youths+0.026
Neg logit contributions
ret-0.024
orse-0.024
orses-0.022
 peanut-0.021
ets-0.020
Token big
Token ID1263
Feature activation+4.40e-02

Pos logit contributions
ret+0.010
orse+0.010
orses+0.009
ets+0.008
 peanut+0.008
Neg logit contributions
 Lu-0.011
 angels-0.009
Ann-0.009
Lu-0.009
 firefighters-0.009
Token ice
Token ID4771
Feature activation+7.45e-02

Pos logit contributions
 Lu+0.002
 angels+0.002
Ann+0.002
Lu+0.002
 firefighters+0.002
Neg logit contributions
ret-0.002
orse-0.002
orses-0.002
 peanut-0.002
ets-0.002
Token cream
Token ID8566
Feature activation-7.93e-01

Pos logit contributions
 Lu+0.003
 angels+0.002
Ann+0.002
Lu+0.002
 firefighters+0.002
Neg logit contributions
ret-0.004
orse-0.004
orses-0.004
 peanut-0.004
ets-0.003
Token in
Token ID287
Feature activation-3.98e-01

Pos logit contributions
ret+0.040
orse+0.039
orses+0.037
ets+0.034
 peanut+0.032
Neg logit contributions
 Lu-0.031
 angels-0.025
 firefighters-0.024
Ann-0.023
 attendant-0.023
Token Ben
Token ID3932
Feature activation-3.80e+00

Pos logit contributions
ret+0.018
orse+0.018
orses+0.017
ets+0.016
 peanut+0.015
Neg logit contributions
 Lu-0.018
Ann-0.014
 angels-0.014
Lu-0.014
 firefighters-0.013
Token's
Token ID338
Feature activation-1.93e+00

Pos logit contributions
ret+0.160
 AW+0.137
orse+0.124
alks+0.123
ocus+0.122
Neg logit contributions
 Lu-0.149
 Pen-0.137
 youths-0.127
 Dog-0.126
co-0.123
Token hand
Token ID1021
Feature activation-1.03e+00

Pos logit contributions
ret+0.100
orse+0.096
orses+0.093
arding+0.084
ets+0.083
Neg logit contributions
 Lu-0.063
 firefighters-0.051
 angels-0.050
 attendant-0.049
 Taxi-0.049
Token and
Token ID290
Feature activation-8.35e-01

Pos logit contributions
ret+0.049
orse+0.047
orses+0.045
 peanut+0.041
ets+0.039
Neg logit contributions
 Lu-0.042
 angels-0.034
Ann-0.032
 firefighters-0.032
co-0.032
Token a
Token ID257
Feature activation-8.93e-01

Pos logit contributions
ret+0.039
orse+0.036
orses+0.035
ets+0.032
ork+0.032
Neg logit contributions
 Lu-0.037
 angels-0.030
 firefighters-0.030
Ann-0.028
 youths-0.027
Token new
Token ID649
Feature activation+8.57e-01

Pos logit contributions
ret+0.039
orse+0.037
orses+0.035
ets+0.034
sel+0.031
Neg logit contributions
 Lu-0.040
 angels-0.034
 firefighters-0.032
Lu-0.032
Ann-0.032
Token puts
Token ID7584
Feature activation-1.76e+00

Pos logit contributions
 Lu+0.017
 angels+0.014
Lu+0.014
Ann+0.013
 firefighters+0.013
Neg logit contributions
ret-0.012
orse-0.011
orses-0.011
 peanut-0.010
ets-0.010
Token a
Token ID257
Feature activation-2.77e+00

Pos logit contributions
orse+0.091
orses+0.086
ret+0.079
ets+0.076
ocus+0.073
Neg logit contributions
 Lu-0.068
 angels-0.056
 Lucy-0.052
 firefighters-0.051
Ann-0.050
Token shiny
Token ID22441
Feature activation-2.27e+00

Pos logit contributions
orses+0.123
ret+0.123
orse+0.122
ets+0.120
ocus+0.107
Neg logit contributions
 Lu-0.093
 firefighter-0.088
 angels-0.085
 angel-0.081
 bud-0.080
Token sticker
Token ID27735
Feature activation-1.37e+00

Pos logit contributions
orse+0.104
orses+0.104
ret+0.098
cious+0.088
ets+0.085
Neg logit contributions
 Lu-0.086
 angels-0.074
 firefighter-0.071
 angel-0.070
 firefighters-0.069
Token on
Token ID319
Feature activation-2.59e+00

Pos logit contributions
orse+0.076
ret+0.074
orses+0.073
 peanut+0.065
ets+0.063
Neg logit contributions
 Lu-0.042
 angels-0.035
 attendant-0.031
Ann-0.030
co-0.030
Token Ben
Token ID3932
Feature activation-3.80e+00

Pos logit contributions
orse+0.144
orses+0.141
ret+0.134
ets+0.131
ocus+0.128
Neg logit contributions
 Lu-0.087
 Lucy-0.071
Ann-0.064
 Ann-0.063
Lu-0.063
Token's
Token ID338
Feature activation-2.76e+00

Pos logit contributions
ret+0.139
orse+0.126
orses+0.125
 seas+0.121
 AW+0.118
Neg logit contributions
 Lu-0.158
co-0.139
 Pen-0.136
 angels-0.133
 Lucy-0.130
Token folder
Token ID9483
Feature activation-1.22e+00

Pos logit contributions
ret+0.115
orse+0.115
orses+0.114
ocus+0.104
iche+0.098
Neg logit contributions
 angels-0.096
 Lu-0.090
 angel-0.089
 attendant-0.082
 firefighters-0.081
Token.
Token ID13
Feature activation-1.01e+00

Pos logit contributions
ret+0.056
orse+0.056
orses+0.053
 peanut+0.048
ocus+0.045
Neg logit contributions
 Lu-0.050
 angels-0.040
Lu-0.038
 attendant-0.038
Ann-0.038
Token Ben
Token ID3932
Feature activation-6.36e-01

Pos logit contributions
ret+0.048
orse+0.047
orses+0.044
ets+0.042
ocket+0.041
Neg logit contributions
 Lu-0.043
Ann-0.033
Lu-0.032
 Lucy-0.032
 youths-0.032
Token feels
Token ID5300
Feature activation-1.85e+00

Pos logit contributions
orse+0.026
ret+0.026
orses+0.024
 peanut+0.022
ork+0.022
Neg logit contributions
 Lu-0.030
 angels-0.024
Ann-0.024
 youths-0.023
 firefighters-0.023
Tokenitty
Token ID9760
Feature activation-8.23e-02

Pos logit contributions
 Lu+0.041
 angels+0.031
 firefighters+0.031
Ann+0.030
Lu+0.029
Neg logit contributions
orse-0.047
ret-0.047
orses-0.044
 peanut-0.041
ocus-0.039
Token never
Token ID1239
Feature activation-4.17e-01

Pos logit contributions
ret+0.003
orse+0.003
orses+0.003
 peanut+0.003
ets+0.003
Neg logit contributions
 Lu-0.004
 angels-0.003
Ann-0.003
Lu-0.003
 firefighters-0.003
Token delayed
Token ID11038
Feature activation+1.07e-01

Pos logit contributions
ret+0.015
orse+0.015
orses+0.014
 peanut+0.012
ork+0.012
Neg logit contributions
 Lu-0.022
 angels-0.018
Ann-0.018
Lu-0.018
 firefighters-0.017
Token playing
Token ID2712
Feature activation+1.41e+00

Pos logit contributions
 Lu+0.005
 angels+0.004
Ann+0.004
Lu+0.004
 firefighters+0.004
Neg logit contributions
ret-0.004
orse-0.004
orses-0.004
 peanut-0.004
ets-0.004
Token with
Token ID351
Feature activation+2.61e-01

Pos logit contributions
 Lu+0.077
Ann+0.067
Lu+0.064
 angels+0.064
 Taxi+0.064
Neg logit contributions
orse-0.039
ret-0.038
 peanut-0.034
orses-0.034
ork-0.033
Token the
Token ID262
Feature activation+1.99e+00

Pos logit contributions
 Lu+0.012
 angels+0.010
Ann+0.009
Lu+0.009
 firefighters+0.009
Neg logit contributions
ret-0.011
orse-0.011
orses-0.010
 peanut-0.010
ets-0.009
Token jar
Token ID17379
Feature activation+1.54e-02

Pos logit contributions
 Lu+0.086
Ann+0.073
Lu+0.067
ators+0.066
Michael+0.064
Neg logit contributions
 peanut-0.081
ret-0.077
orse-0.075
orses-0.072
 ink-0.069
Token again
Token ID757
Feature activation-3.29e-01

Pos logit contributions
 Lu+0.001
 angels+0.001
Ann+0.001
Lu+0.001
 firefighters+0.001
Neg logit contributions
ret-0.001
orse-0.001
orses-0.001
 peanut-0.001
ets-0.001
Token.
Token ID13
Feature activation-2.11e-01

Pos logit contributions
ret+0.014
orse+0.014
orses+0.013
 peanut+0.012
ets+0.012
Neg logit contributions
 Lu-0.015
 angels-0.012
Ann-0.012
Lu-0.012
 firefighters-0.012
Token<|endoftext|>
Token ID50256
Feature activation+9.92e-01

Pos logit contributions
ret+0.008
orse+0.008
orses+0.007
 peanut+0.007
ets+0.007
Neg logit contributions
 Lu-0.011
 angels-0.009
Ann-0.009
Lu-0.009
 firefighters-0.009
TokenOnce
Token ID7454
Feature activation-4.96e-01

Pos logit contributions
 Lu+0.049
 angels+0.042
 firefighters+0.042
 youths+0.040
 attendant+0.039
Neg logit contributions
ret-0.037
orse-0.036
orses-0.033
 peanut-0.031
ork-0.030
Token big
Token ID1263
Feature activation+4.36e-01

Pos logit contributions
 Lu+0.004
 angels+0.003
Ann+0.003
Lu+0.003
 firefighters+0.003
Neg logit contributions
ret-0.003
orse-0.003
orses-0.003
 peanut-0.003
ets-0.003
Token bathroom
Token ID12436
Feature activation-5.27e-01

Pos logit contributions
 Lu+0.021
Ann+0.017
 angels+0.017
Lu+0.017
 youths+0.016
Neg logit contributions
orse-0.018
ret-0.017
orses-0.016
 peanut-0.016
ets-0.015
Token.
Token ID13
Feature activation+3.44e-01

Pos logit contributions
ret+0.023
orse+0.023
orses+0.021
 peanut+0.019
ets+0.019
Neg logit contributions
 Lu-0.024
 angels-0.019
Lu-0.019
 firefighters-0.019
Ann-0.019
Token A
Token ID317
Feature activation+7.00e-01

Pos logit contributions
 Lu+0.020
 angels+0.018
Ann+0.017
Lu+0.017
 firefighters+0.017
Neg logit contributions
orse-0.010
ret-0.010
orses-0.009
 peanut-0.008
ets-0.007
Token family
Token ID1641
Feature activation+1.40e-01

Pos logit contributions
 Lu+0.038
Ann+0.032
 angels+0.032
Lu+0.031
co+0.031
Neg logit contributions
orse-0.023
ret-0.022
orses-0.020
 peanut-0.020
ork-0.018
Token of
Token ID286
Feature activation+2.03e+00

Pos logit contributions
 Lu+0.007
 angels+0.005
Ann+0.005
Lu+0.005
 firefighters+0.005
Neg logit contributions
ret-0.006
orse-0.006
orses-0.005
 peanut-0.005
ets-0.005
Token ducks
Token ID39694
Feature activation-3.93e-01

Pos logit contributions
 Lu+0.092
Ann+0.086
 attendant+0.082
Lu+0.079
K+0.079
Neg logit contributions
 peanut-0.072
 notebooks-0.068
 ol-0.067
 ink-0.067
ret-0.065
Token lived
Token ID5615
Feature activation+9.54e-01

Pos logit contributions
ret+0.016
orse+0.016
orses+0.015
 peanut+0.014
ork+0.013
Neg logit contributions
 Lu-0.019
 angels-0.015
Ann-0.015
Lu-0.015
 firefighters-0.015
Token in
Token ID287
Feature activation+5.68e-01

Pos logit contributions
 Lu+0.049
Ann+0.042
Lu+0.040
 Taxi+0.039
Michael+0.039
Neg logit contributions
ret-0.034
orse-0.033
orses-0.031
 peanut-0.029
ets-0.027
Token this
Token ID428
Feature activation-4.91e-01

Pos logit contributions
 Lu+0.029
 angels+0.024
Ann+0.024
Lu+0.024
co+0.023
Neg logit contributions
ret-0.020
orse-0.020
orses-0.018
 peanut-0.017
ork-0.016
Token house
Token ID2156
Feature activation-3.31e-01

Pos logit contributions
ret+0.025
orse+0.025
orses+0.023
ets+0.022
ocket+0.021
Neg logit contributions
 Lu-0.019
 angels-0.015
 firefighters-0.014
Ann-0.014
Lu-0.014
Token steep
Token ID14559
Feature activation+1.41e+00

Pos logit contributions
 Lu+0.106
Ann+0.093
Lu+0.093
 youths+0.093
 angels+0.089
Neg logit contributions
orse-0.054
 peanut-0.051
ret-0.049
orses-0.047
 mouth-0.045
Token.
Token ID13
Feature activation-6.81e-01

Pos logit contributions
 Lu+0.085
Lu+0.072
Ann+0.072
 youths+0.069
 angels+0.069
Neg logit contributions
ret-0.035
orse-0.034
ets-0.033
orses-0.031
 peanut-0.030
Token They
Token ID1119
Feature activation+3.48e-01

Pos logit contributions
ret+0.026
orse+0.026
orses+0.024
ets+0.023
 peanut+0.022
Neg logit contributions
 Lu-0.035
Ann-0.028
 angels-0.027
 firefighters-0.027
Lu-0.027
Token try
Token ID1949
Feature activation+1.12e+00

Pos logit contributions
 Lu+0.018
 angels+0.015
Lu+0.015
Ann+0.015
 firefighters+0.015
Neg logit contributions
ret-0.012
orse-0.012
orses-0.011
ets-0.010
 peanut-0.010
Token to
Token ID284
Feature activation+1.51e+00

Pos logit contributions
 Lu+0.062
Lu+0.054
Ann+0.054
 firefighters+0.053
 youths+0.052
Neg logit contributions
ret-0.035
orse-0.033
orses-0.030
ork-0.029
 peanut-0.027
Token go
Token ID467
Feature activation+1.89e+00

Pos logit contributions
 Lu+0.084
Lu+0.075
Ann+0.074
 angels+0.074
 youths+0.072
Neg logit contributions
orse-0.044
ret-0.040
orses-0.037
 peanut-0.033
 carve-0.033
Token up
Token ID510
Feature activation+1.46e+00

Pos logit contributions
 Lu+0.096
Lu+0.085
 pastor+0.084
 youths+0.083
Ann+0.083
Neg logit contributions
ret-0.057
s-0.053
orse-0.050
ets-0.048
ork-0.047
Token the
Token ID262
Feature activation+1.52e+00

Pos logit contributions
 Lu+0.082
Ann+0.074
Lu+0.073
 youths+0.073
 angels+0.072
Neg logit contributions
ret-0.035
orse-0.035
ork-0.032
orses-0.030
 peanut-0.029
Token hill
Token ID12788
Feature activation+6.19e-01

Pos logit contributions
 Lu+0.071
Ann+0.061
Lu+0.058
 angels+0.056
pr+0.056
Neg logit contributions
 peanut-0.057
ret-0.055
orse-0.054
orses-0.052
ork-0.052
Token.
Token ID13
Feature activation-3.16e-01

Pos logit contributions
 Lu+0.033
 angels+0.027
Ann+0.027
Lu+0.027
 firefighters+0.026
Neg logit contributions
ret-0.022
orse-0.021
orses-0.019
ets-0.018
 peanut-0.018
Token But
Token ID887
Feature activation+1.72e-01

Pos logit contributions
ret+0.012
orse+0.012
orses+0.011
 peanut+0.011
ets+0.010
Neg logit contributions
 Lu-0.016
Ann-0.013
 angels-0.013
Lu-0.013
 firefighters-0.012
Token
Token ID198
Feature activation-1.37e+00

Pos logit contributions
ret+0.062
orse+0.061
ets+0.058
sel+0.057
orses+0.057
Neg logit contributions
 Lu-0.049
Ann-0.041
Lu-0.039
 angels-0.037
 Pen-0.036
TokenSo
Token ID2396
Feature activation-1.74e+00

Pos logit contributions
ret+0.076
orse+0.076
orses+0.069
ets+0.068
sel+0.067
Neg logit contributions
 Lu-0.044
Ann-0.039
Lu-0.037
 angels-0.032
 youths-0.031
Token,
Token ID11
Feature activation-1.48e+00

Pos logit contributions
orse+0.084
orses+0.078
ret+0.078
ocket+0.070
ets+0.068
Neg logit contributions
 Lu-0.074
 Lucy-0.058
 angels-0.058
Ann-0.057
 Megan-0.057
Token Sophia
Token ID39953
Feature activation+6.83e-01

Pos logit contributions
orse+0.072
ret+0.071
orses+0.068
ets+0.062
sel+0.061
Neg logit contributions
 Lu-0.062
 angels-0.049
 Lucy-0.048
Ann-0.047
 Megan-0.046
Token and
Token ID290
Feature activation+8.05e-01

Pos logit contributions
 Lu+0.036
 angels+0.031
Ann+0.030
 firefighters+0.030
 youths+0.030
Neg logit contributions
orse-0.024
ret-0.024
orses-0.021
 peanut-0.020
ets-0.020
Token Mom
Token ID11254
Feature activation+2.35e+00

Pos logit contributions
 Lu+0.036
Ann+0.031
 firefighters+0.031
co+0.031
Lu+0.031
Neg logit contributions
ret-0.030
orse-0.029
 peanut-0.029
orses-0.027
 notebooks-0.026
Tokenmy
Token ID1820
Feature activation+1.96e+00

Pos logit contributions
 Lu+0.114
 firefighters+0.101
 youths+0.101
 pastor+0.096
 firefighter+0.096
Neg logit contributions
ret-0.077
ets-0.074
's-0.074
 peanut-0.070
orse-0.070
Token went
Token ID1816
Feature activation+1.22e+00

Pos logit contributions
 Lu+0.103
 youths+0.094
 angels+0.092
 firefighters+0.092
 attendant+0.089
Neg logit contributions
ret-0.058
orse-0.055
ets-0.054
 peanut-0.050
sel-0.050
Token home
Token ID1363
Feature activation+9.96e-01

Pos logit contributions
 Lu+0.063
Lu+0.054
Ann+0.054
 angels+0.052
 youths+0.052
Neg logit contributions
ret-0.039
orse-0.038
ets-0.035
orses-0.035
ork-0.034
Token.
Token ID13
Feature activation-1.58e+00

Pos logit contributions
 Lu+0.054
Ann+0.046
Lu+0.046
 Taxi+0.045
 youths+0.044
Neg logit contributions
orse-0.031
ret-0.031
orses-0.028
ork-0.025
 peanut-0.025
Token The
Token ID383
Feature activation+6.33e-01

Pos logit contributions
orse+0.082
ret+0.078
orses+0.075
 peanut+0.068
ocket+0.068
Neg logit contributions
 Lu-0.065
Ann-0.049
 Lucy-0.049
Lu-0.047
 Pen-0.047
Token him
Token ID683
Feature activation+6.89e-02

Pos logit contributions
ret+0.007
orse+0.006
orses+0.006
 peanut+0.006
ets+0.006
Neg logit contributions
 Lu-0.007
 angels-0.006
Ann-0.005
Lu-0.005
 firefighters-0.005
Token scared
Token ID12008
Feature activation+5.31e-01

Pos logit contributions
 Lu+0.003
 angels+0.003
Ann+0.003
Lu+0.003
 firefighters+0.002
Neg logit contributions
ret-0.003
orse-0.003
orses-0.003
 peanut-0.002
ets-0.002
Token.
Token ID13
Feature activation+1.44e-02

Pos logit contributions
 Lu+0.027
Ann+0.023
Lu+0.023
 angels+0.022
 attendant+0.022
Neg logit contributions
ret-0.018
orse-0.018
orses-0.017
 peanut-0.016
ets-0.016
Token He
Token ID679
Feature activation+4.31e-01

Pos logit contributions
 Lu+0.001
 angels+0.001
Ann+0.001
Lu+0.001
 firefighters+0.001
Neg logit contributions
ret-0.001
orse-0.001
orses-0.000
 peanut-0.000
ets-0.000
Token quickly
Token ID2952
Feature activation-3.40e-01

Pos logit contributions
 Lu+0.022
 angels+0.019
Ann+0.019
Lu+0.019
 firefighters+0.018
Neg logit contributions
orse-0.015
ret-0.015
orses-0.014
 peanut-0.013
ets-0.013
Token went
Token ID1816
Feature activation+1.98e+00

Pos logit contributions
ret+0.015
orse+0.015
orses+0.014
 peanut+0.013
ets+0.012
Neg logit contributions
 Lu-0.015
 angels-0.012
Ann-0.012
Lu-0.012
 firefighters-0.012
Token back
Token ID736
Feature activation+2.05e+00

Pos logit contributions
 Lu+0.110
Ann+0.100
Lu+0.100
ators+0.098
 Stev+0.097
Neg logit contributions
ets-0.041
 drawing-0.040
ret-0.040
orse-0.039
ork-0.039
Token inside
Token ID2641
Feature activation+1.69e-01

Pos logit contributions
 Lu+0.113
Ann+0.109
Lu+0.108
 youths+0.107
 angels+0.105
Neg logit contributions
ret-0.042
orse-0.041
 peanut-0.037
's-0.037
 drawing-0.036
Token and
Token ID290
Feature activation+9.47e-02

Pos logit contributions
 Lu+0.008
 angels+0.007
Ann+0.007
Lu+0.007
 firefighters+0.007
Neg logit contributions
ret-0.007
orse-0.007
orses-0.006
 peanut-0.006
ets-0.005
Token wrapped
Token ID12908
Feature activation+8.04e-01

Pos logit contributions
 Lu+0.005
 angels+0.004
Ann+0.004
Lu+0.004
 firefighters+0.004
Neg logit contributions
ret-0.004
orse-0.004
orses-0.003
 peanut-0.003
ets-0.003
Token himself
Token ID2241
Feature activation+6.63e-01

Pos logit contributions
 Lu+0.036
Ann+0.030
 angels+0.030
Lu+0.030
 youths+0.029
Neg logit contributions
ret-0.033
orse-0.031
 peanut-0.029
orses-0.028
ets-0.027
Token for
Token ID329
Feature activation+3.46e-01

Pos logit contributions
ret+0.026
orse+0.026
orses+0.024
 peanut+0.023
ets+0.022
Neg logit contributions
 Lu-0.030
 angels-0.024
Ann-0.023
Lu-0.023
 attendant-0.023
Token the
Token ID262
Feature activation+2.16e-01

Pos logit contributions
 Lu+0.016
Ann+0.013
 angels+0.013
Lu+0.013
 youths+0.012
Neg logit contributions
orse-0.015
ret-0.015
orses-0.013
 peanut-0.013
ets-0.012
Token fun
Token ID1257
Feature activation+3.30e-01

Pos logit contributions
 Lu+0.010
Ann+0.008
 angels+0.008
Lu+0.008
 firefighters+0.008
Neg logit contributions
ret-0.009
orse-0.009
orses-0.008
 peanut-0.008
ets-0.008
Token afternoon
Token ID6672
Feature activation-6.23e-01

Pos logit contributions
 Lu+0.016
Ann+0.013
 angels+0.013
Lu+0.013
 firefighters+0.013
Neg logit contributions
orse-0.013
ret-0.013
orses-0.012
 peanut-0.011
ets-0.011
Token.
Token ID13
Feature activation-3.53e-01

Pos logit contributions
ret+0.028
orse+0.027
orses+0.025
 peanut+0.024
ets+0.023
Neg logit contributions
 Lu-0.028
 angels-0.023
Ann-0.021
 firefighters-0.021
Lu-0.021
Token He
Token ID679
Feature activation+3.35e-01

Pos logit contributions
ret+0.013
orse+0.013
orses+0.012
 peanut+0.011
ets+0.011
Neg logit contributions
 Lu-0.018
Ann-0.015
 angels-0.015
Lu-0.015
 youths-0.014
Token then
Token ID788
Feature activation-8.60e-02

Pos logit contributions
 Lu+0.017
 angels+0.014
Ann+0.013
Lu+0.013
 firefighters+0.013
Neg logit contributions
orse-0.013
ret-0.013
orses-0.012
 peanut-0.011
ets-0.011
Token bid
Token ID8406
Feature activation-8.62e-01

Pos logit contributions
ret+0.004
orse+0.004
orses+0.003
 peanut+0.003
ets+0.003
Neg logit contributions
 Lu-0.004
 angels-0.003
Ann-0.003
Lu-0.003
 firefighters-0.003
Token farewell
Token ID33458
Feature activation-1.39e+00

Pos logit contributions
orse+0.036
ret+0.034
orses+0.034
 peanut+0.032
ets+0.031
Neg logit contributions
 Lu-0.041
 angels-0.032
Ann-0.031
 attendant-0.031
Lu-0.031
Token to
Token ID284
Feature activation-2.91e-02

Pos logit contributions
ret+0.066
orse+0.065
orses+0.063
 peanut+0.058
 notebooks+0.057
Neg logit contributions
 Lu-0.056
 attendant-0.045
 angels-0.043
co-0.041
Lu-0.040
Token all
Token ID477
Feature activation+7.58e-01

Pos logit contributions
ret+0.001
orse+0.001
orses+0.001
 peanut+0.001
ets+0.001
Neg logit contributions
 Lu-0.001
 angels-0.001
Ann-0.001
Lu-0.001
 firefighters-0.001
Token
Token ID198
Feature activation+4.91e-01

Pos logit contributions
ret+0.004
orse+0.004
orses+0.004
 peanut+0.003
ets+0.003
Neg logit contributions
 Lu-0.005
 angels-0.004
Ann-0.004
Lu-0.004
 firefighters-0.004
Token
Token ID198
Feature activation+4.04e-01

Pos logit contributions
 Lu+0.024
 angels+0.021
 firefighters+0.020
 youths+0.020
Ann+0.019
Neg logit contributions
orse-0.019
ret-0.018
orses-0.017
 peanut-0.016
ork-0.015
TokenMom
Token ID29252
Feature activation+1.78e+00

Pos logit contributions
 Lu+0.019
 angels+0.016
 firefighters+0.015
Ann+0.015
 youths+0.015
Neg logit contributions
orse-0.016
ret-0.016
orses-0.015
 peanut-0.014
ork-0.013
Tokenmy
Token ID1820
Feature activation+9.56e-01

Pos logit contributions
 Lu+0.078
 angels+0.069
 youths+0.067
 firefighters+0.066
 taxis+0.063
Neg logit contributions
ret-0.071
orse-0.071
orses-0.065
's-0.064
 peanut-0.064
Token said
Token ID531
Feature activation-2.33e-01

Pos logit contributions
 Lu+0.049
 angels+0.043
 youths+0.041
 firefighters+0.041
 Taxi+0.040
Neg logit contributions
orse-0.035
ret-0.034
orses-0.031
 peanut-0.029
sel-0.027
Token,
Token ID11
Feature activation+2.68e-01

Pos logit contributions
ret+0.009
orse+0.009
orses+0.008
ets+0.007
 peanut+0.007
Neg logit contributions
 Lu-0.012
 angels-0.010
Lu-0.010
Ann-0.010
 firefighters-0.010
Token "
Token ID366
Feature activation+7.36e-01

Pos logit contributions
 Lu+0.013
 angels+0.010
Ann+0.010
Lu+0.010
 firefighters+0.010
Neg logit contributions
orse-0.011
ret-0.011
orses-0.010
 peanut-0.009
ets-0.009
TokenNo
Token ID2949
Feature activation+2.88e-01

Pos logit contributions
 Lu+0.030
 angels+0.024
 firefighters+0.023
 youths+0.022
 Taxi+0.021
Neg logit contributions
orse-0.034
ret-0.034
orses-0.032
 peanut-0.030
ets-0.030
Token,
Token ID11
Feature activation-3.02e-01

Pos logit contributions
 Lu+0.016
 angels+0.013
Ann+0.013
Lu+0.013
 firefighters+0.013
Neg logit contributions
ret-0.009
orse-0.009
orses-0.008
 peanut-0.008
ets-0.008
Token it
Token ID340
Feature activation+4.97e-01

Pos logit contributions
ret+0.010
orse+0.010
orses+0.009
 peanut+0.008
ets+0.008
Neg logit contributions
 Lu-0.017
 angels-0.014
Ann-0.014
Lu-0.013
 firefighters-0.013
Token's
Token ID338
Feature activation+3.80e-01

Pos logit contributions
 Lu+0.036
 angels+0.032
Ann+0.032
Lu+0.031
 firefighters+0.031
Neg logit contributions
ret-0.008
orse-0.007
orses-0.006
ets-0.005
 peanut-0.004
Token,
Token ID11
Feature activation-7.20e-01

Pos logit contributions
orse+0.063
ret+0.060
orses+0.059
sel+0.053
 peanut+0.053
Neg logit contributions
 Lu-0.063
 angels-0.050
 Lucy-0.047
Lu-0.045
 firefighters-0.045
Token I
Token ID314
Feature activation-5.57e-01

Pos logit contributions
ret+0.031
orse+0.029
orses+0.028
ets+0.026
ork+0.025
Neg logit contributions
 Lu-0.034
 angels-0.028
 firefighters-0.028
Ann-0.026
Lu-0.026
Token can
Token ID460
Feature activation+2.93e-01

Pos logit contributions
ret+0.024
orse+0.023
orses+0.022
 peanut+0.021
 notebooks+0.020
Neg logit contributions
 Lu-0.025
Ann-0.020
 angels-0.020
Lu-0.019
 firefighters-0.019
Token see
Token ID766
Feature activation-4.97e-01

Pos logit contributions
 Lu+0.014
Ann+0.011
 angels+0.011
Lu+0.011
 youths+0.011
Neg logit contributions
orse-0.012
ret-0.012
orses-0.011
 peanut-0.010
ets-0.010
Token something
Token ID1223
Feature activation-4.01e-01

Pos logit contributions
ret+0.021
orse+0.021
orses+0.019
ets+0.018
 peanut+0.017
Neg logit contributions
 Lu-0.024
 angels-0.020
 firefighters-0.019
Lu-0.018
Ann-0.018
Token shiny
Token ID22441
Feature activation-2.18e-01

Pos logit contributions
ret+0.017
orse+0.016
orses+0.015
 peanut+0.014
ets+0.014
Neg logit contributions
 Lu-0.019
 angels-0.016
 firefighters-0.015
Lu-0.015
Ann-0.015
Token on
Token ID319
Feature activation-9.54e-01

Pos logit contributions
ret+0.009
orse+0.009
orses+0.009
 peanut+0.008
ets+0.008
Neg logit contributions
 Lu-0.010
 angels-0.008
Ann-0.008
 firefighters-0.008
Lu-0.008
Token the
Token ID262
Feature activation-7.43e-01

Pos logit contributions
orse+0.047
ret+0.047
orses+0.045
ets+0.042
ocket+0.041
Neg logit contributions
 Lu-0.038
 angels-0.030
 firefighters-0.030
Lu-0.029
Ann-0.028
Token other
Token ID584
Feature activation-6.29e-01

Pos logit contributions
ret+0.034
orse+0.033
orses+0.031
 peanut+0.029
ocket+0.028
Neg logit contributions
 Lu-0.032
 angels-0.027
 firefighters-0.026
 attendant-0.025
Ann-0.025
Token side
Token ID1735
Feature activation-1.04e-01

Pos logit contributions
ret+0.031
orse+0.030
orses+0.028
 peanut+0.027
ocket+0.026
Neg logit contributions
 Lu-0.025
 angels-0.020
Ann-0.019
 firefighters-0.019
Lu-0.018
Token."
Token ID526
Feature activation-2.09e-01

Pos logit contributions
ret+0.004
orse+0.004
orses+0.004
 peanut+0.004
ets+0.004
Neg logit contributions
 Lu-0.005
 angels-0.004
Ann-0.004
Lu-0.004
 firefighters-0.004
Token The
Token ID383
Feature activation+8.12e-02

Pos logit contributions
ret+0.001
orse+0.001
orses+0.001
 peanut+0.001
ets+0.001
Neg logit contributions
 Lu-0.002
 angels-0.001
Ann-0.001
Lu-0.001
 firefighters-0.001
Token laser
Token ID12855
Feature activation-4.19e-01

Pos logit contributions
 Lu+0.003
 angels+0.003
Ann+0.003
Lu+0.003
 firefighters+0.003
Neg logit contributions
ret-0.004
orse-0.004
orses-0.004
 peanut-0.003
ets-0.003
Token hits
Token ID7127
Feature activation+2.20e-01

Pos logit contributions
ret+0.017
orse+0.017
orses+0.016
 peanut+0.015
ets+0.014
Neg logit contributions
 Lu-0.020
 angels-0.017
Ann-0.016
 firefighters-0.016
Lu-0.015
Token the
Token ID262
Feature activation-9.20e-01

Pos logit contributions
 Lu+0.011
 angels+0.009
Lu+0.008
Ann+0.008
 youths+0.008
Neg logit contributions
ret-0.009
orse-0.009
orses-0.008
 peanut-0.008
ets-0.007
Token cat
Token ID3797
Feature activation-1.24e+00

Pos logit contributions
ret+0.042
orse+0.041
orses+0.039
ets+0.036
ocket+0.035
Neg logit contributions
 Lu-0.039
 angels-0.033
 firefighters-0.032
 attendant-0.031
 youths-0.030
Token.
Token ID13
Feature activation-1.89e-01

Pos logit contributions
ret+0.057
orse+0.057
orses+0.054
 peanut+0.051
ocket+0.050
Neg logit contributions
 Lu-0.052
 angels-0.042
Ann-0.041
Lu-0.038
co-0.038
Token The
Token ID383
Feature activation-5.92e-01

Pos logit contributions
ret+0.006
orse+0.006
orses+0.005
 peanut+0.005
ets+0.005
Neg logit contributions
 Lu-0.011
 angels-0.009
Ann-0.009
Lu-0.009
 firefighters-0.009
Token cat
Token ID3797
Feature activation-7.93e-01

Pos logit contributions
ret+0.027
orse+0.026
orses+0.025
ets+0.023
ocket+0.022
Neg logit contributions
 Lu-0.026
 angels-0.021
 firefighters-0.021
 attendant-0.020
 youths-0.020
Token makes
Token ID1838
Feature activation-8.81e-01

Pos logit contributions
ret+0.033
orse+0.033
orses+0.030
 peanut+0.028
ocket+0.028
Neg logit contributions
 Lu-0.037
 angels-0.031
Ann-0.030
 firefighters-0.029
Lu-0.028
Token a
Token ID257
Feature activation-1.60e+00

Pos logit contributions
ret+0.042
orse+0.042
orses+0.039
ets+0.037
ocket+0.037
Neg logit contributions
 Lu-0.037
 angels-0.030
Ann-0.028
 firefighters-0.028
Lu-0.026
Token loud
Token ID7812
Feature activation-9.89e-01

Pos logit contributions
ret+0.083
orse+0.079
orses+0.075
ocket+0.074
ets+0.073
Neg logit contributions
 Lu-0.058
 angels-0.051
 firefighters-0.047
Ann-0.044
 attendant-0.044
Token as
Token ID355
Feature activation+2.77e-01

Pos logit contributions
ret+0.002
orse+0.002
orses+0.002
 peanut+0.002
ets+0.002
Neg logit contributions
 Lu-0.002
 angels-0.002
Ann-0.002
Lu-0.002
 firefighters-0.002
Token fun
Token ID1257
Feature activation-7.98e-01

Pos logit contributions
 Lu+0.013
Ann+0.011
 angels+0.011
Lu+0.011
 youths+0.010
Neg logit contributions
ret-0.011
orse-0.011
orses-0.010
 peanut-0.009
ets-0.009
Token as
Token ID355
Feature activation-5.04e-01

Pos logit contributions
ret+0.036
orse+0.034
orses+0.032
 peanut+0.030
ocket+0.029
Neg logit contributions
 Lu-0.036
 angels-0.030
 firefighters-0.028
 youths-0.028
Lu-0.027
Token the
Token ID262
Feature activation+8.55e-01

Pos logit contributions
ret+0.019
orse+0.018
orses+0.017
 peanut+0.016
ets+0.016
Neg logit contributions
 Lu-0.026
 angels-0.022
 firefighters-0.021
Lu-0.020
Ann-0.020
Token old
Token ID1468
Feature activation+8.02e-01

Pos logit contributions
 Lu+0.041
Ann+0.034
Lu+0.033
co+0.032
 angels+0.031
Neg logit contributions
orse-0.033
ret-0.033
orses-0.031
 peanut-0.031
ets-0.028
Token one
Token ID530
Feature activation+2.89e-02

Pos logit contributions
 Lu+0.036
Ann+0.030
Lu+0.029
 angels+0.029
co+0.028
Neg logit contributions
orse-0.033
ret-0.032
orses-0.031
 peanut-0.030
ets-0.028
Token.
Token ID13
Feature activation-6.12e-01

Pos logit contributions
 Lu+0.001
 angels+0.001
Ann+0.001
Lu+0.001
 firefighters+0.001
Neg logit contributions
ret-0.001
orse-0.001
orses-0.001
 peanut-0.001
ets-0.001
Token They
Token ID1119
Feature activation+3.56e-01

Pos logit contributions
ret+0.028
orse+0.027
orses+0.025
 peanut+0.024
ocket+0.024
Neg logit contributions
 Lu-0.028
Ann-0.022
Lu-0.021
 angels-0.021
 Taxi-0.021
Token learned
Token ID4499
Feature activation+6.89e-01

Pos logit contributions
 Lu+0.018
 angels+0.015
Ann+0.015
Lu+0.015
 firefighters+0.015
Neg logit contributions
ret-0.013
orse-0.013
orses-0.012
 peanut-0.011
ets-0.011
Token that
Token ID326
Feature activation+4.77e-01

Pos logit contributions
 Lu+0.038
Ann+0.033
Lu+0.032
 angels+0.031
co+0.031
Neg logit contributions
ret-0.023
orse-0.021
 peanut-0.019
orses-0.019
ets-0.018
Token sometimes
Token ID3360
Feature activation-3.40e-01

Pos logit contributions
 Lu+0.025
Ann+0.021
Lu+0.021
 angels+0.020
co+0.020
Neg logit contributions
orse-0.017
ret-0.017
orses-0.016
 peanut-0.015
ets-0.014
Tokencup
Token ID25244
Feature activation-4.45e-01

Pos logit contributions
ret+0.020
orse+0.020
orses+0.018
 peanut+0.017
ets+0.017
Neg logit contributions
 Lu-0.029
Ann-0.024
Lu-0.024
 angels-0.024
co-0.023
Tokenine
Token ID500
Feature activation-3.61e-01

Pos logit contributions
ret+0.016
orse+0.016
orses+0.015
 peanut+0.014
ets+0.014
Neg logit contributions
 Lu-0.023
 angels-0.019
Ann-0.019
Lu-0.018
 firefighters-0.018
Token!"
Token ID2474
Feature activation-1.24e+00

Pos logit contributions
ret+0.014
orse+0.014
orses+0.013
 peanut+0.012
ets+0.011
Neg logit contributions
 Lu-0.018
 angels-0.015
Ann-0.014
Lu-0.014
 firefighters-0.014
Token said
Token ID531
Feature activation+5.31e-01

Pos logit contributions
ret+0.062
orse+0.058
orses+0.056
ets+0.052
ocus+0.051
Neg logit contributions
 Lu-0.053
 Lucy-0.042
Lu-0.040
 Pen-0.039
 firefighters-0.038
Token Lily
Token ID20037
Feature activation-1.13e-01

Pos logit contributions
 Lu+0.026
 angels+0.023
Ann+0.022
 firefighters+0.021
 youths+0.021
Neg logit contributions
ret-0.020
orse-0.019
 peanut-0.018
orses-0.017
ork-0.016
Token.
Token ID13
Feature activation-6.73e-01

Pos logit contributions
ret+0.005
orse+0.005
orses+0.004
 peanut+0.004
ets+0.004
Neg logit contributions
 Lu-0.005
 angels-0.004
Ann-0.004
Lu-0.004
 firefighters-0.004
Token The
Token ID383
Feature activation+6.48e-01

Pos logit contributions
ret+0.032
orse+0.031
orses+0.030
ets+0.028
ocket+0.027
Neg logit contributions
 Lu-0.030
Lu-0.023
 Lucy-0.022
 angels-0.022
 attendant-0.022
Token por
Token ID16964
Feature activation+5.20e-01

Pos logit contributions
 Lu+0.031
 angels+0.025
Ann+0.025
Lu+0.024
ators+0.024
Neg logit contributions
orse-0.026
ret-0.026
 peanut-0.025
orses-0.024
ocket-0.022
Tokencup
Token ID25244
Feature activation-3.09e-01

Pos logit contributions
 Lu+0.020
 angels+0.016
 firefighters+0.016
 youths+0.015
Lu+0.015
Neg logit contributions
orse-0.026
ret-0.025
orses-0.024
 peanut-0.023
ets-0.022
Tokenine
Token ID500
Feature activation+1.73e-01

Pos logit contributions
ret+0.010
orse+0.010
orses+0.009
 peanut+0.009
ets+0.009
Neg logit contributions
 Lu-0.017
 angels-0.014
Ann-0.014
Lu-0.014
 firefighters-0.013
Token said
Token ID531
Feature activation+7.62e-02

Pos logit contributions
 Lu+0.008
 angels+0.007
Ann+0.007
Lu+0.007
 firefighters+0.007
Neg logit contributions
orse-0.007
ret-0.007
orses-0.006
 peanut-0.006
ets-0.006
Token of
Token ID286
Feature activation+3.44e-01

Pos logit contributions
 Lu+0.030
 angels+0.024
Lu+0.024
Ann+0.024
 youths+0.024
Neg logit contributions
ret-0.028
orse-0.028
orses-0.026
 peanut-0.024
ork-0.024
Token the
Token ID262
Feature activation-2.25e-01

Pos logit contributions
 Lu+0.017
 angels+0.014
Ann+0.014
Lu+0.014
 youths+0.013
Neg logit contributions
ret-0.013
orse-0.013
orses-0.012
 peanut-0.012
ork-0.011
Token visit
Token ID3187
Feature activation-8.14e-01

Pos logit contributions
ret+0.010
orse+0.010
orses+0.009
 peanut+0.009
ets+0.009
Neg logit contributions
 Lu-0.010
 angels-0.008
Ann-0.008
Lu-0.008
 firefighters-0.008
Token,
Token ID11
Feature activation-2.55e-01

Pos logit contributions
orse+0.033
ret+0.033
orses+0.030
 peanut+0.028
ets+0.027
Neg logit contributions
 Lu-0.040
 angels-0.032
Ann-0.031
Lu-0.031
 firefighters-0.031
Token the
Token ID262
Feature activation+1.00e+00

Pos logit contributions
ret+0.011
orse+0.011
orses+0.011
ets+0.010
 peanut+0.010
Neg logit contributions
 Lu-0.011
 angels-0.009
 firefighters-0.009
Lu-0.009
Ann-0.009
Token doctor
Token ID6253
Feature activation-3.17e-01

Pos logit contributions
 Lu+0.039
Ann+0.031
Lu+0.030
 Karen+0.029
co+0.028
Neg logit contributions
orse-0.047
ret-0.047
 peanut-0.045
orses-0.044
ork-0.042
Token opened
Token ID4721
Feature activation-1.03e-01

Pos logit contributions
ret+0.013
orse+0.012
orses+0.012
 peanut+0.011
ets+0.011
Neg logit contributions
 Lu-0.015
 angels-0.012
Ann-0.012
Lu-0.012
 firefighters-0.012
Token two
Token ID734
Feature activation-1.03e+00

Pos logit contributions
ret+0.004
orse+0.004
orses+0.004
 peanut+0.004
ets+0.004
Neg logit contributions
 Lu-0.005
 angels-0.004
Ann-0.004
Lu-0.004
 firefighters-0.004
Token pieces
Token ID5207
Feature activation-7.96e-01

Pos logit contributions
ret+0.049
orse+0.048
orses+0.044
 peanut+0.040
ork+0.039
Neg logit contributions
 Lu-0.043
 angels-0.036
 firefighters-0.034
 youths-0.034
Ann-0.032
Token of
Token ID286
Feature activation-6.62e-01

Pos logit contributions
ret+0.038
orse+0.038
orses+0.036
 peanut+0.033
ork+0.032
Neg logit contributions
 Lu-0.031
 angels-0.025
 firefighters-0.024
Ann-0.023
Lu-0.023
Token paper
Token ID3348
Feature activation-9.83e-01

Pos logit contributions
orse+0.029
ret+0.029
orses+0.027
ets+0.025
ork+0.024
Neg logit contributions
 Lu-0.030
 angels-0.025
 firefighters-0.024
Ann-0.023
Lu-0.023
Token touch
Token ID3638
Feature activation-6.19e-01

Pos logit contributions
ret+0.029
orse+0.027
orses+0.026
sel+0.025
ets+0.024
Neg logit contributions
 Lu-0.030
 angels-0.024
Ann-0.023
 youths-0.023
 firefighters-0.023
Token it
Token ID340
Feature activation-5.42e-01

Pos logit contributions
orse+0.023
ret+0.022
orses+0.021
 peanut+0.019
ets+0.018
Neg logit contributions
 Lu-0.032
 angels-0.027
Ann-0.026
 firefighters-0.026
Lu-0.026
Token or
Token ID393
Feature activation-1.26e+00

Pos logit contributions
ret+0.024
orse+0.024
orses+0.023
 peanut+0.021
sel+0.020
Neg logit contributions
 Lu-0.024
 angels-0.020
Ann-0.018
Lu-0.018
 firefighters-0.018
Token it
Token ID340
Feature activation-4.69e-01

Pos logit contributions
ret+0.053
orse+0.050
orses+0.047
sel+0.043
ork+0.043
Neg logit contributions
 Lu-0.059
 angels-0.049
 firefighters-0.047
 youths-0.046
Ann-0.045
Token will
Token ID481
Feature activation-4.00e-01

Pos logit contributions
orse+0.021
ret+0.021
orses+0.019
 peanut+0.018
ocket+0.017
Neg logit contributions
 Lu-0.021
 angels-0.017
Ann-0.016
Lu-0.016
 firefighters-0.016
Token break
Token ID2270
Feature activation-3.47e-01

Pos logit contributions
ret+0.017
orse+0.016
orses+0.015
 peanut+0.014
ets+0.014
Neg logit contributions
 Lu-0.019
 angels-0.016
Ann-0.015
 firefighters-0.015
Lu-0.015
Token."
Token ID526
Feature activation-6.54e-01

Pos logit contributions
orse+0.014
ret+0.014
orses+0.013
 peanut+0.012
ets+0.012
Neg logit contributions
 Lu-0.016
 angels-0.014
Ann-0.013
Lu-0.013
 firefighters-0.013
Token
Token ID198
Feature activation-3.49e-01

Pos logit contributions
ret+0.030
orse+0.029
orses+0.028
ets+0.027
sel+0.026
Neg logit contributions
 Lu-0.028
Ann-0.022
Lu-0.022
 angels-0.021
 Lucy-0.021
Token
Token ID198
Feature activation-3.48e-01

Pos logit contributions
ret+0.015
orse+0.015
orses+0.014
 peanut+0.013
ets+0.013
Neg logit contributions
 Lu-0.016
Ann-0.013
Lu-0.013
 angels-0.013
 firefighters-0.012
TokenM
Token ID44
Feature activation-8.64e-01

Pos logit contributions
ret+0.015
orse+0.015
orses+0.014
 peanut+0.013
ets+0.013
Neg logit contributions
 Lu-0.016
Ann-0.013
Lu-0.013
 angels-0.013
 firefighters-0.012
Tokenia
Token ID544
Feature activation+6.40e-01

Pos logit contributions
orse+0.041
ret+0.040
orses+0.039
 peanut+0.038
ets+0.037
Neg logit contributions
 Lu-0.032
Ann-0.026
 angels-0.026
 firefighters-0.024
Lu-0.024
Token adventure
Token ID8855
Feature activation-1.01e-01

Pos logit contributions
ret+0.016
orse+0.015
orses+0.015
 peanut+0.013
ets+0.013
Neg logit contributions
 Lu-0.013
 angels-0.010
Lu-0.010
Ann-0.010
 firefighters-0.010
Token.
Token ID13
Feature activation+6.49e-01

Pos logit contributions
ret+0.004
orse+0.004
orses+0.004
 peanut+0.004
ets+0.004
Neg logit contributions
 Lu-0.005
 angels-0.004
Ann-0.004
Lu-0.004
 firefighters-0.004
Token He
Token ID679
Feature activation-8.66e-02

Pos logit contributions
 Lu+0.031
 angels+0.028
Ann+0.026
Lu+0.026
co+0.026
Neg logit contributions
orse-0.024
ret-0.024
orses-0.022
 peanut-0.020
ork-0.019
Token found
Token ID1043
Feature activation+1.16e-01

Pos logit contributions
ret+0.003
orse+0.003
orses+0.003
 peanut+0.002
ets+0.002
Neg logit contributions
 Lu-0.005
 angels-0.004
Ann-0.004
Lu-0.004
 firefighters-0.004
Token a
Token ID257
Feature activation-6.08e-01

Pos logit contributions
 Lu+0.006
 angels+0.005
Ann+0.005
Lu+0.004
 firefighters+0.004
Neg logit contributions
ret-0.005
orse-0.005
orses-0.004
 peanut-0.004
ets-0.004
Token peaceful
Token ID12309
Feature activation-5.31e-01

Pos logit contributions
ret+0.025
orse+0.025
orses+0.023
ets+0.022
sel+0.021
Neg logit contributions
 Lu-0.029
 angels-0.023
Lu-0.023
 firefighters-0.022
Ann-0.022
Token case
Token ID1339
Feature activation-6.91e-01

Pos logit contributions
ret+0.025
orse+0.024
orses+0.023
ets+0.021
 peanut+0.020
Neg logit contributions
 Lu-0.023
 angels-0.018
Lu-0.018
Ann-0.017
 firefighters-0.017
Token deep
Token ID2769
Feature activation+2.38e-01

Pos logit contributions
ret+0.029
orse+0.028
orses+0.027
 peanut+0.025
ets+0.024
Neg logit contributions
 Lu-0.032
 angels-0.026
 attendant-0.025
Lu-0.025
Ann-0.025
Token in
Token ID287
Feature activation-2.29e-01

Pos logit contributions
 Lu+0.011
 angels+0.009
Ann+0.009
Lu+0.009
 firefighters+0.009
Neg logit contributions
ret-0.010
orse-0.010
orses-0.009
 peanut-0.009
ets-0.009
Token the
Token ID262
Feature activation-7.82e-01

Pos logit contributions
ret+0.011
orse+0.010
orses+0.010
ets+0.009
 peanut+0.009
Neg logit contributions
 Lu-0.010
 angels-0.008
Ann-0.008
Lu-0.008
 firefighters-0.008
Token woods
Token ID16479
Feature activation-8.32e-01

Pos logit contributions
orse+0.042
ret+0.042
orses+0.039
ets+0.035
ocus+0.035
Neg logit contributions
 Lu-0.030
Lu-0.022
Ann-0.022
 angels-0.022
 Taxi-0.021
Token.
Token ID13
Feature activation-6.49e-01

Pos logit contributions
ret+0.017
orse+0.017
orses+0.016
 peanut+0.015
ets+0.014
Neg logit contributions
 Lu-0.019
 angels-0.015
Lu-0.015
Ann-0.015
 firefighters-0.014
Token He
Token ID679
Feature activation+1.50e-01

Pos logit contributions
ret+0.032
orse+0.032
orses+0.031
ocket+0.027
ets+0.027
Neg logit contributions
 Lu-0.027
Lu-0.020
 firefighters-0.020
Ann-0.020
 Lucy-0.020
Token asked
Token ID1965
Feature activation-4.18e-02

Pos logit contributions
 Lu+0.008
 angels+0.006
Ann+0.006
Lu+0.006
 firefighters+0.006
Neg logit contributions
ret-0.006
orse-0.006
orses-0.005
 peanut-0.005
ets-0.005
Token what
Token ID644
Feature activation+4.59e-01

Pos logit contributions
ret+0.002
orse+0.002
orses+0.002
 peanut+0.002
ets+0.002
Neg logit contributions
 Lu-0.002
 angels-0.001
Ann-0.001
Lu-0.001
 firefighters-0.001
Token they
Token ID484
Feature activation-5.21e-01

Pos logit contributions
 Lu+0.024
 angels+0.020
Ann+0.019
 Taxi+0.019
 attendant+0.019
Neg logit contributions
orse-0.016
ret-0.016
orses-0.015
 peanut-0.015
ork-0.013
Token were
Token ID547
Feature activation-6.42e-01

Pos logit contributions
ret+0.021
orse+0.021
orses+0.020
 peanut+0.018
ork+0.018
Neg logit contributions
 Lu-0.025
 angels-0.020
Lu-0.020
Ann-0.019
 firefighters-0.019
Token having
Token ID1719
Feature activation-4.16e-01

Pos logit contributions
ret+0.031
orse+0.030
orses+0.028
ork+0.026
 peanut+0.026
Neg logit contributions
 Lu-0.026
 angels-0.021
 firefighters-0.020
 youths-0.019
Lu-0.019
Token for
Token ID329
Feature activation-9.62e-01

Pos logit contributions
ret+0.018
orse+0.017
orses+0.016
 peanut+0.015
ets+0.015
Neg logit contributions
 Lu-0.019
 angels-0.016
 firefighters-0.015
Lu-0.015
Ann-0.015
Token dinner
Token ID8073
Feature activation-4.35e-01

Pos logit contributions
ret+0.043
orse+0.041
orses+0.039
 peanut+0.036
ets+0.036
Neg logit contributions
 Lu-0.044
 angels-0.035
Lu-0.034
 firefighters-0.033
 youths-0.033
Token and
Token ID290
Feature activation+6.63e-02

Pos logit contributions
ret+0.018
orse+0.018
orses+0.016
 peanut+0.015
ets+0.015
Neg logit contributions
 Lu-0.021
 angels-0.017
Lu-0.016
Ann-0.016
 firefighters-0.016
Token Lily
Token ID20037
Feature activation+2.90e-01

Pos logit contributions
 Lu+0.003
 angels+0.003
Ann+0.003
Lu+0.003
 firefighters+0.003
Neg logit contributions
ret-0.003
orse-0.003
orses-0.002
 peanut-0.002
ets-0.002
Token up
Token ID510
Feature activation-7.98e-01

Pos logit contributions
ret+0.008
orse+0.008
orses+0.008
 peanut+0.007
ets+0.007
Neg logit contributions
 Lu-0.008
 angels-0.006
Ann-0.006
Lu-0.006
 firefighters-0.006
Token the
Token ID262
Feature activation+1.34e+00

Pos logit contributions
orse+0.037
ret+0.037
orses+0.035
ocket+0.032
 peanut+0.032
Neg logit contributions
 Lu-0.034
 angels-0.027
Lu-0.026
 firefighters-0.026
Ann-0.026
Token mess
Token ID2085
Feature activation-2.40e-01

Pos logit contributions
 Lu+0.087
Ann+0.075
 Pen+0.073
 Luis+0.073
K+0.072
Neg logit contributions
ret-0.027
 peanut-0.026
 notebooks-0.025
ork-0.024
 drawing-0.023
Token they
Token ID484
Feature activation-6.12e-01

Pos logit contributions
ret+0.010
orse+0.010
orses+0.009
 peanut+0.009
ets+0.008
Neg logit contributions
 Lu-0.011
 angels-0.009
Ann-0.009
Lu-0.009
 firefighters-0.009
Token made
Token ID925
Feature activation-4.57e-01

Pos logit contributions
ret+0.024
orse+0.023
orses+0.022
 peanut+0.020
ork+0.019
Neg logit contributions
 Lu-0.030
 angels-0.025
 firefighters-0.024
Ann-0.024
Lu-0.024
Token.
Token ID13
Feature activation-2.52e+00

Pos logit contributions
orse+0.020
ret+0.020
orses+0.019
 peanut+0.018
ocket+0.017
Neg logit contributions
 Lu-0.020
 angels-0.017
Lu-0.016
Ann-0.016
 firefighters-0.016
Token
Token ID220
Feature activation-9.90e-02

Pos logit contributions
ret+0.132
orse+0.129
ocket+0.122
orses+0.122
ocus+0.119
Neg logit contributions
 Lu-0.090
 Lucy-0.078
 Jenkins-0.068
 Ann-0.067
 youths-0.064
Token
Token ID198
Feature activation-1.59e+00

Pos logit contributions
ret+0.004
orse+0.004
orses+0.004
 peanut+0.003
ets+0.003
Neg logit contributions
 Lu-0.005
 angels-0.004
Ann-0.004
Lu-0.004
 firefighters-0.004
Token
Token ID198
Feature activation-1.97e+00

Pos logit contributions
ret+0.084
orse+0.078
ets+0.078
ocket+0.077
sel+0.077
Neg logit contributions
 Lu-0.055
Lu-0.044
Ann-0.044
 attendant-0.038
 Lucy-0.038
TokenThe
Token ID464
Feature activation+1.33e+00

Pos logit contributions
ret+0.107
orse+0.097
ocket+0.096
alks+0.095
 peanut+0.092
Neg logit contributions
Lu-0.064
 Lu-0.061
Ann-0.059
Michael-0.051
 attendant-0.049
Token boys
Token ID6510
Feature activation+9.87e-01

Pos logit contributions
 Lu+0.072
 Luis+0.058
 Stev+0.058
 Pen+0.056
Ann+0.056
Neg logit contributions
 peanut-0.041
orse-0.041
ret-0.040
orses-0.039
 notebooks-0.038
Token was
Token ID373
Feature activation-2.56e-02

Pos logit contributions
ret+0.018
orse+0.018
orses+0.016
 peanut+0.015
ets+0.015
Neg logit contributions
 Lu-0.020
 angels-0.016
 firefighters-0.015
Ann-0.015
Lu-0.015
Token going
Token ID1016
Feature activation-9.39e-01

Pos logit contributions
ret+0.001
orse+0.001
orses+0.001
 peanut+0.001
ets+0.001
Neg logit contributions
 Lu-0.001
 angels-0.001
Ann-0.001
Lu-0.001
 firefighters-0.001
Token away
Token ID1497
Feature activation+1.41e-01

Pos logit contributions
orse+0.047
ret+0.045
orses+0.043
ocket+0.039
 peanut+0.038
Neg logit contributions
 Lu-0.038
 angels-0.031
 firefighters-0.029
 attendant-0.029
 Taxi-0.028
Token.
Token ID13
Feature activation-2.23e+00

Pos logit contributions
 Lu+0.007
 angels+0.006
Ann+0.005
Lu+0.005
 firefighters+0.005
Neg logit contributions
ret-0.006
orse-0.006
orses-0.005
 peanut-0.005
ets-0.005
Token
Token ID198
Feature activation-8.39e-01

Pos logit contributions
ret+0.126
ocket+0.122
orse+0.120
orses+0.114
ocus+0.112
Neg logit contributions
 Lu-0.069
 youths-0.051
Ann-0.047
 Lucy-0.047
 Jenkins-0.046
Token
Token ID198
Feature activation-2.53e+00

Pos logit contributions
ret+0.038
orse+0.038
orses+0.035
 peanut+0.035
ets+0.035
Neg logit contributions
 Lu-0.036
Ann-0.028
Lu-0.028
 angels-0.027
 attendant-0.026
TokenAt
Token ID2953
Feature activation+8.21e-02

Pos logit contributions
ret+0.139
ocket+0.138
orse+0.128
 peanut+0.123
alks+0.121
Neg logit contributions
Ann-0.071
Lu-0.068
 Lu-0.068
 youths-0.062
Michael-0.058
Token first
Token ID717
Feature activation-1.98e+00

Pos logit contributions
 Lu+0.004
 angels+0.003
Ann+0.003
Lu+0.003
 firefighters+0.003
Neg logit contributions
ret-0.003
orse-0.003
orses-0.003
 peanut-0.003
ets-0.003
Token,
Token ID11
Feature activation-2.08e+00

Pos logit contributions
ret+0.095
orse+0.092
ifying+0.090
ocket+0.090
orses+0.090
Neg logit contributions
 Lu-0.074
 Lucy-0.060
 Ann-0.054
 angels-0.053
 Pen-0.052
Token Ben
Token ID3932
Feature activation-8.58e-01

Pos logit contributions
ret+0.110
ocket+0.101
orse+0.098
ocus+0.097
orses+0.095
Neg logit contributions
 Lu-0.074
 youths-0.064
 Luis-0.057
 angels-0.056
 firefighters-0.056
Token was
Token ID373
Feature activation+8.95e-01

Pos logit contributions
ret+0.036
orse+0.034
orses+0.032
 peanut+0.029
ets+0.029
Neg logit contributions
 Lu-0.041
Ann-0.032
 angels-0.032
Lu-0.032
 firefighters-0.032
Token.
Token ID13
Feature activation+1.21e+00

Pos logit contributions
ret+0.032
orse+0.032
orses+0.030
 peanut+0.027
ets+0.026
Neg logit contributions
 Lu-0.033
 angels-0.027
Lu-0.026
Ann-0.025
 firefighters-0.025
Token It
Token ID632
Feature activation+3.50e-01

Pos logit contributions
 Lu+0.043
 angels+0.038
guard+0.036
co+0.036
Ann+0.035
Neg logit contributions
ret-0.053
orse-0.053
 peanut-0.051
 This-0.051
orses-0.050
Token made
Token ID925
Feature activation+5.18e-01

Pos logit contributions
 Lu+0.018
 angels+0.015
Ann+0.015
 youths+0.014
 firefighters+0.014
Neg logit contributions
ret-0.013
orse-0.013
orses-0.012
 peanut-0.011
ets-0.011
Token the
Token ID262
Feature activation-1.05e+00

Pos logit contributions
 Lu+0.020
 angels+0.016
Ann+0.016
 youths+0.015
Lu+0.015
Neg logit contributions
ret-0.024
orse-0.023
orses-0.022
 peanut-0.022
ets-0.021
Token salad
Token ID20698
Feature activation-7.77e-01

Pos logit contributions
ret+0.043
orse+0.042
orses+0.038
ocus+0.035
ork+0.035
Neg logit contributions
 Lu-0.049
 angels-0.045
 firefighters-0.042
 youths-0.041
Lu-0.040
Token look
Token ID804
Feature activation-2.57e+00

Pos logit contributions
ret+0.033
orse+0.033
orses+0.030
 peanut+0.027
ocket+0.027
Neg logit contributions
 Lu-0.036
 angels-0.030
Lu-0.028
 firefighters-0.028
Ann-0.028
Token wet
Token ID9583
Feature activation+1.59e-01

Pos logit contributions
orse+0.148
ret+0.141
orses+0.137
ocket+0.128
alks+0.123
Neg logit contributions
 Lu-0.076
 Lucy-0.063
 angels-0.061
 firefighters-0.059
Lu-0.056
Token,
Token ID11
Feature activation-9.26e-01

Pos logit contributions
 Lu+0.008
 angels+0.007
Ann+0.006
Lu+0.006
 firefighters+0.006
Neg logit contributions
ret-0.006
orse-0.006
orses-0.006
 peanut-0.005
ets-0.005
Token but
Token ID475
Feature activation+1.26e+00

Pos logit contributions
ret+0.044
orse+0.041
orses+0.039
ork+0.036
ocket+0.036
Neg logit contributions
 Lu-0.040
 angels-0.033
 firefighters-0.032
Lu-0.031
 Lucy-0.030
Token it
Token ID340
Feature activation+5.32e-01

Pos logit contributions
 Lu+0.049
co+0.042
 youths+0.041
 Taxi+0.041
Ann+0.040
Neg logit contributions
ret-0.054
orse-0.053
 peanut-0.050
orses-0.049
ets-0.045
Token tasted
Token ID29187
Feature activation-9.34e-01

Pos logit contributions
 Lu+0.028
 angels+0.024
Ann+0.023
 youths+0.023
 Taxi+0.023
Neg logit contributions
orse-0.018
ret-0.018
orses-0.017
 peanut-0.016
ets-0.015
Token She
Token ID1375
Feature activation+4.04e-01

Pos logit contributions
 Lu+0.013
 angels+0.010
Ann+0.010
Lu+0.010
 firefighters+0.010
Neg logit contributions
ret-0.013
orse-0.012
orses-0.012
 peanut-0.011
ets-0.011
Token picks
Token ID11103
Feature activation-1.01e+00

Pos logit contributions
 Lu+0.021
 angels+0.018
Lu+0.017
Ann+0.017
 firefighters+0.017
Neg logit contributions
ret-0.015
orse-0.014
orses-0.013
ets-0.012
 peanut-0.012
Token a
Token ID257
Feature activation-2.34e+00

Pos logit contributions
orse+0.056
orses+0.052
ret+0.052
ets+0.046
ocket+0.046
Neg logit contributions
 Lu-0.036
 angels-0.029
 youths-0.027
 firefighters-0.027
Ann-0.027
Token card
Token ID2657
Feature activation-4.04e-01

Pos logit contributions
orse+0.103
ret+0.103
orses+0.098
ets+0.086
ocket+0.086
Neg logit contributions
 Lu-0.088
 angels-0.082
 firefighter-0.080
 attendant-0.079
 firefighters-0.078
Token with
Token ID351
Feature activation-1.57e+00

Pos logit contributions
ret+0.017
orse+0.016
orses+0.015
 peanut+0.014
ets+0.014
Neg logit contributions
 Lu-0.019
 angels-0.016
Ann-0.015
Lu-0.015
 firefighters-0.015
Token a
Token ID257
Feature activation-3.00e+00

Pos logit contributions
orse+0.091
ret+0.087
orses+0.084
ork+0.077
ets+0.076
Neg logit contributions
 Lu-0.052
 angels-0.041
 Lucy-0.038
 firefighters-0.038
 taxis-0.036
Token cat
Token ID3797
Feature activation-1.08e+00

Pos logit contributions
ret+0.136
orse+0.127
orses+0.124
ets+0.119
earing+0.113
Neg logit contributions
 Lu-0.102
 firefighter-0.096
 angels-0.096
 attendant-0.092
 firefighters-0.090
Token on
Token ID319
Feature activation-1.31e+00

Pos logit contributions
ret+0.050
orse+0.048
orses+0.045
 peanut+0.041
ets+0.040
Neg logit contributions
 Lu-0.047
 angels-0.037
Ann-0.037
Lu-0.036
 firefighters-0.035
Token it
Token ID340
Feature activation-5.27e-01

Pos logit contributions
orse+0.063
ret+0.061
orses+0.059
ets+0.053
ocket+0.053
Neg logit contributions
 Lu-0.057
Ann-0.046
 angels-0.045
 Lucy-0.044
Lu-0.044
Token.
Token ID13
Feature activation+4.49e-02

Pos logit contributions
ret+0.023
orse+0.023
orses+0.021
 peanut+0.020
ets+0.019
Neg logit contributions
 Lu-0.024
 angels-0.019
Ann-0.018
Lu-0.018
 firefighters-0.018
Token She
Token ID1375
Feature activation+2.64e-01

Pos logit contributions
 Lu+0.002
 angels+0.002
Ann+0.002
Lu+0.002
 firefighters+0.001
Neg logit contributions
ret-0.002
orse-0.002
orses-0.002
 peanut-0.002
ets-0.002
Token of
Token ID286
Feature activation+1.55e+00

Pos logit contributions
 Lu+0.022
 angels+0.017
Ann+0.017
 firefighters+0.016
 attendant+0.016
Neg logit contributions
orse-0.022
ret-0.022
orses-0.021
ets-0.020
 peanut-0.020
Token fun
Token ID1257
Feature activation+1.01e+00

Pos logit contributions
 Lu+0.088
 attendant+0.078
 department+0.077
jack+0.076
 Williams+0.074
Neg logit contributions
ets-0.043
orse-0.043
orses-0.042
ret-0.040
orm-0.035
Token.
Token ID13
Feature activation-2.95e+00

Pos logit contributions
 Lu+0.056
 attendant+0.048
Ann+0.047
 Taxi+0.046
Lu+0.046
Neg logit contributions
orse-0.033
orses-0.031
ret-0.029
ets-0.028
ork-0.024
Token
Token ID220
Feature activation+1.15e-01

Pos logit contributions
ret+0.134
orse+0.131
 peanut+0.129
ork+0.122
ocus+0.121
Neg logit contributions
 Lu-0.104
 Lucy-0.088
Ann-0.087
 Ann-0.084
 angels-0.079
Token
Token ID198
Feature activation-1.93e+00

Pos logit contributions
 Lu+0.006
 angels+0.005
Ann+0.005
Lu+0.005
 firefighters+0.004
Neg logit contributions
ret-0.005
orse-0.004
orses-0.004
 peanut-0.004
ets-0.004
Token
Token ID198
Feature activation-2.79e+00

Pos logit contributions
ret+0.098
 peanut+0.096
orse+0.096
sel+0.091
ifying+0.091
Neg logit contributions
 Lu-0.066
Ann-0.056
Lu-0.053
 angels-0.050
 Pen-0.046
TokenRachel
Token ID44045
Feature activation-1.24e+00

Pos logit contributions
ret+0.144
orse+0.140
 peanut+0.139
ocket+0.128
eg+0.126
Neg logit contributions
Ann-0.084
Lu-0.083
 Lu-0.080
Mark-0.073
Andy-0.068
Token was
Token ID373
Feature activation+7.84e-01

Pos logit contributions
ret+0.051
orse+0.048
orses+0.045
 peanut+0.043
ocket+0.043
Neg logit contributions
 Lu-0.059
Ann-0.047
 angels-0.046
Lu-0.046
co-0.045
Token so
Token ID523
Feature activation-2.09e-01

Pos logit contributions
 Lu+0.041
Lu+0.035
 angels+0.035
Ann+0.035
 firefighters+0.033
Neg logit contributions
orse-0.027
ret-0.026
orses-0.024
 peanut-0.022
ets-0.021
Token happy
Token ID3772
Feature activation-1.86e-01

Pos logit contributions
ret+0.009
orse+0.009
orses+0.008
 peanut+0.008
ets+0.008
Neg logit contributions
 Lu-0.010
 angels-0.008
Ann-0.008
Lu-0.008
 firefighters-0.007
Token that
Token ID326
Feature activation-4.02e-01

Pos logit contributions
ret+0.007
orse+0.007
orses+0.006
 peanut+0.006
ets+0.006
Neg logit contributions
 Lu-0.010
 angels-0.008
Ann-0.008
Lu-0.008
 firefighters-0.008