TOP ACTIVATIONS
MAX = 0.158

the pigeon all those weeks ago . <|endoftext|> Mike and his
velvet box all those years ago . They were glad that
ancestors who sang it long ago . Would you like to
on her mom my 's brand new table !
showed him her other bath ro bes . She had a
man drove off in his brand new car , and he
children put on their bath ro bes and ran around in
his favorite shows on their brand new television . <|endoftext|> Once
â s Spring time . This is the time
bird . You admit your fault and ask for mercy .
were so proud of their super strong work that they all
. He was wearing his brand new icy blue jacket as
hours helping people understand their history . One day
the tree to its once former beauty . He was happy
my had told him long ago . The bird spread out
brother would wear their bath ro bes together and play games
feeling good because his special doctor was coming to visit .
his friend because of his selfish ness . <|endoftext|> Once upon
learned that even though his license was special and valuable ,
animals and people from long ago . Sam 's mom said

MIN ACTIVATIONS
MIN = -0.141

made him an even y umm ier snack and they both
idea . He brought a basket and filled it with things
Here , take a cr ay on ." They
ier ? You are y umm ier . You are my
want to make a da isy necklace too , but I
" Is it a cr ay on ?" Ben asks .
he couldn 't make a basket . He felt sad and
chair and takes a cr ay on and a paper .
the basketball and making a basket . Sally cheered each time
, and it was pri ve leg ed to be part
to make an ash tr ay out of clay . As
and it was the y umm iest steak she ever tasted
berries to make a y ummy snack !" The squirrel agreed
. She always brought a basket with some bread and cheese
Can I have a cr ay on instead ?" Her uncle
She wanted to make a sweet perfume for her mom .
happy . She brought a basket of treats to share with
, he finally made a basket ! He felt so happy
bite and makes a y ummy sound . "
some flowers and make a bou quet . We can also

INTERVAL 0.083 - 0.158
CONTAINS 0.097%

time and their new toy car . They wished they had
. She cried louder and louder . Ben felt sorry and
, there lived two friends named Jack and Sally . They
understand the world around us better . Lily was happy to
or frogs or snakes . Some of them might be friendly

INTERVAL 0.008 - 0.083
CONTAINS 33.770%

's ordinary day turned into a wonderful adventure ! <|endoftext|> One
. He realized the voice was right , the stair wasn
so grateful to the fairy who had helped her find her
skipped and skipped until they saw the boat again . "
that she was able to visit the library and find the

INTERVAL -0.067 - 0.008
CONTAINS 65.656%

immediately hung the h anger on the wall . He asked
can take care of him ! â The
a long journey to find the magical sword . Along the
, but he didn 't know how to .
making it rum ble and wh ir . "

INTERVAL -0.141 - -0.067
CONTAINS 0.477%

. I want to help all the animals , even the
are happy . They are friends . <|endoftext|> L ily and
day , he sees a big building far away . It
. They saw a big pile of ash near a bench
nobody answered . She was all alone . Suddenly , it
Token the
Token ID262
Feature activation-2.34e-02

Pos logit contributions
 shampoo+0.025
 L+0.024
 common+0.023
 Qu+0.022
 fault+0.022
Neg logit contributions
pole-0.029
emaker-0.028
umbo-0.028
 warrior-0.028
ickets-0.027
Token pigeon
Token ID46387
Feature activation+6.13e-03

Pos logit contributions
 warrior+0.026
 owl+0.024
 King+0.023
 eagle+0.023
 angel+0.023
Neg logit contributions
ours-0.045
 vinegar-0.044
 fault-0.043
 bruises-0.042
 common-0.042
Token all
Token ID477
Feature activation-4.81e-02

Pos logit contributions
 shampoo+0.009
 fault+0.009
 L+0.009
 common+0.009
 vinegar+0.009
Neg logit contributions
pole-0.008
emaker-0.008
 warrior-0.008
ickets-0.008
ados-0.008
Token those
Token ID883
Feature activation+6.22e-02

Pos logit contributions
pole+0.062
emaker+0.059
 warrior+0.056
ickets+0.056
stone+0.054
Neg logit contributions
 fault-0.080
 shampoo-0.079
 vinegar-0.079
 bruises-0.077
aj-0.075
Token weeks
Token ID2745
Feature activation+4.53e-02

Pos logit contributions
 fault+0.106
 vinegar+0.103
 shampoo+0.102
 common+0.100
 L+0.097
Neg logit contributions
pole-0.078
 warrior-0.075
emaker-0.072
stone-0.072
ickets-0.070
Token ago
Token ID2084
Feature activation+1.47e-01

Pos logit contributions
 fault+0.076
 vinegar+0.074
 shampoo+0.074
 common+0.072
 bruises+0.071
Neg logit contributions
pole-0.059
emaker-0.055
stone-0.053
ickets-0.053
 warrior-0.052
Token.
Token ID13
Feature activation+5.64e-03

Pos logit contributions
 vinegar+0.252
 shampoo+0.247
 common+0.243
 bruises+0.242
 fault+0.239
Neg logit contributions
pole-0.180
emaker-0.162
ados-0.158
person-0.154
 warrior-0.154
Token<|endoftext|>
Token ID50256
Feature activation+1.01e-02

Pos logit contributions
 shampoo+0.006
 L+0.006
 fault+0.005
 Qu+0.005
 common+0.005
Neg logit contributions
pole-0.011
emaker-0.011
 warrior-0.011
ados-0.010
ickets-0.010
TokenMike
Token ID16073
Feature activation+1.62e-02

Pos logit contributions
 fault+0.014
 shampoo+0.014
 vinegar+0.013
 bruises+0.013
 common+0.013
Neg logit contributions
pole-0.016
ickets-0.015
emaker-0.015
 warrior-0.015
oon-0.015
Token and
Token ID290
Feature activation+1.49e-02

Pos logit contributions
 fault+0.031
 shampoo+0.031
 bruises+0.031
 vinegar+0.031
 common+0.030
Neg logit contributions
pole-0.017
emaker-0.016
 warrior-0.015
ickets-0.014
umb-0.014
Token his
Token ID465
Feature activation+3.74e-02

Pos logit contributions
 shampoo+0.021
 fault+0.020
 L+0.020
 common+0.020
 vinegar+0.019
Neg logit contributions
pole-0.023
emaker-0.022
 warrior-0.022
ickets-0.022
ados-0.021
Token velvet
Token ID47750
Feature activation+5.01e-03

Pos logit contributions
pole+0.048
 warrior+0.047
 King+0.046
stone+0.045
 eagle+0.045
Neg logit contributions
ours-0.057
 L-0.055
 vinegar-0.055
aj-0.054
 shampoo-0.054
Token box
Token ID3091
Feature activation-4.31e-02

Pos logit contributions
 shampoo+0.008
 fault+0.008
 vinegar+0.008
 common+0.008
 L+0.008
Neg logit contributions
pole-0.006
emaker-0.006
 warrior-0.006
ickets-0.006
ados-0.006
Token all
Token ID477
Feature activation-6.49e-02

Pos logit contributions
pole+0.063
emaker+0.058
 warrior+0.058
stone+0.057
ickets+0.056
Neg logit contributions
 shampoo-0.066
 fault-0.064
 vinegar-0.063
 common-0.062
 bruises-0.061
Token those
Token ID883
Feature activation+5.02e-02

Pos logit contributions
pole+0.058
emaker+0.052
 warrior+0.051
ickets+0.048
stone+0.047
Neg logit contributions
 shampoo-0.135
 fault-0.133
 vinegar-0.131
 bruises-0.130
 L-0.128
Token years
Token ID812
Feature activation+8.53e-02

Pos logit contributions
 fault+0.087
 shampoo+0.085
 vinegar+0.084
 common+0.080
ours+0.080
Neg logit contributions
pole-0.064
 warrior-0.059
stone-0.058
 King-0.056
emaker-0.055
Token ago
Token ID2084
Feature activation+1.45e-01

Pos logit contributions
 bruises+0.143
 shampoo+0.142
 vinegar+0.138
 fault+0.136
 mustard+0.129
Neg logit contributions
pole-0.106
stone-0.103
 warrior-0.098
person-0.096
 King-0.096
Token.
Token ID13
Feature activation-1.32e-03

Pos logit contributions
 shampoo+0.242
 vinegar+0.235
 bruises+0.230
 common+0.229
 fault+0.229
Neg logit contributions
pole-0.182
ados-0.165
emaker-0.160
person-0.160
stone-0.160
Token They
Token ID1119
Feature activation-7.64e-03

Pos logit contributions
pole+0.002
ickets+0.002
amber+0.002
umbo+0.002
 warrior+0.002
Neg logit contributions
 bruises-0.002
 ruined-0.002
 shampoo-0.002
 vinegar-0.002
 fault-0.002
Token were
Token ID547
Feature activation-7.03e-03

Pos logit contributions
pole+0.013
emaker+0.013
 warrior+0.013
ickets+0.012
ados+0.012
Neg logit contributions
 shampoo-0.009
 fault-0.009
 vinegar-0.009
 common-0.009
 L-0.009
Token glad
Token ID9675
Feature activation-1.20e-02

Pos logit contributions
pole+0.010
emaker+0.010
 warrior+0.010
ickets+0.009
ados+0.009
Neg logit contributions
 shampoo-0.011
 fault-0.010
 vinegar-0.010
 common-0.010
 L-0.010
Token that
Token ID326
Feature activation+2.68e-02

Pos logit contributions
 warrior+0.014
 King+0.014
 Peter+0.014
stone+0.013
ados+0.013
Neg logit contributions
 vinegar-0.019
 bruises-0.019
aj-0.019
 common-0.019
 fault-0.018
Token ancestors
Token ID18668
Feature activation+3.04e-02

Pos logit contributions
 shampoo+0.082
 vinegar+0.081
 fault+0.081
 common+0.079
 L+0.078
Neg logit contributions
pole-0.065
 warrior-0.064
emaker-0.062
ickets-0.060
stone-0.059
Token who
Token ID508
Feature activation+5.14e-02

Pos logit contributions
 shampoo+0.047
 fault+0.046
 vinegar+0.045
 common+0.045
 bruises+0.044
Neg logit contributions
pole-0.042
 warrior-0.040
emaker-0.040
ickets-0.039
ados-0.038
Token sang
Token ID25889
Feature activation+9.29e-03

Pos logit contributions
 fault+0.062
 shampoo+0.061
 vinegar+0.060
 bruises+0.058
 L+0.057
Neg logit contributions
pole-0.088
 warrior-0.087
emaker-0.085
ickets-0.084
stone-0.082
Token it
Token ID340
Feature activation+2.95e-02

Pos logit contributions
 shampoo+0.013
 fault+0.013
 vinegar+0.013
 bruises+0.012
 common+0.012
Neg logit contributions
pole-0.014
 warrior-0.014
emaker-0.013
ickets-0.013
ados-0.013
Token long
Token ID890
Feature activation+5.44e-02

Pos logit contributions
 shampoo+0.037
 fault+0.037
 common+0.037
 L+0.035
 cheaper+0.032
Neg logit contributions
emaker-0.050
ados-0.046
umbo-0.046
 warrior-0.046
person-0.045
Token ago
Token ID2084
Feature activation+1.44e-01

Pos logit contributions
 vinegar+0.094
 shampoo+0.092
 bruises+0.092
 fault+0.089
ours+0.087
Neg logit contributions
pole-0.068
 warrior-0.063
emaker-0.061
ickets-0.060
stone-0.058
Token.
Token ID13
Feature activation-7.74e-03

Pos logit contributions
 shampoo+0.230
 vinegar+0.226
 fault+0.220
 bruises+0.219
 common+0.218
Neg logit contributions
pole-0.197
emaker-0.177
 warrior-0.175
ados-0.175
ickets-0.172
Token Would
Token ID10928
Feature activation+2.15e-02

Pos logit contributions
pole+0.012
emaker+0.011
 warrior+0.011
ados+0.011
stone+0.011
Neg logit contributions
 shampoo-0.011
 L-0.011
 fault-0.011
 vinegar-0.010
 common-0.010
Token you
Token ID345
Feature activation-1.27e-02

Pos logit contributions
 shampoo+0.033
 L+0.031
 vinegar+0.031
 fault+0.031
 common+0.031
Neg logit contributions
pole-0.030
emaker-0.029
 warrior-0.029
ickets-0.028
ados-0.027
Token like
Token ID588
Feature activation-1.01e-02

Pos logit contributions
pole+0.022
 warrior+0.022
ickets+0.021
emaker+0.021
stone+0.020
Neg logit contributions
 vinegar-0.015
 fault-0.015
 bruises-0.015
 shampoo-0.015
 L-0.014
Token to
Token ID284
Feature activation-2.37e-03

Pos logit contributions
pole+0.014
 warrior+0.014
ickets+0.014
emaker+0.013
stone+0.013
Neg logit contributions
 fault-0.015
 vinegar-0.015
 shampoo-0.015
 bruises-0.015
 common-0.014
Token on
Token ID319
Feature activation+1.02e-02

Pos logit contributions
 fault+0.020
 shampoo+0.020
 vinegar+0.019
 common+0.019
 bruises+0.018
Neg logit contributions
pole-0.021
emaker-0.020
 warrior-0.020
ados-0.020
ickets-0.019
Token her
Token ID607
Feature activation-8.70e-04

Pos logit contributions
 fault+0.018
aj+0.018
ses+0.017
 vinegar+0.017
 bruises+0.017
Neg logit contributions
ados-0.011
 Charlie-0.011
pole-0.011
 King-0.010
 mushroom-0.010
Token mom
Token ID1995
Feature activation+3.79e-02

Pos logit contributions
pole+0.001
 warrior+0.001
emaker+0.001
ados+0.001
stone+0.001
Neg logit contributions
 shampoo-0.001
 fault-0.001
 vinegar-0.001
 common-0.001
 L-0.001
Tokenmy
Token ID1820
Feature activation+1.54e-02

Pos logit contributions
 shampoo+0.071
 fault+0.069
 L+0.068
 vinegar+0.067
 common+0.067
Neg logit contributions
pole-0.039
 warrior-0.038
emaker-0.038
ickets-0.037
ados-0.036
Token's
Token ID338
Feature activation+3.19e-02

Pos logit contributions
 shampoo+0.030
 fault+0.030
 vinegar+0.029
 common+0.029
 L+0.029
Neg logit contributions
pole-0.015
emaker-0.014
 warrior-0.014
ickets-0.013
ados-0.013
Token brand
Token ID4508
Feature activation+1.40e-01

Pos logit contributions
 shampoo+0.047
 fault+0.046
 vinegar+0.046
 common+0.045
 L+0.044
Neg logit contributions
pole-0.046
 warrior-0.044
ados-0.042
emaker-0.042
stone-0.042
Token new
Token ID649
Feature activation+8.03e-02

Pos logit contributions
 shampoo+0.143
 fault+0.140
 vinegar+0.134
 common+0.132
 bruises+0.130
Neg logit contributions
pole-0.267
emaker-0.258
 warrior-0.257
ickets-0.252
ados-0.250
Token table
Token ID3084
Feature activation+2.36e-02

Pos logit contributions
 shampoo+0.109
 fault+0.108
 vinegar+0.106
 L+0.103
 bruises+0.103
Neg logit contributions
pole-0.125
 warrior-0.120
emaker-0.117
ados-0.115
stone-0.115
Token!
Token ID0
Feature activation+1.72e-03

Pos logit contributions
 shampoo+0.038
 fault+0.037
 vinegar+0.037
 common+0.036
 bruises+0.036
Neg logit contributions
pole-0.032
emaker-0.029
 warrior-0.029
stone-0.028
ados-0.028
Token
Token ID198
Feature activation+9.86e-03

Pos logit contributions
 shampoo+0.003
 fault+0.003
 L+0.002
 vinegar+0.002
 common+0.002
Neg logit contributions
pole-0.002
emaker-0.002
 warrior-0.002
stone-0.002
ickets-0.002
Token
Token ID198
Feature activation+5.83e-03

Pos logit contributions
 shampoo+0.011
 fault+0.011
 vinegar+0.011
 common+0.011
 L+0.010
Neg logit contributions
pole-0.018
emaker-0.017
 warrior-0.017
ickets-0.017
ados-0.016
Token showed
Token ID3751
Feature activation-7.06e-03

Pos logit contributions
 fault+0.006
 shampoo+0.006
 vinegar+0.006
 common+0.006
 bruises+0.006
Neg logit contributions
pole-0.007
 warrior-0.006
emaker-0.006
stone-0.006
ickets-0.006
Token him
Token ID683
Feature activation+7.37e-03

Pos logit contributions
emaker+0.009
pole+0.009
ados+0.008
 warrior+0.008
ickets+0.008
Neg logit contributions
 fault-0.012
 common-0.011
 shampoo-0.011
 vinegar-0.011
 bruises-0.011
Token her
Token ID607
Feature activation-1.96e-02

Pos logit contributions
 shampoo+0.009
 common+0.009
 fault+0.009
 vinegar+0.009
 bruises+0.009
Neg logit contributions
pole-0.012
emaker-0.011
ados-0.011
 warrior-0.011
stone-0.011
Token other
Token ID584
Feature activation+4.53e-02

Pos logit contributions
 mushroom+0.022
 image+0.022
 King+0.021
ados+0.021
stone+0.021
Neg logit contributions
ours-0.033
 Qu-0.033
 vinegar-0.033
 shampoo-0.032
Aw-0.032
Token bath
Token ID7837
Feature activation+7.97e-02

Pos logit contributions
 vinegar+0.066
ours+0.066
 common+0.066
 shampoo+0.065
 fault+0.065
Neg logit contributions
 warrior-0.060
pole-0.059
emaker-0.058
ados-0.058
ickets-0.056
Tokenro
Token ID305
Feature activation+1.39e-01

Pos logit contributions
 common+0.147
 bruises+0.144
 fault+0.142
 vinegar+0.140
 cheaper+0.139
Neg logit contributions
est-0.074
 around-0.074
ickets-0.072
oon-0.071
emaker-0.069
Tokenbes
Token ID12636
Feature activation+3.70e-02

Pos logit contributions
 fault+0.222
 shampoo+0.221
 vinegar+0.220
 L+0.217
ours+0.214
Neg logit contributions
pole-0.177
oon-0.166
emaker-0.164
ados-0.164
 warrior-0.161
Token.
Token ID13
Feature activation+6.34e-03

Pos logit contributions
 shampoo+0.061
 common+0.061
 fault+0.060
 vinegar+0.060
 L+0.059
Neg logit contributions
pole-0.048
emaker-0.043
stone-0.042
 warrior-0.042
ados-0.042
Token She
Token ID1375
Feature activation-1.70e-02

Pos logit contributions
 fault+0.011
 common+0.011
 bruises+0.011
 shampoo+0.011
 vinegar+0.010
Neg logit contributions
pole-0.008
ados-0.007
ickets-0.007
 warrior-0.007
emaker-0.007
Token had
Token ID550
Feature activation+1.87e-02

Pos logit contributions
pole+0.022
lf+0.021
 warrior+0.020
stone+0.019
 around+0.019
Neg logit contributions
 fault-0.031
 common-0.026
 vinegar-0.026
 injuries-0.026
 bruises-0.026
Token a
Token ID257
Feature activation+9.10e-04

Pos logit contributions
ours+0.037
ses+0.035
etchup+0.034
 arose+0.033
 common+0.033
Neg logit contributions
 Charlie-0.016
 around-0.016
pole-0.015
 dragons-0.015
 all-0.015
Token man
Token ID582
Feature activation+5.64e-03

Pos logit contributions
 fault+0.053
 common+0.051
ours+0.050
ucker+0.048
 L+0.047
Neg logit contributions
 warrior-0.031
 King-0.029
pole-0.028
 knight-0.027
 eagle-0.027
Token drove
Token ID10357
Feature activation+2.29e-02

Pos logit contributions
 fault+0.007
 shampoo+0.006
 common+0.006
 vinegar+0.006
 bruises+0.006
Neg logit contributions
pole-0.010
 warrior-0.010
emaker-0.010
stone-0.010
ickets-0.009
Token off
Token ID572
Feature activation-3.02e-02

Pos logit contributions
 shampoo+0.039
 fault+0.038
 vinegar+0.037
 common+0.037
 L+0.036
Neg logit contributions
pole-0.029
emaker-0.028
 warrior-0.028
ickets-0.027
ados-0.026
Token in
Token ID287
Feature activation+3.44e-03

Pos logit contributions
pole+0.045
emaker+0.043
 warrior+0.043
ickets+0.042
ados+0.041
Neg logit contributions
 shampoo-0.044
 fault-0.043
 vinegar-0.042
 L-0.042
 common-0.042
Token his
Token ID465
Feature activation+4.07e-02

Pos logit contributions
 fault+0.006
aj+0.006
 shampoo+0.006
ours+0.006
 vinegar+0.006
Neg logit contributions
 warrior-0.004
 Charlie-0.004
 King-0.004
emaker-0.004
pole-0.004
Token brand
Token ID4508
Feature activation+1.39e-01

Pos logit contributions
 fault+0.069
 shampoo+0.068
 vinegar+0.067
 L+0.066
 common+0.064
Neg logit contributions
 warrior-0.048
pole-0.047
 King-0.044
 kingdom-0.043
ados-0.042
Token new
Token ID649
Feature activation+9.06e-02

Pos logit contributions
 shampoo+0.168
 fault+0.168
 bruises+0.165
 vinegar+0.163
 common+0.160
Neg logit contributions
pole-0.230
ados-0.216
stone-0.213
emaker-0.212
 warrior-0.211
Token car
Token ID1097
Feature activation+1.04e-01

Pos logit contributions
 vinegar+0.160
 fault+0.157
 L+0.156
 shampoo+0.155
ours+0.152
Neg logit contributions
pole-0.103
 warrior-0.099
est-0.090
ados-0.088
 King-0.087
Token,
Token ID11
Feature activation+8.67e-03

Pos logit contributions
 shampoo+0.170
 fault+0.168
 vinegar+0.164
 common+0.163
 L+0.160
Neg logit contributions
pole-0.136
emaker-0.128
 warrior-0.128
ickets-0.122
ados-0.121
Token and
Token ID290
Feature activation-8.76e-03

Pos logit contributions
 fault+0.014
 shampoo+0.013
 common+0.013
 vinegar+0.013
 bruises+0.012
Neg logit contributions
pole-0.012
 warrior-0.011
emaker-0.011
stone-0.011
ados-0.010
Token he
Token ID339
Feature activation+2.41e-02

Pos logit contributions
pole+0.012
 warrior+0.012
emaker+0.012
stone+0.011
 King+0.011
Neg logit contributions
 fault-0.014
 common-0.013
 shampoo-0.013
 vinegar-0.013
ours-0.013
Token children
Token ID1751
Feature activation+4.71e-02

Pos logit contributions
pole+0.017
 warrior+0.017
stone+0.016
 King+0.016
 eagle+0.015
Neg logit contributions
 fault-0.016
 vinegar-0.015
 shampoo-0.015
 common-0.014
 bruises-0.014
Token put
Token ID1234
Feature activation-2.13e-02

Pos logit contributions
 shampoo+0.070
 common+0.070
 fault+0.070
 vinegar+0.070
 bruises+0.067
Neg logit contributions
pole-0.071
 warrior-0.063
ickets-0.063
emaker-0.062
 King-0.061
Token on
Token ID319
Feature activation-1.73e-02

Pos logit contributions
pole+0.026
 down+0.026
ados+0.026
 around+0.025
est+0.023
Neg logit contributions
 fault-0.036
 common-0.033
aj-0.033
 bruises-0.032
rou-0.032
Token their
Token ID511
Feature activation+2.14e-02

Pos logit contributions
ados+0.026
 Charlie+0.025
pole+0.025
 King+0.024
 around+0.024
Neg logit contributions
 fault-0.023
ses-0.022
aj-0.021
ours-0.021
 bruises-0.021
Token bath
Token ID7837
Feature activation+9.16e-02

Pos logit contributions
 fault+0.032
 arose+0.031
ours+0.030
ucker+0.030
 L+0.029
Neg logit contributions
 warrior-0.028
 King-0.027
pole-0.027
ados-0.027
 eagle-0.026
Tokenro
Token ID305
Feature activation+1.39e-01

Pos logit contributions
 bruises+0.164
 vinegar+0.162
 fault+0.159
 common+0.157
 ruined+0.153
Neg logit contributions
pole-0.091
oon-0.091
est-0.090
ickets-0.089
 around-0.087
Tokenbes
Token ID12636
Feature activation+3.93e-02

Pos logit contributions
 vinegar+0.224
 fault+0.220
 bruises+0.219
 shampoo+0.217
ours+0.212
Neg logit contributions
pole-0.177
oon-0.166
emaker-0.159
 warrior-0.159
ados-0.158
Token and
Token ID290
Feature activation+1.61e-02

Pos logit contributions
 shampoo+0.063
 fault+0.063
 vinegar+0.062
 common+0.061
 bruises+0.061
Neg logit contributions
pole-0.052
 warrior-0.048
emaker-0.048
ickets-0.047
stone-0.046
Token ran
Token ID4966
Feature activation-3.09e-03

Pos logit contributions
 fault+0.027
 common+0.024
 vinegar+0.022
rou+0.022
ses+0.021
Neg logit contributions
 forth-0.021
 down-0.021
 warrior-0.021
pole-0.021
 King-0.020
Token around
Token ID1088
Feature activation-2.72e-02

Pos logit contributions
pole+0.002
 down+0.002
 warrior+0.002
 around+0.002
emaker+0.002
Neg logit contributions
 fault-0.006
 vinegar-0.006
 bruises-0.006
 shampoo-0.006
 common-0.006
Token in
Token ID287
Feature activation+1.09e-02

Pos logit contributions
 around+0.030
 down+0.028
 warrior+0.026
 through+0.025
 outside+0.025
Neg logit contributions
 fault-0.052
 bruises-0.050
 vinegar-0.050
aj-0.050
ours-0.049
Token his
Token ID465
Feature activation+8.64e-03

Pos logit contributions
 fault+0.015
 shampoo+0.015
 bruises+0.014
 vinegar+0.014
 common+0.014
Neg logit contributions
pole-0.015
 warrior-0.015
emaker-0.015
ickets-0.014
ados-0.014
Token favorite
Token ID4004
Feature activation+2.56e-02

Pos logit contributions
 shampoo+0.013
 vinegar+0.013
 fault+0.013
 bruises+0.013
 L+0.013
Neg logit contributions
 warrior-0.012
pole-0.011
 King-0.011
ados-0.010
stone-0.010
Token shows
Token ID2523
Feature activation-2.40e-02

Pos logit contributions
 shampoo+0.040
 fault+0.040
 vinegar+0.039
 common+0.038
 L+0.038
Neg logit contributions
pole-0.035
emaker-0.033
 warrior-0.033
ickets-0.032
ados-0.031
Token on
Token ID319
Feature activation-1.35e-02

Pos logit contributions
pole+0.033
 warrior+0.030
emaker+0.030
ickets+0.030
ados+0.029
Neg logit contributions
 shampoo-0.038
 fault-0.038
 vinegar-0.038
 common-0.037
 bruises-0.037
Token their
Token ID511
Feature activation+1.64e-02

Pos logit contributions
 warrior+0.017
pole+0.016
 Charlie+0.016
 King+0.016
lf+0.016
Neg logit contributions
 fault-0.022
 vinegar-0.021
 bruises-0.021
 shampoo-0.021
ours-0.020
Token brand
Token ID4508
Feature activation+1.38e-01

Pos logit contributions
 shampoo+0.024
 vinegar+0.024
 fault+0.024
 L+0.024
 bruises+0.023
Neg logit contributions
pole-0.023
 warrior-0.023
ados-0.021
 King-0.021
stone-0.021
Token new
Token ID649
Feature activation+8.38e-02

Pos logit contributions
 fault+0.150
 shampoo+0.149
 bruises+0.145
 vinegar+0.143
 common+0.139
Neg logit contributions
pole-0.252
 warrior-0.238
emaker-0.238
ickets-0.236
ados-0.234
Token television
Token ID5581
Feature activation+3.24e-02

Pos logit contributions
 shampoo+0.128
 fault+0.125
 common+0.121
 vinegar+0.121
 L+0.119
Neg logit contributions
pole-0.119
emaker-0.115
 warrior-0.113
ickets-0.111
ados-0.108
Token.
Token ID13
Feature activation-2.56e-03

Pos logit contributions
 shampoo+0.047
 fault+0.047
 vinegar+0.045
 common+0.045
 L+0.044
Neg logit contributions
pole-0.048
emaker-0.046
 warrior-0.046
ickets-0.044
ados-0.044
Token<|endoftext|>
Token ID50256
Feature activation+3.54e-03

Pos logit contributions
pole+0.004
ickets+0.003
umbo+0.003
 warrior+0.003
 Charlie+0.003
Neg logit contributions
 shampoo-0.004
 fault-0.004
 vinegar-0.004
 common-0.004
 bruises-0.004
TokenOnce
Token ID7454
Feature activation+3.42e-02

Pos logit contributions
 fault+0.005
 shampoo+0.005
 vinegar+0.005
 bruises+0.005
 common+0.004
Neg logit contributions
pole-0.005
emaker-0.005
ickets-0.005
 warrior-0.005
oon-0.005
Tokenâ
Token ID22940
Feature activation+3.06e-02

Pos logit contributions
 fault+0.036
 shampoo+0.035
 common+0.034
 vinegar+0.034
 bruises+0.034
Neg logit contributions
pole-0.042
 warrior-0.041
emaker-0.040
ickets-0.040
stone-0.039
Token
Token ID26391
Feature activation+3.91e-02

Pos logit contributions
 shampoo+0.053
 fault+0.053
 vinegar+0.051
 common+0.051
 L+0.050
Neg logit contributions
pole-0.037
emaker-0.035
 warrior-0.034
ickets-0.033
ados-0.032
Token
Token ID8151
Feature activation+5.80e-02

Pos logit contributions
 shampoo+0.059
 vinegar+0.058
 fault+0.057
 common+0.055
 bruises+0.055
Neg logit contributions
pole-0.054
 warrior-0.052
ickets-0.052
emaker-0.052
ados-0.050
Tokens
Token ID82
Feature activation+2.47e-02

Pos logit contributions
 shampoo+0.098
 bruises+0.097
 vinegar+0.096
 fault+0.095
 common+0.094
Neg logit contributions
pole-0.074
ickets-0.072
emaker-0.069
umb-0.066
umbo-0.066
Token Spring
Token ID8225
Feature activation+6.49e-02

Pos logit contributions
 vinegar+0.033
 bruises+0.033
 common+0.033
 fault+0.032
 shampoo+0.032
Neg logit contributions
pole-0.036
est-0.033
ickets-0.033
 around-0.032
 down-0.031
Tokentime
Token ID2435
Feature activation+1.36e-01

Pos logit contributions
 bruises+0.093
 fault+0.091
 vinegar+0.090
 shampoo+0.086
 common+0.084
Neg logit contributions
pole-0.095
 warrior-0.093
ickets-0.089
est-0.089
emaker-0.088
Token.
Token ID13
Feature activation+1.68e-03

Pos logit contributions
 bruises+0.219
 fault+0.217
 vinegar+0.214
 shampoo+0.204
ours+0.204
Neg logit contributions
pole-0.172
 warrior-0.162
est-0.157
ickets-0.157
 King-0.152
Token This
Token ID770
Feature activation+3.87e-02

Pos logit contributions
 fault+0.003
 common+0.003
 vinegar+0.003
 ruined+0.003
 shampoo+0.003
Neg logit contributions
pole-0.002
ickets-0.002
 warrior-0.002
emaker-0.002
umbo-0.002
Token is
Token ID318
Feature activation+2.25e-02

Pos logit contributions
 bruises+0.054
 fault+0.053
 vinegar+0.053
ses+0.050
 injuries+0.049
Neg logit contributions
 warrior-0.059
pole-0.057
est-0.056
ickets-0.055
oon-0.055
Token the
Token ID262
Feature activation-3.19e-02

Pos logit contributions
ses+0.038
 bruises+0.037
 fault+0.036
aj+0.035
 vinegar+0.035
Neg logit contributions
 around-0.025
pole-0.024
 Charlie-0.024
 King-0.023
 forward-0.023
Token time
Token ID640
Feature activation+3.68e-02

Pos logit contributions
 warrior+0.038
pole+0.037
 King+0.036
 eagle+0.036
 angel+0.033
Neg logit contributions
ours-0.055
 fault-0.054
 vinegar-0.053
 bruises-0.053
 common-0.052
Token bird
Token ID6512
Feature activation+1.05e-02

Pos logit contributions
 warrior+0.002
pole+0.002
emaker+0.001
stone+0.001
 eagle+0.001
Neg logit contributions
 shampoo-0.003
 fault-0.003
 vinegar-0.003
 common-0.003
aj-0.003
Token.
Token ID13
Feature activation-9.88e-03

Pos logit contributions
 shampoo+0.017
 fault+0.016
 vinegar+0.016
 common+0.016
 bruises+0.016
Neg logit contributions
pole-0.015
emaker-0.014
 warrior-0.014
stone-0.013
ickets-0.013
Token You
Token ID921
Feature activation+2.05e-02

Pos logit contributions
pole+0.012
emaker+0.012
 warrior+0.012
ickets+0.011
ados+0.011
Neg logit contributions
 shampoo-0.017
 fault-0.016
 vinegar-0.016
 common-0.016
 L-0.016
Token admit
Token ID9159
Feature activation+2.33e-02

Pos logit contributions
 shampoo+0.019
 fault+0.019
 vinegar+0.018
 common+0.018
 L+0.018
Neg logit contributions
pole-0.041
emaker-0.040
 warrior-0.039
ickets-0.039
ados-0.038
Token your
Token ID534
Feature activation+6.78e-02

Pos logit contributions
 shampoo+0.032
 fault+0.031
 vinegar+0.030
 L+0.030
 common+0.030
Neg logit contributions
pole-0.037
emaker-0.035
 warrior-0.035
ickets-0.034
ados-0.033
Token fault
Token ID8046
Feature activation+1.33e-01

Pos logit contributions
 vinegar+0.109
 shampoo+0.106
ours+0.104
 L+0.104
 Qu+0.103
Neg logit contributions
 warrior-0.085
 eagle-0.085
 owl-0.084
 angel-0.082
pole-0.079
Token and
Token ID290
Feature activation+6.36e-03

Pos logit contributions
 shampoo+0.193
 fault+0.188
 vinegar+0.186
 common+0.185
 bruises+0.180
Neg logit contributions
pole-0.200
emaker-0.191
 warrior-0.189
ickets-0.184
ados-0.182
Token ask
Token ID1265
Feature activation-1.71e-02

Pos logit contributions
 fault+0.010
 vinegar+0.010
 shampoo+0.010
aj+0.010
 common+0.010
Neg logit contributions
 warrior-0.008
pole-0.008
ados-0.008
 owl-0.008
stone-0.008
Token for
Token ID329
Feature activation-6.91e-03

Pos logit contributions
pole+0.019
 warrior+0.018
ados+0.018
emaker+0.018
ickets+0.017
Neg logit contributions
 fault-0.030
 shampoo-0.030
 vinegar-0.029
 common-0.028
 bruises-0.028
Token mercy
Token ID17703
Feature activation+8.88e-03

Pos logit contributions
 owl+0.007
 warrior+0.006
 Charlie+0.006
ados+0.006
 eagle+0.006
Neg logit contributions
 fault-0.013
ours-0.013
aj-0.012
outed-0.012
ucker-0.012
Token.
Token ID13
Feature activation-9.79e-03

Pos logit contributions
 vinegar+0.018
 shampoo+0.018
 bleach+0.017
 bruises+0.017
ses+0.017
Neg logit contributions
pole-0.008
 warrior-0.007
emaker-0.007
est-0.007
other-0.007
Token were
Token ID547
Feature activation-1.02e-02

Pos logit contributions
pole+0.093
 warrior+0.090
emaker+0.089
ickets+0.087
stone+0.085
Neg logit contributions
 fault-0.064
 shampoo-0.064
 common-0.061
 vinegar-0.061
 bruises-0.058
Token so
Token ID523
Feature activation-1.08e-02

Pos logit contributions
pole+0.014
emaker+0.014
 warrior+0.013
ickets+0.013
ados+0.013
Neg logit contributions
 shampoo-0.016
 fault-0.016
 vinegar-0.015
 common-0.015
 L-0.015
Token proud
Token ID6613
Feature activation-4.79e-02

Pos logit contributions
pole+0.014
 warrior+0.014
emaker+0.014
ickets+0.013
stone+0.013
Neg logit contributions
 shampoo-0.017
 fault-0.017
 vinegar-0.017
 common-0.016
 L-0.016
Token of
Token ID286
Feature activation+1.86e-02

Pos logit contributions
pole+0.042
 warrior+0.040
emaker+0.039
ickets+0.039
stone+0.038
Neg logit contributions
 fault-0.097
 shampoo-0.096
 common-0.095
 vinegar-0.094
 bruises-0.093
Token their
Token ID511
Feature activation+3.51e-02

Pos logit contributions
aj+0.032
 shampoo+0.029
 fault+0.028
 cheaper+0.028
 vinegar+0.028
Neg logit contributions
pole-0.024
 Charlie-0.024
 warrior-0.024
 Bernie-0.023
 trolls-0.023
Token super
Token ID2208
Feature activation+1.33e-01

Pos logit contributions
 L+0.054
 shampoo+0.052
 fault+0.051
 vinegar+0.050
 common+0.050
Neg logit contributions
 warrior-0.046
pole-0.043
stone-0.042
 eagle-0.042
ados-0.041
Token strong
Token ID1913
Feature activation+5.09e-02

Pos logit contributions
 shampoo+0.189
 fault+0.185
 vinegar+0.180
 common+0.178
 L+0.177
Neg logit contributions
pole-0.201
 warrior-0.193
emaker-0.193
ickets-0.187
ados-0.184
Token work
Token ID670
Feature activation+1.39e-02

Pos logit contributions
 shampoo+0.078
 vinegar+0.076
 L+0.076
 fault+0.076
 bruises+0.075
Neg logit contributions
 warrior-0.067
pole-0.065
emaker-0.063
ados-0.061
 eagle-0.060
Token that
Token ID326
Feature activation+2.78e-02

Pos logit contributions
 shampoo+0.022
 fault+0.021
 vinegar+0.021
 common+0.021
 L+0.021
Neg logit contributions
pole-0.019
emaker-0.018
 warrior-0.018
ickets-0.017
ados-0.017
Token they
Token ID484
Feature activation+8.79e-03

Pos logit contributions
aj+0.031
 shampoo+0.031
 fault+0.030
 bruises+0.030
 vinegar+0.029
Neg logit contributions
pole-0.051
 warrior-0.049
emaker-0.048
stone-0.047
ickets-0.046
Token all
Token ID477
Feature activation-3.14e-02

Pos logit contributions
 shampoo+0.010
 fault+0.010
 vinegar+0.010
 common+0.010
 L+0.010
Neg logit contributions
pole-0.015
emaker-0.015
 warrior-0.015
ickets-0.014
ados-0.014
Token.
Token ID13
Feature activation+3.54e-03

Pos logit contributions
 shampoo+0.043
 fault+0.042
 vinegar+0.040
 L+0.040
 common+0.040
Neg logit contributions
pole-0.051
emaker-0.049
 warrior-0.049
ickets-0.048
ados-0.047
Token He
Token ID679
Feature activation-8.50e-03

Pos logit contributions
 shampoo+0.006
 fault+0.006
 vinegar+0.006
 common+0.006
 L+0.006
Neg logit contributions
pole-0.004
emaker-0.004
 warrior-0.004
ickets-0.004
ados-0.004
Token was
Token ID373
Feature activation+8.25e-03

Pos logit contributions
pole+0.013
 warrior+0.012
 King+0.011
lf+0.011
emaker+0.011
Neg logit contributions
 fault-0.013
 vinegar-0.013
 common-0.012
 shampoo-0.012
 bruises-0.012
Token wearing
Token ID5762
Feature activation+2.31e-03

Pos logit contributions
 fault+0.013
 vinegar+0.013
 shampoo+0.013
 common+0.013
 bruises+0.013
Neg logit contributions
pole-0.011
 warrior-0.010
emaker-0.010
 King-0.009
ickets-0.009
Token his
Token ID465
Feature activation+3.65e-02

Pos logit contributions
 fault+0.004
 vinegar+0.003
ours+0.003
 bruises+0.003
 shampoo+0.003
Neg logit contributions
 warrior-0.003
pole-0.003
 King-0.003
ados-0.003
 Charlie-0.003
Token brand
Token ID4508
Feature activation+1.32e-01

Pos logit contributions
 fault+0.050
 vinegar+0.050
 shampoo+0.047
ours+0.045
 bruises+0.045
Neg logit contributions
pole-0.055
 warrior-0.054
 King-0.052
ados-0.051
ickets-0.050
Token new
Token ID649
Feature activation+8.14e-02

Pos logit contributions
 fault+0.164
 bruises+0.157
 vinegar+0.157
 shampoo+0.154
 common+0.149
Neg logit contributions
pole-0.220
ados-0.205
emaker-0.205
umbo-0.205
ickets-0.205
Token icy
Token ID30284
Feature activation+8.22e-02

Pos logit contributions
 fault+0.109
 shampoo+0.109
 vinegar+0.108
 bruises+0.103
 common+0.103
Neg logit contributions
pole-0.127
 warrior-0.122
emaker-0.119
ickets-0.116
ados-0.116
Token blue
Token ID4171
Feature activation+4.41e-02

Pos logit contributions
 shampoo+0.103
 fault+0.102
 vinegar+0.099
 common+0.097
 L+0.096
Neg logit contributions
pole-0.136
 warrior-0.131
emaker-0.131
ickets-0.128
ados-0.126
Token jacket
Token ID15224
Feature activation+1.99e-02

Pos logit contributions
 fault+0.062
 vinegar+0.061
 common+0.059
 bruises+0.058
 shampoo+0.057
Neg logit contributions
pole-0.066
 warrior-0.063
ickets-0.063
emaker-0.062
ados-0.062
Token as
Token ID355
Feature activation+2.11e-03

Pos logit contributions
 shampoo+0.029
 fault+0.029
 vinegar+0.028
 common+0.027
 L+0.027
Neg logit contributions
pole-0.029
emaker-0.028
 warrior-0.028
ickets-0.027
ados-0.027
Token hours
Token ID2250
Feature activation+2.18e-02

Pos logit contributions
 shampoo+0.026
 common+0.025
 fault+0.024
 bruises+0.024
 vinegar+0.024
Neg logit contributions
pole-0.025
emaker-0.024
ickets-0.024
 warrior-0.023
ados-0.023
Token helping
Token ID5742
Feature activation+1.36e-02

Pos logit contributions
 shampoo+0.034
 fault+0.034
 vinegar+0.033
 common+0.033
 L+0.032
Neg logit contributions
pole-0.030
emaker-0.028
 warrior-0.028
ickets-0.027
ados-0.027
Token people
Token ID661
Feature activation+2.40e-02

Pos logit contributions
 shampoo+0.022
 common+0.021
 L+0.021
 fault+0.021
 vinegar+0.020
Neg logit contributions
pole-0.018
emaker-0.018
 warrior-0.018
ickets-0.017
umbo-0.017
Token understand
Token ID1833
Feature activation+1.45e-02

Pos logit contributions
 shampoo+0.033
 fault+0.031
 common+0.031
 L+0.030
 vinegar+0.030
Neg logit contributions
emaker-0.036
pole-0.036
 warrior-0.036
ados-0.035
ickets-0.035
Token their
Token ID511
Feature activation+7.01e-02

Pos logit contributions
 vinegar+0.024
 fault+0.024
 shampoo+0.023
ses+0.023
 bruises+0.023
Neg logit contributions
pole-0.018
ados-0.017
emaker-0.017
 warrior-0.017
 King-0.016
Token history
Token ID2106
Feature activation+1.31e-01

Pos logit contributions
 shampoo+0.103
 vinegar+0.101
 L+0.098
 fault+0.096
 bruises+0.095
Neg logit contributions
 warrior-0.099
pole-0.097
ados-0.095
emaker-0.093
 trolls-0.092
Token.
Token ID13
Feature activation+1.91e-03

Pos logit contributions
 shampoo+0.170
 fault+0.168
 common+0.162
 vinegar+0.160
 L+0.158
Neg logit contributions
pole-0.214
emaker-0.208
 warrior-0.205
ickets-0.201
ados-0.198
Token
Token ID198
Feature activation+4.28e-03

Pos logit contributions
 shampoo+0.003
 vinegar+0.003
 bruises+0.003
 fault+0.003
 common+0.003
Neg logit contributions
pole-0.003
ickets-0.003
emaker-0.003
umbo-0.003
 warrior-0.003
Token
Token ID198
Feature activation+1.04e-03

Pos logit contributions
 shampoo+0.006
 vinegar+0.006
 fault+0.006
 bruises+0.006
 common+0.006
Neg logit contributions
pole-0.006
ickets-0.006
emaker-0.006
 warrior-0.006
umbo-0.006
TokenOne
Token ID3198
Feature activation+5.06e-02

Pos logit contributions
 shampoo+0.001
 fault+0.001
 vinegar+0.001
 bruises+0.001
 common+0.001
Neg logit contributions
pole-0.002
 warrior-0.002
emaker-0.002
ickets-0.002
umbo-0.002
Token day
Token ID1110
Feature activation+1.22e-02

Pos logit contributions
 shampoo+0.087
 common+0.083
 fault+0.083
 L+0.083
 vinegar+0.082
Neg logit contributions
pole-0.064
emaker-0.061
 warrior-0.059
ados-0.059
ickets-0.059
Token the
Token ID262
Feature activation-1.79e-02

Pos logit contributions
 fault+0.023
aj+0.022
ses+0.022
 bruises+0.022
 vinegar+0.022
Neg logit contributions
pole-0.017
ados-0.017
 warrior-0.017
 down-0.016
 King-0.016
Token tree
Token ID5509
Feature activation-2.10e-02

Pos logit contributions
pole+0.014
 warrior+0.013
emaker+0.013
ados+0.012
stone+0.012
Neg logit contributions
 shampoo-0.038
 fault-0.038
 common-0.037
 vinegar-0.037
 L-0.037
Token to
Token ID284
Feature activation+1.56e-02

Pos logit contributions
pole+0.028
emaker+0.028
 warrior+0.028
ickets+0.027
ados+0.026
Neg logit contributions
 shampoo-0.033
 fault-0.032
 vinegar-0.031
 L-0.031
 common-0.031
Token its
Token ID663
Feature activation+2.55e-02

Pos logit contributions
 fault+0.025
 shampoo+0.025
aj+0.025
ours+0.024
 vinegar+0.024
Neg logit contributions
pole-0.020
 warrior-0.020
emaker-0.019
 King-0.019
 Charlie-0.018
Token once
Token ID1752
Feature activation+3.48e-02

Pos logit contributions
 shampoo+0.044
 vinegar+0.044
 fault+0.042
 L+0.042
 common+0.042
Neg logit contributions
pole-0.031
 warrior-0.029
stone-0.027
ados-0.027
emaker-0.027
Token former
Token ID1966
Feature activation+1.31e-01

Pos logit contributions
 fault+0.058
 shampoo+0.058
 vinegar+0.057
 common+0.056
ours+0.055
Neg logit contributions
pole-0.046
emaker-0.041
est-0.041
 warrior-0.041
stone-0.040
Token beauty
Token ID8737
Feature activation+3.93e-02

Pos logit contributions
 shampoo+0.182
 fault+0.173
 vinegar+0.172
 L+0.172
 bruises+0.166
Neg logit contributions
pole-0.202
 warrior-0.193
ados-0.189
emaker-0.189
ickets-0.184
Token.
Token ID13
Feature activation+1.83e-03

Pos logit contributions
 shampoo+0.058
 fault+0.057
 vinegar+0.055
 common+0.054
 L+0.054
Neg logit contributions
pole-0.058
 warrior-0.055
emaker-0.055
ickets-0.053
ados-0.053
Token He
Token ID679
Feature activation+4.36e-03

Pos logit contributions
 shampoo+0.004
 vinegar+0.003
 bruises+0.003
 common+0.003
 ruined+0.003
Neg logit contributions
pole-0.002
 warrior-0.002
ickets-0.002
umbo-0.002
person-0.002
Token was
Token ID373
Feature activation+2.55e-02

Pos logit contributions
 fault+0.006
 shampoo+0.005
 vinegar+0.005
 common+0.005
 L+0.005
Neg logit contributions
pole-0.008
 warrior-0.007
stone-0.007
emaker-0.007
 eagle-0.007
Token happy
Token ID3772
Feature activation-1.34e-02

Pos logit contributions
 shampoo+0.042
 vinegar+0.042
 fault+0.042
 common+0.041
 bruises+0.040
Neg logit contributions
pole-0.034
 warrior-0.030
emaker-0.030
 King-0.029
stone-0.028
Tokenmy
Token ID1820
Feature activation-2.12e-03

Pos logit contributions
 fault+0.014
 common+0.014
 vinegar+0.013
 shampoo+0.013
 Qu+0.013
Neg logit contributions
pole-0.014
emaker-0.013
stone-0.013
on-0.012
 owl-0.012
Token had
Token ID550
Feature activation+3.00e-02

Pos logit contributions
pole+0.003
stone+0.003
emaker+0.003
 owl+0.003
ard+0.003
Neg logit contributions
 common-0.003
 vinegar-0.003
 shampoo-0.003
 fault-0.003
 Qu-0.003
Token told
Token ID1297
Feature activation-1.87e-02

Pos logit contributions
 common+0.044
 vinegar+0.043
 Qu+0.043
 shampoo+0.042
 fault+0.042
Neg logit contributions
pole-0.041
stone-0.040
on-0.039
emaker-0.037
oon-0.037
Token him
Token ID683
Feature activation+2.82e-02

Pos logit contributions
pole+0.023
emaker+0.022
 warrior+0.021
ickets+0.021
ados+0.021
Neg logit contributions
 shampoo-0.032
 fault-0.032
 vinegar-0.031
 common-0.031
 bruises-0.030
Token long
Token ID890
Feature activation+3.91e-02

Pos logit contributions
 shampoo+0.045
 vinegar+0.044
 common+0.043
aj+0.042
 bruises+0.042
Neg logit contributions
pole-0.036
stone-0.034
 warrior-0.034
emaker-0.034
ados-0.033
Token ago
Token ID2084
Feature activation+1.29e-01

Pos logit contributions
 Qu+0.059
 vinegar+0.056
 common+0.055
ours+0.055
Aw+0.054
Neg logit contributions
est-0.051
 warrior-0.049
emaker-0.047
ados-0.047
 owl-0.047
Token.
Token ID13
Feature activation-3.51e-04

Pos logit contributions
 shampoo+0.214
 vinegar+0.212
 common+0.210
 Qu+0.206
 fault+0.205
Neg logit contributions
pole-0.160
ados-0.144
emaker-0.143
lf-0.141
person-0.139
Token The
Token ID383
Feature activation+2.37e-02

Pos logit contributions
pole+0.000
 warrior+0.000
ickets+0.000
ados+0.000
 Charlie+0.000
Neg logit contributions
 fault-0.001
 shampoo-0.001
 common-0.001
 vinegar-0.001
 bruises-0.001
Token bird
Token ID6512
Feature activation+1.52e-02

Pos logit contributions
 fault+0.042
 common+0.041
ours+0.041
 shampoo+0.040
 vinegar+0.039
Neg logit contributions
 warrior-0.029
 King-0.027
 eagle-0.026
 owl-0.026
pole-0.025
Token spread
Token ID4104
Feature activation-1.81e-02

Pos logit contributions
 fault+0.019
 shampoo+0.018
 common+0.017
 vinegar+0.017
 L+0.016
Neg logit contributions
pole-0.028
emaker-0.026
 warrior-0.026
stone-0.025
ickets-0.025
Token out
Token ID503
Feature activation-2.07e-02

Pos logit contributions
pole+0.024
emaker+0.023
 warrior+0.023
ickets+0.022
ados+0.022
Neg logit contributions
 fault-0.029
 shampoo-0.029
 common-0.028
 vinegar-0.028
 bruises-0.027
Token brother
Token ID3956
Feature activation+4.87e-02

Pos logit contributions
 vinegar+0.015
 fault+0.015
 common+0.015
ours+0.014
 bruises+0.014
Neg logit contributions
 warrior-0.011
emaker-0.011
 owl-0.010
 King-0.010
 knight-0.010
Token would
Token ID561
Feature activation+1.11e-02

Pos logit contributions
 vinegar+0.062
 fault+0.062
 common+0.062
 shampoo+0.059
 bruises+0.058
Neg logit contributions
pole-0.080
emaker-0.079
 warrior-0.077
ickets-0.075
umbo-0.074
Token wear
Token ID5806
Feature activation-9.15e-03

Pos logit contributions
 vinegar+0.019
 fault+0.019
 bruises+0.019
aj+0.018
 shampoo+0.018
Neg logit contributions
pole-0.014
 warrior-0.013
ickets-0.012
amber-0.012
emaker-0.012
Token their
Token ID511
Feature activation+2.98e-02

Pos logit contributions
 around+0.015
 down+0.013
 through+0.013
 outdoors+0.013
 outside+0.013
Neg logit contributions
 fault-0.014
ses-0.013
 vinegar-0.013
 arose-0.013
 bruises-0.013
Token bath
Token ID7837
Feature activation+8.33e-02

Pos logit contributions
 fault+0.053
 arose+0.051
ours+0.049
 vinegar+0.049
rou+0.048
Neg logit contributions
 around-0.033
est-0.032
 outdoors-0.030
 King-0.028
 down-0.028
Tokenro
Token ID305
Feature activation+1.29e-01

Pos logit contributions
 fault+0.156
 vinegar+0.152
 bruises+0.151
 common+0.148
 shampoo+0.145
Neg logit contributions
pole-0.084
ickets-0.080
oon-0.077
est-0.076
ados-0.076
Tokenbes
Token ID12636
Feature activation+2.02e-02

Pos logit contributions
 fault+0.204
 vinegar+0.203
 shampoo+0.198
 L+0.195
 bruises+0.194
Neg logit contributions
pole-0.169
emaker-0.159
 warrior-0.158
oon-0.156
lf-0.155
Token together
Token ID1978
Feature activation+2.09e-03

Pos logit contributions
 shampoo+0.030
 fault+0.029
 common+0.028
 L+0.028
 vinegar+0.028
Neg logit contributions
pole-0.029
emaker-0.028
 warrior-0.028
ickets-0.027
ados-0.027
Token and
Token ID290
Feature activation+8.61e-03

Pos logit contributions
 vinegar+0.004
 fault+0.004
 bruises+0.004
 shampoo+0.004
 common+0.004
Neg logit contributions
pole-0.002
 warrior-0.002
emaker-0.002
stone-0.002
ickets-0.002
Token play
Token ID711
Feature activation+2.82e-02

Pos logit contributions
 fault+0.014
ours+0.014
 vinegar+0.014
 bruises+0.014
aj+0.013
Neg logit contributions
 forth-0.011
 around-0.011
pole-0.011
 King-0.011
 Charlie-0.011
Token games
Token ID1830
Feature activation-1.60e-02

Pos logit contributions
 fault+0.054
 vinegar+0.050
 bruises+0.050
 common+0.048
 shampoo+0.047
Neg logit contributions
pole-0.030
 warrior-0.030
 around-0.029
oon-0.028
emaker-0.027
Token feeling
Token ID4203
Feature activation-6.90e-03

Pos logit contributions
pole+0.012
 warrior+0.012
 King+0.011
stone+0.011
emaker+0.011
Neg logit contributions
 fault-0.018
 vinegar-0.017
 shampoo-0.017
 bruises-0.016
aj-0.016
Token good
Token ID922
Feature activation+1.76e-02

Pos logit contributions
 warrior+0.008
 King+0.008
 around+0.008
pole+0.008
 forward+0.008
Neg logit contributions
 fault-0.012
aj-0.012
ses-0.011
 vinegar-0.011
omo-0.011
Token because
Token ID780
Feature activation+5.28e-03

Pos logit contributions
 vinegar+0.031
 shampoo+0.030
 common+0.030
 bruises+0.029
 fault+0.029
Neg logit contributions
 warrior-0.020
pole-0.020
emaker-0.020
stone-0.019
ados-0.019
Token his
Token ID465
Feature activation+5.19e-02

Pos logit contributions
 fault+0.010
 shampoo+0.010
 vinegar+0.009
 common+0.009
aj+0.009
Neg logit contributions
pole-0.006
 warrior-0.005
emaker-0.005
ickets-0.005
ados-0.005
Token special
Token ID2041
Feature activation+6.69e-02

Pos logit contributions
 shampoo+0.087
 vinegar+0.087
 fault+0.086
 L+0.085
 bruises+0.084
Neg logit contributions
 warrior-0.061
pole-0.060
ados-0.058
 King-0.057
emaker-0.057
Token doctor
Token ID6253
Feature activation+1.27e-01

Pos logit contributions
 bruises+0.109
 vinegar+0.109
 L+0.107
 Qu+0.106
 fault+0.106
Neg logit contributions
pole-0.080
est-0.079
 warrior-0.078
 King-0.077
person-0.076
Token was
Token ID373
Feature activation+2.58e-02

Pos logit contributions
 vinegar+0.154
 shampoo+0.151
 bruises+0.147
 fault+0.145
 common+0.144
Neg logit contributions
pole-0.220
stone-0.206
 warrior-0.206
emaker-0.206
 King-0.201
Token coming
Token ID2406
Feature activation+1.98e-03

Pos logit contributions
 fault+0.041
 vinegar+0.041
ses+0.040
 shampoo+0.040
 bruises+0.040
Neg logit contributions
pole-0.035
 King-0.031
 warrior-0.031
emaker-0.030
stone-0.030
Token to
Token ID284
Feature activation+5.19e-04

Pos logit contributions
 fault+0.003
 shampoo+0.003
 vinegar+0.003
 bruises+0.003
 common+0.003
Neg logit contributions
pole-0.002
emaker-0.002
 warrior-0.002
ados-0.002
stone-0.002
Token visit
Token ID3187
Feature activation+4.56e-03

Pos logit contributions
 fault+0.001
ours+0.001
aj+0.001
outed+0.001
 vinegar+0.001
Neg logit contributions
pole-0.001
 King-0.001
 warrior-0.001
 Charlie-0.001
 owl-0.000
Token.
Token ID13
Feature activation-4.61e-03

Pos logit contributions
 shampoo+0.007
 fault+0.007
 vinegar+0.007
 bruises+0.007
 common+0.007
Neg logit contributions
pole-0.006
 warrior-0.006
emaker-0.006
ados-0.005
stone-0.005
Token his
Token ID465
Feature activation+2.03e-02

Pos logit contributions
ours+0.082
 shampoo+0.082
 vinegar+0.081
aj+0.081
 common+0.080
Neg logit contributions
pole-0.050
ados-0.050
 warrior-0.049
emaker-0.049
 King-0.045
Token friend
Token ID1545
Feature activation+3.42e-02

Pos logit contributions
 shampoo+0.034
 L+0.034
 Qu+0.034
ours+0.033
 vinegar+0.032
Neg logit contributions
 warrior-0.025
pole-0.024
 King-0.023
 owl-0.022
 eagle-0.022
Token because
Token ID780
Feature activation+1.74e-02

Pos logit contributions
 vinegar+0.063
 shampoo+0.062
 common+0.061
 fault+0.059
ours+0.059
Neg logit contributions
pole-0.039
emaker-0.037
 warrior-0.036
stone-0.034
ados-0.033
Token of
Token ID286
Feature activation+2.65e-02

Pos logit contributions
 shampoo+0.032
 fault+0.032
 vinegar+0.031
 common+0.031
aj+0.031
Neg logit contributions
pole-0.018
emaker-0.018
 warrior-0.018
ados-0.016
ickets-0.016
Token his
Token ID465
Feature activation+4.87e-02

Pos logit contributions
aj+0.052
ours+0.050
 shampoo+0.049
 fault+0.048
 vinegar+0.048
Neg logit contributions
ados-0.028
 Charlie-0.027
 Mickey-0.026
pole-0.026
emaker-0.026
Token selfish
Token ID20363
Feature activation+1.26e-01

Pos logit contributions
 shampoo+0.080
 L+0.080
 Qu+0.078
 vinegar+0.076
ours+0.076
Neg logit contributions
 warrior-0.062
pole-0.058
 King-0.057
 owl-0.057
 eagle-0.057
Tokenness
Token ID1108
Feature activation+4.59e-02

Pos logit contributions
 shampoo+0.191
 vinegar+0.183
 common+0.183
 fault+0.182
 L+0.182
Neg logit contributions
pole-0.179
 warrior-0.175
emaker-0.172
ados-0.167
ickets-0.163
Token.
Token ID13
Feature activation+5.97e-03

Pos logit contributions
 vinegar+0.068
 shampoo+0.068
 common+0.068
ours+0.067
 L+0.066
Neg logit contributions
pole-0.064
emaker-0.062
ickets-0.059
stone-0.059
 warrior-0.058
Token<|endoftext|>
Token ID50256
Feature activation+8.01e-03

Pos logit contributions
 shampoo+0.008
 fault+0.007
 vinegar+0.007
 common+0.007
 bruises+0.007
Neg logit contributions
pole-0.010
emaker-0.010
 warrior-0.009
ickets-0.009
ados-0.009
TokenOnce
Token ID7454
Feature activation+4.20e-02

Pos logit contributions
 fault+0.012
 shampoo+0.012
 vinegar+0.012
 bruises+0.012
ours+0.011
Neg logit contributions
pole-0.011
ickets-0.011
emaker-0.010
oon-0.010
 warrior-0.010
Token upon
Token ID2402
Feature activation+1.24e-02

Pos logit contributions
 shampoo+0.046
 fault+0.044
 vinegar+0.043
 common+0.042
 bruises+0.041
Neg logit contributions
pole-0.078
emaker-0.076
 warrior-0.074
ickets-0.073
ados-0.072
Token learned
Token ID4499
Feature activation+2.62e-02

Pos logit contributions
pole+0.029
emaker+0.028
 warrior+0.028
ickets+0.027
ados+0.027
Neg logit contributions
 shampoo-0.016
 fault-0.015
 vinegar-0.015
 L-0.014
 common-0.014
Token that
Token ID326
Feature activation+2.92e-02

Pos logit contributions
ses+0.047
 vinegar+0.046
ours+0.045
 fault+0.045
etchup+0.044
Neg logit contributions
ados-0.027
 owl-0.026
 Charlie-0.025
stone-0.025
 Mickey-0.025
Token even
Token ID772
Feature activation+1.37e-02

Pos logit contributions
 shampoo+0.038
 fault+0.037
 vinegar+0.036
 common+0.036
 L+0.035
Neg logit contributions
pole-0.047
emaker-0.046
 warrior-0.046
ickets-0.044
ados-0.044
Token though
Token ID996
Feature activation+1.69e-02

Pos logit contributions
 fault+0.024
aj+0.023
ses+0.022
 vinegar+0.022
 shampoo+0.022
Neg logit contributions
 warrior-0.017
emaker-0.016
pole-0.016
stone-0.015
ados-0.015
Token his
Token ID465
Feature activation+5.67e-02

Pos logit contributions
aj+0.031
 fault+0.030
 vinegar+0.030
ses+0.030
outed+0.030
Neg logit contributions
ados-0.016
 warrior-0.015
 Charlie-0.015
lf-0.015
emaker-0.015
Token license
Token ID5964
Feature activation+1.26e-01

Pos logit contributions
 L+0.095
 vinegar+0.094
 arose+0.091
 Qu+0.090
ours+0.088
Neg logit contributions
 warrior-0.069
 eagle-0.063
emaker-0.057
 owl-0.057
 image-0.057
Token was
Token ID373
Feature activation+3.28e-02

Pos logit contributions
 common+0.133
 vinegar+0.132
 L+0.131
 shampoo+0.131
aj+0.125
Neg logit contributions
pole-0.222
emaker-0.220
 warrior-0.216
stone-0.212
est-0.208
Token special
Token ID2041
Feature activation-6.06e-03

Pos logit contributions
ours+0.050
 L+0.049
aj+0.049
ses+0.049
 unison+0.049
Neg logit contributions
pole-0.043
stone-0.039
 owl-0.039
 down-0.038
 around-0.038
Token and
Token ID290
Feature activation-2.92e-02

Pos logit contributions
 warrior+0.005
pole+0.005
ados+0.005
emaker+0.005
stone+0.005
Neg logit contributions
 common-0.012
 vinegar-0.012
 shampoo-0.012
 L-0.011
aj-0.011
Token valuable
Token ID8119
Feature activation+1.94e-02

Pos logit contributions
stone+0.036
pole+0.034
 warrior+0.034
ados+0.033
emaker+0.033
Neg logit contributions
aj-0.048
 shampoo-0.047
 fault-0.046
 common-0.045
 L-0.045
Token,
Token ID11
Feature activation-1.64e-02

Pos logit contributions
aj+0.033
 vinegar+0.032
 common+0.032
ours+0.031
 bruises+0.031
Neg logit contributions
stone-0.022
emaker-0.022
 warrior-0.021
ados-0.021
est-0.021
Token animals
Token ID4695
Feature activation+2.44e-03

Pos logit contributions
aj+0.002
ours+0.002
outed+0.002
 fault+0.002
omo+0.002
Neg logit contributions
 King-0.001
 owl-0.001
 mushroom-0.001
 trolls-0.001
pole-0.001
Token and
Token ID290
Feature activation-4.08e-03

Pos logit contributions
 fault+0.004
 shampoo+0.004
 vinegar+0.004
 bruises+0.004
 common+0.004
Neg logit contributions
pole-0.003
 warrior-0.003
stone-0.003
emaker-0.003
ados-0.003
Token people
Token ID661
Feature activation+2.15e-02

Pos logit contributions
 trolls+0.004
 King+0.004
 owl+0.004
 dragons+0.004
 warrior+0.003
Neg logit contributions
aj-0.008
 fault-0.008
ours-0.008
ucker-0.008
etchup-0.008
Token from
Token ID422
Feature activation+1.13e-02

Pos logit contributions
 fault+0.035
 vinegar+0.034
 shampoo+0.034
 bruises+0.034
 common+0.033
Neg logit contributions
pole-0.029
emaker-0.027
stone-0.026
 warrior-0.026
 King-0.025
Token long
Token ID890
Feature activation+4.01e-02

Pos logit contributions
aj+0.022
omo+0.021
 fault+0.021
ucker+0.020
 bruises+0.020
Neg logit contributions
 King-0.013
 around-0.012
 warrior-0.012
 angel-0.012
 kingdom-0.012
Token ago
Token ID2084
Feature activation+1.26e-01

Pos logit contributions
 vinegar+0.055
 shampoo+0.055
 fault+0.051
 Qu+0.051
 common+0.051
Neg logit contributions
ados-0.059
pole-0.058
 warrior-0.058
emaker-0.057
 trolls-0.056
Token.
Token ID13
Feature activation+1.41e-02

Pos logit contributions
 shampoo+0.218
 vinegar+0.216
 common+0.212
 Qu+0.209
 fault+0.207
Neg logit contributions
pole-0.144
ados-0.134
lf-0.132
emaker-0.123
on-0.123
Token Sam
Token ID3409
Feature activation-1.22e-02

Pos logit contributions
 shampoo+0.020
 fault+0.020
 common+0.019
 vinegar+0.019
 bruises+0.019
Neg logit contributions
pole-0.021
 warrior-0.020
ickets-0.020
emaker-0.020
ados-0.020
Token's
Token ID338
Feature activation+1.29e-02

Pos logit contributions
pole+0.021
 warrior+0.021
emaker+0.020
stone+0.020
 King+0.019
Neg logit contributions
 fault-0.015
 vinegar-0.015
 shampoo-0.014
 common-0.014
 bruises-0.014
Token mom
Token ID1995
Feature activation+2.32e-02

Pos logit contributions
 vinegar+0.019
 shampoo+0.019
 common+0.018
 fault+0.018
 bruises+0.018
Neg logit contributions
 warrior-0.019
 King-0.018
pole-0.017
emaker-0.017
 trolls-0.017
Token said
Token ID531
Feature activation-1.07e-03

Pos logit contributions
 fault+0.033
 common+0.032
 vinegar+0.031
 shampoo+0.031
 bruises+0.030
Neg logit contributions
pole-0.038
emaker-0.035
 warrior-0.034
stone-0.033
 King-0.033
Token made
Token ID925
Feature activation-4.32e-02

Pos logit contributions
pole+0.063
 warrior+0.061
 King+0.059
 around+0.056
 Charlie+0.056
Neg logit contributions
 fault-0.064
 vinegar-0.060
 common-0.059
 shampoo-0.059
 bruises-0.058
Token him
Token ID683
Feature activation-3.71e-02

Pos logit contributions
pole+0.054
emaker+0.052
 around+0.052
ickets+0.052
ados+0.051
Neg logit contributions
 common-0.067
aj-0.063
 vinegar-0.063
 fault-0.062
 bruises-0.061
Token an
Token ID281
Feature activation-4.71e-02

Pos logit contributions
pole+0.045
ickets+0.041
 warrior+0.040
 down+0.040
emaker+0.040
Neg logit contributions
 vinegar-0.061
 common-0.059
 shampoo-0.059
 fault-0.058
ours-0.057
Token even
Token ID772
Feature activation-4.06e-02

Pos logit contributions
emaker+0.075
pole+0.074
ickets+0.072
 warrior+0.072
ados+0.070
Neg logit contributions
 shampoo-0.063
 fault-0.062
 vinegar-0.060
 L-0.057
 bruises-0.057
Token y
Token ID331
Feature activation-7.26e-02

Pos logit contributions
pole+0.054
 down+0.049
 warrior+0.049
 around+0.048
est+0.047
Neg logit contributions
 fault-0.075
 common-0.065
ses-0.065
 Qu-0.065
aj-0.063
Tokenumm
Token ID13929
Feature activation-1.40e-01

Pos logit contributions
pole+0.080
 warrior+0.072
emaker+0.071
stone+0.065
 King+0.065
Neg logit contributions
 shampoo-0.140
 fault-0.139
 vinegar-0.136
 L-0.130
 common-0.130
Tokenier
Token ID959
Feature activation-2.35e-02

Pos logit contributions
pole+0.106
emaker+0.101
 warrior+0.093
ickets+0.088
ados+0.088
Neg logit contributions
 shampoo-0.307
 fault-0.300
 common-0.299
 vinegar-0.296
 L-0.294
Token snack
Token ID26906
Feature activation+1.86e-02

Pos logit contributions
pole+0.032
emaker+0.031
 warrior+0.031
ickets+0.029
ados+0.029
Neg logit contributions
 shampoo-0.037
 fault-0.036
 vinegar-0.035
 common-0.035
 L-0.035
Token and
Token ID290
Feature activation-3.48e-03

Pos logit contributions
 shampoo+0.028
 fault+0.027
 common+0.026
 vinegar+0.026
 bruises+0.026
Neg logit contributions
pole-0.027
emaker-0.026
 warrior-0.025
ickets-0.025
ados-0.025
Token they
Token ID484
Feature activation+7.48e-04

Pos logit contributions
pole+0.005
stone+0.004
ados+0.004
 forth+0.004
lf+0.004
Neg logit contributions
 fault-0.006
 common-0.005
aj-0.005
ses-0.005
ours-0.005
Token both
Token ID1111
Feature activation-7.64e-03

Pos logit contributions
 fault+0.001
 shampoo+0.001
 common+0.001
aj+0.001
 vinegar+0.001
Neg logit contributions
pole-0.001
emaker-0.001
 warrior-0.001
ickets-0.001
stone-0.001
Token idea
Token ID2126
Feature activation-7.04e-02

Pos logit contributions
 warrior+0.052
pole+0.048
est+0.046
lf+0.046
 outdoors+0.045
Neg logit contributions
 Qu-0.078
 L-0.078
 fault-0.078
 bruises-0.078
 vinegar-0.077
Token.
Token ID13
Feature activation-9.82e-03

Pos logit contributions
pole+0.103
emaker+0.098
 warrior+0.097
stone+0.093
ickets+0.093
Neg logit contributions
 shampoo-0.104
 fault-0.102
 vinegar-0.100
 common-0.099
 bruises-0.097
Token He
Token ID679
Feature activation-1.22e-02

Pos logit contributions
pole+0.012
emaker+0.012
 warrior+0.011
ickets+0.011
stone+0.011
Neg logit contributions
 fault-0.017
 shampoo-0.017
 L-0.016
 vinegar-0.016
 common-0.016
Token brought
Token ID3181
Feature activation-3.26e-02

Pos logit contributions
pole+0.020
 warrior+0.019
stone+0.018
emaker+0.018
 eagle+0.017
Neg logit contributions
 fault-0.017
 shampoo-0.017
 vinegar-0.016
 common-0.016
 bruises-0.016
Token a
Token ID257
Feature activation-3.67e-02

Pos logit contributions
pole+0.054
emaker+0.051
 warrior+0.051
ickets+0.050
ados+0.050
Neg logit contributions
 shampoo-0.042
 fault-0.042
 vinegar-0.040
 common-0.040
 L-0.039
Token basket
Token ID7988
Feature activation-1.37e-01

Pos logit contributions
 warrior+0.050
pole+0.049
stone+0.047
 mushroom+0.047
 King+0.044
Neg logit contributions
 fault-0.056
 L-0.053
 bruises-0.053
 vinegar-0.051
 Qu-0.051
Token and
Token ID290
Feature activation-2.84e-02

Pos logit contributions
 warrior+0.225
emaker+0.222
 trolls+0.209
ados+0.208
ickets+0.208
Neg logit contributions
 shampoo-0.178
 L-0.171
 vinegar-0.167
 fault-0.163
 towels-0.160
Token filled
Token ID5901
Feature activation-3.01e-02

Pos logit contributions
stone+0.040
pole+0.039
ados+0.038
 warrior+0.038
 Charlie+0.038
Neg logit contributions
 fault-0.047
 common-0.041
 vinegar-0.037
 shampoo-0.037
 bruises-0.037
Token it
Token ID340
Feature activation-2.56e-02

Pos logit contributions
pole+0.042
ados+0.040
emaker+0.038
 warrior+0.038
stone+0.037
Neg logit contributions
 fault-0.049
 bruises-0.044
 shampoo-0.044
aj-0.043
 vinegar-0.043
Token with
Token ID351
Feature activation-1.91e-02

Pos logit contributions
emaker+0.034
 warrior+0.033
ickets+0.031
pole+0.031
 eagle+0.029
Neg logit contributions
 shampoo-0.043
 fault-0.041
 vinegar-0.041
 L-0.041
 common-0.040
Token things
Token ID1243
Feature activation-1.91e-02

Pos logit contributions
ados+0.022
pole+0.021
 down+0.021
 King+0.021
 mushroom+0.021
Neg logit contributions
 fault-0.033
aj-0.032
ours-0.031
ses-0.031
 common-0.030
Token Here
Token ID3423
Feature activation-5.01e-03

Pos logit contributions
pole+0.022
emaker+0.021
 warrior+0.021
ickets+0.020
ados+0.020
Neg logit contributions
 shampoo-0.024
 fault-0.023
 vinegar-0.023
 common-0.022
 L-0.022
Token,
Token ID11
Feature activation-3.09e-02

Pos logit contributions
pole+0.006
 warrior+0.006
emaker+0.006
ados+0.006
stone+0.006
Neg logit contributions
 fault-0.008
 shampoo-0.008
 vinegar-0.008
 bruises-0.008
 common-0.008
Token take
Token ID1011
Feature activation-3.93e-02

Pos logit contributions
pole+0.041
 warrior+0.039
emaker+0.038
ickets+0.037
stone+0.036
Neg logit contributions
 fault-0.051
 shampoo-0.050
 common-0.048
 vinegar-0.048
 bruises-0.048
Token a
Token ID257
Feature activation-1.93e-02

Pos logit contributions
pole+0.067
emaker+0.064
 warrior+0.064
ickets+0.063
ados+0.061
Neg logit contributions
 shampoo-0.050
 fault-0.048
 L-0.047
 vinegar-0.047
 common-0.047
Token cr
Token ID1067
Feature activation-7.56e-02

Pos logit contributions
pole+0.029
emaker+0.029
 warrior+0.028
ickets+0.028
ados+0.027
Neg logit contributions
 shampoo-0.028
 fault-0.027
 vinegar-0.026
 common-0.026
 L-0.026
Tokenay
Token ID323
Feature activation-1.34e-01

Pos logit contributions
 warrior+0.099
 forth+0.095
 traveller+0.094
 eagle+0.091
 trolls+0.090
Neg logit contributions
 shampoo-0.119
 vinegar-0.118
 L-0.118
 fault-0.116
 common-0.112
Tokenon
Token ID261
Feature activation-6.61e-02

Pos logit contributions
 warrior+0.134
pole+0.129
 traveller+0.124
jack+0.120
 trolls+0.118
Neg logit contributions
 shampoo-0.265
 L-0.261
 vinegar-0.260
 common-0.251
 lemon-0.242
Token."
Token ID526
Feature activation-5.02e-03

Pos logit contributions
 warrior+0.135
Charlie+0.125
emaker+0.124
 eagle+0.124
 traveller+0.122
Neg logit contributions
 L-0.069
 shampoo-0.067
 vinegar-0.061
 fault-0.059
 Sara-0.055
Token
Token ID198
Feature activation-4.28e-04

Pos logit contributions
pole+0.009
emaker+0.008
 warrior+0.008
ickets+0.008
ados+0.008
Neg logit contributions
 shampoo-0.006
 fault-0.006
 vinegar-0.006
 L-0.006
 common-0.006
Token
Token ID198
Feature activation-1.71e-03

Pos logit contributions
pole+0.001
emaker+0.001
ickets+0.001
 warrior+0.001
ados+0.001
Neg logit contributions
 fault-0.001
 shampoo-0.001
 vinegar-0.001
 common-0.001
 bruises-0.000
TokenThey
Token ID2990
Feature activation-4.07e-03

Pos logit contributions
pole+0.004
emaker+0.003
ados+0.003
 warrior+0.003
est+0.003
Neg logit contributions
 shampoo-0.002
 L-0.002
 bruises-0.002
 common-0.002
 vinegar-0.001
Tokenier
Token ID959
Feature activation-3.03e-02

Pos logit contributions
emaker+0.112
pole+0.108
ados+0.102
ickets+0.097
 warrior+0.096
Neg logit contributions
 shampoo-0.244
 common-0.240
 fault-0.237
 bruises-0.235
 vinegar-0.233
Token?
Token ID30
Feature activation-1.07e-02

Pos logit contributions
pole+0.035
 warrior+0.034
emaker+0.034
ados+0.033
stone+0.033
Neg logit contributions
 shampoo-0.052
 bruises-0.050
 vinegar-0.050
 fault-0.049
 common-0.048
Token You
Token ID921
Feature activation+2.13e-03

Pos logit contributions
pole+0.014
ados+0.013
 warrior+0.013
emaker+0.013
ickets+0.013
Neg logit contributions
 fault-0.017
 shampoo-0.017
 common-0.017
 vinegar-0.016
 bruises-0.016
Token are
Token ID389
Feature activation-2.26e-02

Pos logit contributions
 shampoo+0.003
 fault+0.003
 common+0.002
 bruises+0.002
 vinegar+0.002
Neg logit contributions
pole-0.004
 warrior-0.004
emaker-0.003
ickets-0.003
stone-0.003
Token y
Token ID331
Feature activation-6.06e-02

Pos logit contributions
pole+0.039
emaker+0.038
 warrior+0.038
ickets+0.037
ados+0.036
Neg logit contributions
 shampoo-0.028
 vinegar-0.027
 fault-0.027
 L-0.026
 common-0.026
Tokenumm
Token ID13929
Feature activation-1.33e-01

Pos logit contributions
pole+0.080
 warrior+0.074
 King+0.067
emaker+0.067
 eagle+0.066
Neg logit contributions
 shampoo-0.108
 vinegar-0.107
 fault-0.107
ours-0.103
aj-0.103
Tokenier
Token ID959
Feature activation-4.44e-02

Pos logit contributions
pole+0.154
emaker+0.148
 warrior+0.146
ickets+0.140
ados+0.138
Neg logit contributions
 shampoo-0.237
 fault-0.234
 vinegar-0.228
 common-0.227
 L-0.225
Token.
Token ID13
Feature activation-1.89e-02

Pos logit contributions
pole+0.059
 warrior+0.057
emaker+0.057
ados+0.054
ickets+0.054
Neg logit contributions
 shampoo-0.071
 fault-0.069
 vinegar-0.068
 common-0.067
 L-0.066
Token You
Token ID921
Feature activation+3.43e-03

Pos logit contributions
pole+0.027
emaker+0.026
 warrior+0.026
ickets+0.025
ados+0.025
Neg logit contributions
 shampoo-0.028
 fault-0.028
 common-0.027
 vinegar-0.027
 bruises-0.026
Token are
Token ID389
Feature activation-1.80e-02

Pos logit contributions
 fault+0.004
 shampoo+0.004
 common+0.004
 vinegar+0.004
 L+0.004
Neg logit contributions
pole-0.006
 warrior-0.006
emaker-0.006
ickets-0.006
stone-0.006
Token my
Token ID616
Feature activation-2.13e-03

Pos logit contributions
pole+0.032
emaker+0.031
 warrior+0.031
ickets+0.030
ados+0.029
Neg logit contributions
 shampoo-0.022
 vinegar-0.021
 fault-0.020
 L-0.020
 common-0.020
Token want
Token ID765
Feature activation-4.21e-02

Pos logit contributions
 bruises+0.019
aj+0.018
 vinegar+0.018
outed+0.017
 belts+0.017
Neg logit contributions
 warrior-0.012
emaker-0.011
orn-0.011
umb-0.011
string-0.010
Token to
Token ID284
Feature activation-6.70e-03

Pos logit contributions
ados+0.042
stone+0.040
pole+0.039
umbo+0.037
 King+0.036
Neg logit contributions
 fault-0.078
 common-0.075
ses-0.075
aj-0.074
 bruises-0.074
Token make
Token ID787
Feature activation-2.79e-02

Pos logit contributions
pole+0.010
 warrior+0.009
emaker+0.009
ickets+0.009
ados+0.009
Neg logit contributions
 fault-0.010
 shampoo-0.010
 vinegar-0.010
 bruises-0.009
 L-0.009
Token a
Token ID257
Feature activation-4.46e-02

Pos logit contributions
pole+0.046
ados+0.044
ickets+0.043
emaker+0.043
 warrior+0.043
Neg logit contributions
 fault-0.035
 common-0.034
 shampoo-0.033
 vinegar-0.033
 bruises-0.033
Token da
Token ID12379
Feature activation-9.23e-02

Pos logit contributions
pole+0.077
emaker+0.075
 warrior+0.074
ickets+0.073
ados+0.072
Neg logit contributions
 shampoo-0.054
 fault-0.053
 vinegar-0.051
 L-0.051
 common-0.050
Tokenisy
Token ID13560
Feature activation-1.31e-01

Pos logit contributions
 warrior+0.121
 Charlie+0.118
person+0.117
ados+0.113
 traveller+0.112
Neg logit contributions
 shampoo-0.142
rou-0.134
 lemon-0.133
 L-0.131
aj-0.130
Token necklace
Token ID38987
Feature activation-2.89e-02

Pos logit contributions
 warrior+0.198
emaker+0.197
pole+0.193
ickets+0.186
person+0.184
Neg logit contributions
 shampoo-0.189
 L-0.181
 fault-0.176
 vinegar-0.175
 common-0.170
Token too
Token ID1165
Feature activation+2.86e-02

Pos logit contributions
emaker+0.052
 warrior+0.052
person+0.049
 eagle+0.049
ados+0.049
Neg logit contributions
 L-0.032
 shampoo-0.029
 fault-0.028
 common-0.028
 cheaper-0.028
Token,
Token ID11
Feature activation-3.02e-02

Pos logit contributions
 shampoo+0.047
 fault+0.046
 common+0.045
 vinegar+0.044
 L+0.044
Neg logit contributions
pole-0.038
emaker-0.037
 warrior-0.036
ickets-0.035
ados-0.035
Token but
Token ID475
Feature activation-5.63e-02

Pos logit contributions
pole+0.042
 warrior+0.039
emaker+0.038
ickets+0.037
umbo+0.036
Neg logit contributions
 fault-0.048
 shampoo-0.048
 common-0.047
 vinegar-0.047
 bruises-0.047
Token I
Token ID314
Feature activation+2.04e-03

Pos logit contributions
pole+0.063
 warrior+0.054
stone+0.054
 King+0.052
 mushroom+0.052
Neg logit contributions
 fault-0.112
 bruises-0.107
aj-0.106
 common-0.103
 scratches-0.102
Token"
Token ID1
Feature activation-3.82e-02

Pos logit contributions
pole+0.013
emaker+0.012
 warrior+0.012
ickets+0.012
stone+0.011
Neg logit contributions
 fault-0.023
 shampoo-0.022
 vinegar-0.022
 common-0.021
 bruises-0.021
TokenIs
Token ID3792
Feature activation+3.45e-02

Pos logit contributions
pole+0.058
 warrior+0.055
emaker+0.055
ickets+0.052
stone+0.051
Neg logit contributions
 fault-0.061
aj-0.053
 vinegar-0.052
ours-0.051
 shampoo-0.051
Token it
Token ID340
Feature activation-5.88e-02

Pos logit contributions
 bruises+0.064
 common+0.063
 fault+0.062
ses+0.061
 unison+0.061
Neg logit contributions
ados-0.037
stone-0.036
pole-0.035
 King-0.033
 eagle-0.033
Token a
Token ID257
Feature activation-3.12e-02

Pos logit contributions
pole+0.099
stone+0.090
ados+0.090
ickets+0.089
 King+0.089
Neg logit contributions
 fault-0.075
 bruises-0.072
 common-0.070
 shampoo-0.070
 vinegar-0.067
Token cr
Token ID1067
Feature activation-7.96e-02

Pos logit contributions
 warrior+0.042
pole+0.041
 King+0.040
 mushroom+0.039
 eagle+0.037
Neg logit contributions
 fault-0.047
 bruises-0.047
ours-0.047
aj-0.047
outed-0.046
Tokenay
Token ID323
Feature activation-1.30e-01

Pos logit contributions
 warrior+0.091
 traveller+0.083
 trolls+0.083
 eagle+0.080
pole+0.079
Neg logit contributions
 shampoo-0.143
 vinegar-0.139
 fault-0.137
aj-0.134
 L-0.134
Tokenon
Token ID261
Feature activation-7.19e-02

Pos logit contributions
 warrior+0.076
pole+0.075
 trolls+0.061
emaker+0.061
 traveller+0.059
Neg logit contributions
 shampoo-0.308
 vinegar-0.298
 L-0.296
 fault-0.290
 common-0.287
Token?"
Token ID1701
Feature activation-5.54e-03

Pos logit contributions
pole+0.108
 warrior+0.106
emaker+0.105
ickets+0.101
ados+0.101
Neg logit contributions
 shampoo-0.102
 fault-0.099
 vinegar-0.097
 L-0.095
 common-0.095
Token Ben
Token ID3932
Feature activation-1.63e-02

Pos logit contributions
 King+0.008
 warrior+0.008
 Charlie+0.008
emaker+0.007
pole+0.007
Neg logit contributions
 fault-0.009
rou-0.008
 bruises-0.007
 vinegar-0.007
aj-0.007
Token asks
Token ID7893
Feature activation-2.45e-02

Pos logit contributions
pole+0.032
emaker+0.031
 warrior+0.030
ickets+0.030
ados+0.030
Neg logit contributions
 shampoo-0.017
 fault-0.016
 L-0.015
 vinegar-0.015
 common-0.015
Token.
Token ID13
Feature activation-6.76e-03

Pos logit contributions
pole+0.034
emaker+0.034
 warrior+0.033
ados+0.032
ickets+0.031
Neg logit contributions
 fault-0.037
 shampoo-0.036
 common-0.035
 vinegar-0.035
 bruises-0.034
Token he
Token ID339
Feature activation+2.37e-03

Pos logit contributions
pole+0.051
emaker+0.050
 warrior+0.049
ados+0.047
stone+0.046
Neg logit contributions
 fault-0.061
 shampoo-0.060
 vinegar-0.059
aj-0.058
 common-0.058
Token couldn
Token ID3521
Feature activation-1.87e-02

Pos logit contributions
 common+0.003
 fault+0.003
 shampoo+0.003
 vinegar+0.003
aj+0.003
Neg logit contributions
emaker-0.004
pole-0.004
 warrior-0.004
stone-0.004
umbo-0.004
Token't
Token ID470
Feature activation-3.47e-02

Pos logit contributions
pole+0.022
 warrior+0.021
emaker+0.020
ados+0.019
stone+0.019
Neg logit contributions
 shampoo-0.034
 fault-0.033
 vinegar-0.032
 L-0.032
 common-0.032
Token make
Token ID787
Feature activation-2.50e-02

Pos logit contributions
pole+0.069
ados+0.066
emaker+0.063
 trolls+0.063
ickets+0.062
Neg logit contributions
 shampoo-0.037
 L-0.035
 common-0.033
 Qu-0.031
 ruined-0.031
Token a
Token ID257
Feature activation-3.28e-02

Pos logit contributions
ados+0.036
pole+0.035
emaker+0.035
 warrior+0.034
umbo+0.033
Neg logit contributions
aj-0.036
 vinegar-0.035
 shampoo-0.035
 bruises-0.034
 common-0.034
Token basket
Token ID7988
Feature activation-1.29e-01

Pos logit contributions
pole+0.063
emaker+0.062
ickets+0.060
 warrior+0.060
ados+0.059
Neg logit contributions
 shampoo-0.034
 fault-0.034
 common-0.031
 vinegar-0.031
 L-0.031
Token.
Token ID13
Feature activation+2.65e-03

Pos logit contributions
 warrior+0.191
pole+0.188
emaker+0.187
ados+0.184
ickets+0.183
Neg logit contributions
 shampoo-0.184
 fault-0.179
 vinegar-0.174
 L-0.174
 common-0.171
Token He
Token ID679
Feature activation-3.99e-03

Pos logit contributions
 shampoo+0.004
 fault+0.004
 vinegar+0.004
 common+0.004
 L+0.004
Neg logit contributions
pole-0.004
emaker-0.004
 warrior-0.004
ickets-0.004
ados-0.003
Token felt
Token ID2936
Feature activation-4.66e-03

Pos logit contributions
pole+0.006
 warrior+0.006
emaker+0.006
 forth+0.005
stone+0.005
Neg logit contributions
 fault-0.006
 common-0.006
aj-0.006
 vinegar-0.006
 bruises-0.005
Token sad
Token ID6507
Feature activation+5.09e-02

Pos logit contributions
 around+0.005
 forward+0.005
 down+0.005
 warrior+0.005
 alone+0.005
Neg logit contributions
aj-0.009
 fault-0.008
ours-0.008
 common-0.008
omo-0.008
Token and
Token ID290
Feature activation-2.02e-03

Pos logit contributions
 shampoo+0.089
 common+0.088
 vinegar+0.087
 fault+0.085
 bruises+0.085
Neg logit contributions
pole-0.058
 warrior-0.057
emaker-0.057
ickets-0.053
ados-0.053
Token chair
Token ID5118
Feature activation+2.55e-02

Pos logit contributions
 shampoo+0.005
 fault+0.005
 vinegar+0.005
 common+0.005
 L+0.005
Neg logit contributions
pole-0.004
emaker-0.004
 warrior-0.003
ickets-0.003
ados-0.003
Token and
Token ID290
Feature activation+9.00e-03

Pos logit contributions
 vinegar+0.051
 common+0.051
 shampoo+0.050
 fault+0.049
 Qu+0.048
Neg logit contributions
pole-0.024
emaker-0.021
 warrior-0.020
 down-0.020
 around-0.020
Token takes
Token ID2753
Feature activation-1.95e-02

Pos logit contributions
 fault+0.012
 shampoo+0.011
 vinegar+0.011
 common+0.011
 bruises+0.011
Neg logit contributions
pole-0.014
 warrior-0.014
emaker-0.013
stone-0.013
ados-0.013
Token a
Token ID257
Feature activation-2.22e-02

Pos logit contributions
emaker+0.021
pole+0.021
 warrior+0.020
ados+0.020
 King+0.019
Neg logit contributions
 fault-0.035
 vinegar-0.034
 shampoo-0.034
 common-0.033
aj-0.033
Token cr
Token ID1067
Feature activation-7.71e-02

Pos logit contributions
pole+0.032
 warrior+0.031
emaker+0.031
ickets+0.030
stone+0.029
Neg logit contributions
 fault-0.033
 shampoo-0.033
 vinegar-0.032
 common-0.031
 bruises-0.031
Tokenay
Token ID323
Feature activation-1.28e-01

Pos logit contributions
 warrior+0.100
 forth+0.095
 trolls+0.090
ados+0.090
 traveller+0.089
Neg logit contributions
 shampoo-0.127
 fault-0.127
aj-0.122
 bruises-0.119
 L-0.118
Tokenon
Token ID261
Feature activation-6.00e-02

Pos logit contributions
pole+0.108
 warrior+0.106
ados+0.092
 trolls+0.090
 traveller+0.086
Neg logit contributions
 shampoo-0.283
 L-0.273
 vinegar-0.267
 bruises-0.266
 common-0.262
Token and
Token ID290
Feature activation-3.19e-02

Pos logit contributions
 warrior+0.099
pole+0.096
emaker+0.094
ados+0.092
ickets+0.092
Neg logit contributions
 shampoo-0.079
 fault-0.076
 L-0.075
 vinegar-0.071
 bruises-0.069
Token a
Token ID257
Feature activation-8.12e-03

Pos logit contributions
stone+0.044
 warrior+0.044
on+0.043
 Charlie+0.043
 down+0.043
Neg logit contributions
 fault-0.046
 common-0.042
omo-0.040
rou-0.040
ucker-0.039
Token paper
Token ID3348
Feature activation-3.62e-02

Pos logit contributions
pole+0.011
 warrior+0.011
stone+0.010
emaker+0.010
 King+0.010
Neg logit contributions
 fault-0.013
 common-0.012
 shampoo-0.012
 vinegar-0.012
 L-0.012
Token.
Token ID13
Feature activation-3.88e-03

Pos logit contributions
pole+0.052
emaker+0.049
 warrior+0.049
stone+0.047
ados+0.047
Neg logit contributions
 shampoo-0.054
 fault-0.054
 common-0.053
 vinegar-0.052
 bruises-0.051
Token the
Token ID262
Feature activation-9.36e-03

Pos logit contributions
aj+0.026
 fault+0.026
ours+0.025
 bruises+0.024
outed+0.024
Neg logit contributions
ados-0.021
 warrior-0.020
 Charlie-0.020
pole-0.019
 down-0.019
Token basketball
Token ID9669
Feature activation+7.34e-03

Pos logit contributions
 warrior+0.012
 eagle+0.011
pole+0.011
 King+0.011
 mushroom+0.011
Neg logit contributions
 L-0.015
 common-0.015
ours-0.015
 fault-0.015
 Qu-0.015
Token and
Token ID290
Feature activation+2.14e-03

Pos logit contributions
 shampoo+0.010
 fault+0.010
 vinegar+0.010
 L+0.010
 common+0.009
Neg logit contributions
pole-0.011
emaker-0.011
 warrior-0.011
ickets-0.011
ados-0.010
Token making
Token ID1642
Feature activation-2.15e-02

Pos logit contributions
 fault+0.003
aj+0.003
 common+0.003
 shampoo+0.003
ours+0.003
Neg logit contributions
 warrior-0.003
pole-0.003
 King-0.003
 forth-0.003
emaker-0.003
Token a
Token ID257
Feature activation-2.36e-02

Pos logit contributions
pole+0.029
 warrior+0.028
ados+0.028
 Charlie+0.027
emaker+0.027
Neg logit contributions
aj-0.032
 common-0.031
 bruises-0.031
 shampoo-0.031
 fault-0.031
Token basket
Token ID7988
Feature activation-1.28e-01

Pos logit contributions
pole+0.037
 warrior+0.037
ickets+0.034
emaker+0.034
umbo+0.034
Neg logit contributions
 fault-0.031
 shampoo-0.030
 bruises-0.029
 vinegar-0.029
 common-0.029
Token.
Token ID13
Feature activation-1.01e-02

Pos logit contributions
pole+0.181
 warrior+0.179
emaker+0.178
ados+0.170
ickets+0.170
Neg logit contributions
 shampoo-0.190
 fault-0.186
 vinegar-0.181
 L-0.179
 common-0.179
Token Sally
Token ID25737
Feature activation-3.40e-02

Pos logit contributions
pole+0.011
 warrior+0.011
ickets+0.010
emaker+0.010
umbo+0.010
Neg logit contributions
 shampoo-0.019
 fault-0.018
 vinegar-0.018
 common-0.018
 bruises-0.018
Token cheered
Token ID34767
Feature activation-1.61e-02

Pos logit contributions
pole+0.063
 warrior+0.061
emaker+0.061
ickets+0.059
stone+0.058
Neg logit contributions
 shampoo-0.037
 fault-0.036
 vinegar-0.035
 common-0.035
 bruises-0.033
Token each
Token ID1123
Feature activation+2.16e-02

Pos logit contributions
umb+0.032
orn+0.032
emaker+0.031
ickets+0.031
 warrior+0.030
Neg logit contributions
 L-0.018
 their-0.016
 Sara-0.014
 shampoo-0.014
 Qu-0.014
Token time
Token ID640
Feature activation+7.49e-02

Pos logit contributions
 shampoo+0.024
 fault+0.022
 L+0.021
 vinegar+0.021
 common+0.021
Neg logit contributions
pole-0.040
ados-0.039
emaker-0.039
stone-0.038
 warrior-0.038
Token,
Token ID11
Feature activation-1.45e-02

Pos logit contributions
pole+0.094
 warrior+0.090
emaker+0.089
stone+0.086
ados+0.086
Neg logit contributions
 shampoo-0.112
 vinegar-0.110
 fault-0.109
 common-0.107
 bruises-0.106
Token and
Token ID290
Feature activation-2.60e-02

Pos logit contributions
pole+0.017
 warrior+0.016
 eagle+0.015
emaker+0.015
 Charlie+0.015
Neg logit contributions
 shampoo-0.025
 vinegar-0.025
 fault-0.025
 common-0.025
ours-0.024
Token it
Token ID340
Feature activation+8.41e-03

Pos logit contributions
pole+0.034
 warrior+0.033
stone+0.032
 King+0.032
 Charlie+0.031
Neg logit contributions
 fault-0.042
aj-0.042
 shampoo-0.040
 vinegar-0.040
ours-0.039
Token was
Token ID373
Feature activation+1.99e-02

Pos logit contributions
 shampoo+0.009
 fault+0.009
 vinegar+0.008
 common+0.008
 L+0.008
Neg logit contributions
pole-0.016
emaker-0.015
 warrior-0.015
ickets-0.015
ados-0.015
Token pri
Token ID1293
Feature activation-3.32e-02

Pos logit contributions
 vinegar+0.032
 bruises+0.032
 shampoo+0.031
 fault+0.031
ses+0.030
Neg logit contributions
pole-0.028
 King-0.024
 Charlie-0.023
emaker-0.023
est-0.023
Tokenve
Token ID303
Feature activation-1.26e-01

Pos logit contributions
pole+0.034
emaker+0.032
 warrior+0.031
ickets+0.030
stone+0.029
Neg logit contributions
 shampoo-0.064
 fault-0.064
 vinegar-0.062
 common-0.061
 bruises-0.061
Tokenleg
Token ID1455
Feature activation-1.35e-02

Pos logit contributions
pole+0.151
emaker+0.142
 warrior+0.139
stone+0.134
ickets+0.132
Neg logit contributions
 shampoo-0.223
 fault-0.219
 vinegar-0.216
 common-0.213
 L-0.211
Tokened
Token ID276
Feature activation-3.79e-02

Pos logit contributions
pole+0.012
emaker+0.011
ickets+0.011
stone+0.010
 warrior+0.010
Neg logit contributions
 fault-0.028
 bruises-0.028
 shampoo-0.028
 vinegar-0.027
 common-0.027
Token to
Token ID284
Feature activation+1.49e-02

Pos logit contributions
pole+0.039
 warrior+0.036
emaker+0.035
ados+0.034
stone+0.033
Neg logit contributions
 shampoo-0.072
 fault-0.072
 vinegar-0.071
aj-0.069
 common-0.069
Token be
Token ID307
Feature activation+2.45e-02

Pos logit contributions
 fault+0.024
aj+0.023
 shampoo+0.023
 bruises+0.022
 vinegar+0.022
Neg logit contributions
pole-0.020
 warrior-0.020
 King-0.019
emaker-0.018
 Charlie-0.018
Token part
Token ID636
Feature activation+1.03e-02

Pos logit contributions
 fault+0.038
 shampoo+0.037
 vinegar+0.037
 bruises+0.035
 common+0.035
Neg logit contributions
pole-0.035
 warrior-0.032
emaker-0.031
 King-0.030
stone-0.030
Token to
Token ID284
Feature activation+8.86e-03

Pos logit contributions
pole+0.030
 warrior+0.029
emaker+0.029
ados+0.028
ickets+0.028
Neg logit contributions
 shampoo-0.028
 fault-0.028
 vinegar-0.027
 common-0.026
 L-0.026
Token make
Token ID787
Feature activation-1.84e-02

Pos logit contributions
 shampoo+0.013
 fault+0.012
 common+0.012
 vinegar+0.012
 L+0.012
Neg logit contributions
pole-0.014
emaker-0.013
 warrior-0.013
ados-0.013
ickets-0.013
Token an
Token ID281
Feature activation-4.76e-02

Pos logit contributions
pole+0.035
 warrior+0.034
emaker+0.034
ados+0.033
ickets+0.033
Neg logit contributions
 fault-0.018
 shampoo-0.018
 common-0.018
 vinegar-0.017
 bruises-0.017
Token ash
Token ID12530
Feature activation-5.17e-03

Pos logit contributions
emaker+0.080
ickets+0.075
oon+0.075
pole+0.075
 warrior+0.074
Neg logit contributions
 fault-0.060
 shampoo-0.059
 vinegar-0.056
 L-0.055
 cheaper-0.053
Tokentr
Token ID2213
Feature activation-1.45e-02

Pos logit contributions
emaker+0.010
 warrior+0.010
pole+0.010
ickets+0.010
ados+0.010
Neg logit contributions
 shampoo-0.005
 fault-0.005
 vinegar-0.005
 L-0.005
 bruises-0.004
Tokenay
Token ID323
Feature activation-1.26e-01

Pos logit contributions
 warrior+0.011
pole+0.011
emaker+0.010
ados+0.009
 eagle+0.009
Neg logit contributions
 fault-0.031
 shampoo-0.031
 L-0.030
 vinegar-0.030
 bruises-0.030
Token out
Token ID503
Feature activation-5.44e-02

Pos logit contributions
 warrior+0.208
pole+0.203
ados+0.198
umbo+0.194
 traveller+0.193
Neg logit contributions
 shampoo-0.159
 L-0.155
 fault-0.152
 gas-0.141
 ruined-0.140
Token of
Token ID286
Feature activation+3.67e-03

Pos logit contributions
pole+0.048
emaker+0.047
 warrior+0.045
ickets+0.043
stone+0.042
Neg logit contributions
 fault-0.115
 shampoo-0.111
 vinegar-0.109
 common-0.108
aj-0.105
Token clay
Token ID21558
Feature activation-5.92e-03

Pos logit contributions
aj+0.007
ours+0.007
ucker+0.007
outed+0.007
 fault+0.007
Neg logit contributions
 Charlie-0.004
on-0.004
 King-0.003
ados-0.003
 Mickey-0.003
Token.
Token ID13
Feature activation+1.71e-03

Pos logit contributions
pole+0.009
emaker+0.009
 warrior+0.009
ickets+0.009
ados+0.008
Neg logit contributions
 shampoo-0.008
 fault-0.008
 vinegar-0.008
 L-0.008
 common-0.007
Token As
Token ID1081
Feature activation+2.20e-02

Pos logit contributions
 L+0.003
 shampoo+0.003
 vinegar+0.002
 fault+0.002
 Qu+0.002
Neg logit contributions
emaker-0.002
pole-0.002
 warrior-0.002
ickets-0.002
quet-0.002
Token and
Token ID290
Feature activation-1.91e-02

Pos logit contributions
pole+0.004
emaker+0.003
 warrior+0.003
ickets+0.003
ados+0.003
Neg logit contributions
 fault-0.004
 shampoo-0.004
 common-0.004
 vinegar-0.004
 bruises-0.004
Token it
Token ID340
Feature activation-1.52e-03

Pos logit contributions
 Charlie+0.025
pole+0.025
 King+0.024
stone+0.024
on+0.024
Neg logit contributions
 fault-0.033
 common-0.029
aj-0.029
 shampoo-0.027
ses-0.027
Token was
Token ID373
Feature activation+1.79e-02

Pos logit contributions
pole+0.002
emaker+0.002
stone+0.002
 warrior+0.002
ickets+0.002
Neg logit contributions
 fault-0.002
 common-0.002
aj-0.002
 shampoo-0.002
 bruises-0.002
Token the
Token ID262
Feature activation-4.15e-02

Pos logit contributions
aj+0.028
 fault+0.027
 bruises+0.027
ses+0.027
ours+0.027
Neg logit contributions
pole-0.024
 mushroom-0.021
 Charlie-0.021
 down-0.020
 around-0.020
Token y
Token ID331
Feature activation-5.03e-02

Pos logit contributions
pole+0.059
 warrior+0.057
emaker+0.053
 eagle+0.053
 King+0.053
Neg logit contributions
 L-0.062
 shampoo-0.060
 common-0.059
 vinegar-0.058
 fault-0.058
Tokenumm
Token ID13929
Feature activation-1.26e-01

Pos logit contributions
pole+0.057
 warrior+0.054
emaker+0.052
stone+0.047
 King+0.047
Neg logit contributions
 vinegar-0.096
 shampoo-0.094
 fault-0.091
 common-0.089
 mustard-0.087
Tokeniest
Token ID6386
Feature activation-3.11e-02

Pos logit contributions
pole+0.115
 warrior+0.111
emaker+0.103
ickets+0.103
ados+0.099
Neg logit contributions
 shampoo-0.256
 fault-0.252
 vinegar-0.251
 common-0.243
 L-0.242
Token steak
Token ID26320
Feature activation-1.51e-02

Pos logit contributions
pole+0.043
 warrior+0.042
emaker+0.041
ados+0.040
ickets+0.039
Neg logit contributions
 fault-0.047
 shampoo-0.046
 L-0.045
 common-0.045
 bruises-0.045
Token she
Token ID673
Feature activation-1.70e-02

Pos logit contributions
pole+0.023
 warrior+0.022
emaker+0.022
ickets+0.022
ados+0.021
Neg logit contributions
 shampoo-0.022
 fault-0.021
 vinegar-0.021
 L-0.020
 common-0.020
Token ever
Token ID1683
Feature activation+1.71e-02

Pos logit contributions
pole+0.027
 warrior+0.026
stone+0.025
emaker+0.025
 King+0.025
Neg logit contributions
 fault-0.024
 shampoo-0.024
 vinegar-0.022
 bruises-0.022
ours-0.021
Token tasted
Token ID29187
Feature activation-1.90e-02

Pos logit contributions
 fault+0.031
 shampoo+0.031
ours+0.028
aj+0.028
 bruises+0.028
Neg logit contributions
stone-0.021
pole-0.020
emaker-0.020
 warrior-0.020
ard-0.019
Token berries
Token ID36322
Feature activation-2.81e-02

Pos logit contributions
pole+0.035
ados+0.034
 warrior+0.033
stone+0.032
 mushroom+0.031
Neg logit contributions
 fault-0.044
aj-0.041
 common-0.040
 shampoo-0.039
 bruises-0.038
Token to
Token ID284
Feature activation-7.20e-05

Pos logit contributions
pole+0.039
emaker+0.037
 warrior+0.037
ickets+0.036
ados+0.035
Neg logit contributions
 shampoo-0.044
 fault-0.043
 vinegar-0.042
 common-0.042
 bruises-0.041
Token make
Token ID787
Feature activation-3.05e-02

Pos logit contributions
pole+0.000
ickets+0.000
 warrior+0.000
emaker+0.000
ados+0.000
Neg logit contributions
 fault-0.000
aj-0.000
 bruises-0.000
 shampoo-0.000
 common-0.000
Token a
Token ID257
Feature activation-4.53e-02

Pos logit contributions
pole+0.049
emaker+0.046
 warrior+0.046
ados+0.046
ickets+0.046
Neg logit contributions
 fault-0.041
 shampoo-0.040
 common-0.039
 vinegar-0.038
 bruises-0.038
Token y
Token ID331
Feature activation-9.99e-02

Pos logit contributions
emaker+0.079
pole+0.077
ickets+0.075
 warrior+0.075
ados+0.073
Neg logit contributions
 shampoo-0.055
 fault-0.053
 vinegar-0.052
 common-0.051
 L-0.051
Tokenummy
Token ID13513
Feature activation-1.26e-01

Pos logit contributions
 warrior+0.143
pole+0.136
 King+0.135
person+0.134
emaker+0.131
Neg logit contributions
 shampoo-0.152
 vinegar-0.148
omo-0.148
 lemon-0.147
ucker-0.142
Token snack
Token ID26906
Feature activation-3.00e-02

Pos logit contributions
emaker+0.227
pole+0.219
 warrior+0.218
ickets+0.211
umbo+0.206
Neg logit contributions
 shampoo-0.156
 vinegar-0.149
 fault-0.139
 lemon-0.136
 common-0.133
Token!"
Token ID2474
Feature activation-9.75e-03

Pos logit contributions
 warrior+0.043
emaker+0.043
pole+0.042
ickets+0.039
umbo+0.039
Neg logit contributions
 shampoo-0.045
 fault-0.044
 vinegar-0.044
 L-0.043
 common-0.042
Token The
Token ID383
Feature activation+2.23e-02

Pos logit contributions
pole+0.016
emaker+0.016
 warrior+0.016
ickets+0.015
umbo+0.015
Neg logit contributions
 shampoo-0.013
 L-0.012
 vinegar-0.012
 fault-0.011
 bruises-0.011
Token squirrel
Token ID33039
Feature activation+2.49e-03

Pos logit contributions
 shampoo+0.036
 fault+0.035
 vinegar+0.034
 common+0.034
 L+0.033
Neg logit contributions
pole-0.030
emaker-0.029
 warrior-0.029
ickets-0.028
ados-0.027
Token agreed
Token ID4987
Feature activation-2.44e-02

Pos logit contributions
 shampoo+0.002
 fault+0.002
 L+0.002
 vinegar+0.002
 common+0.002
Neg logit contributions
pole-0.005
emaker-0.005
 warrior-0.005
ados-0.005
ickets-0.005
Token.
Token ID13
Feature activation+2.33e-03

Pos logit contributions
 shampoo+0.004
 fault+0.004
 vinegar+0.004
 L+0.004
 common+0.004
Neg logit contributions
pole-0.005
emaker-0.005
 warrior-0.005
ickets-0.005
ados-0.005
Token She
Token ID1375
Feature activation-2.86e-02

Pos logit contributions
 bruises+0.004
 common+0.004
 fault+0.004
 shampoo+0.004
 vinegar+0.004
Neg logit contributions
pole-0.003
umbo-0.003
ickets-0.003
emaker-0.003
 warrior-0.003
Token always
Token ID1464
Feature activation+1.44e-02

Pos logit contributions
 warrior+0.040
pole+0.040
 King+0.038
 owl+0.037
 kingdom+0.036
Neg logit contributions
 fault-0.045
 vinegar-0.044
 common-0.041
 shampoo-0.040
 bruises-0.040
Token brought
Token ID3181
Feature activation-3.07e-02

Pos logit contributions
 fault+0.021
 vinegar+0.021
 shampoo+0.020
 bruises+0.019
 common+0.018
Neg logit contributions
 warrior-0.021
pole-0.021
stone-0.019
emaker-0.019
 King-0.019
Token a
Token ID257
Feature activation-3.12e-02

Pos logit contributions
pole+0.054
 warrior+0.052
emaker+0.052
ados+0.051
ickets+0.051
Neg logit contributions
 fault-0.035
 shampoo-0.035
 vinegar-0.034
 common-0.033
 bruises-0.033
Token basket
Token ID7988
Feature activation-1.26e-01

Pos logit contributions
pole+0.046
 warrior+0.045
stone+0.043
emaker+0.043
ickets+0.043
Neg logit contributions
 fault-0.044
 shampoo-0.043
 vinegar-0.043
 bruises-0.042
 L-0.042
Token with
Token ID351
Feature activation-2.88e-02

Pos logit contributions
 warrior+0.233
emaker+0.229
ickets+0.217
ados+0.212
 eagle+0.211
Neg logit contributions
 shampoo-0.145
 L-0.144
 cheaper-0.134
 fault-0.130
 Sara-0.130
Token some
Token ID617
Feature activation+1.95e-02

Pos logit contributions
ados+0.028
pole+0.026
 King+0.026
stone+0.025
 mushroom+0.024
Neg logit contributions
 fault-0.061
aj-0.057
ses-0.054
ours-0.053
 vinegar-0.052
Token bread
Token ID8509
Feature activation-9.20e-03

Pos logit contributions
 fault+0.038
 L+0.033
aj+0.033
rou+0.033
omo+0.033
Neg logit contributions
pole-0.020
ados-0.020
 mushroom-0.020
stone-0.019
 owl-0.018
Token and
Token ID290
Feature activation-5.71e-03

Pos logit contributions
pole+0.011
ados+0.010
stone+0.010
emaker+0.010
ickets+0.010
Neg logit contributions
 fault-0.016
 shampoo-0.016
 common-0.016
 bruises-0.016
 vinegar-0.015
Token cheese
Token ID9891
Feature activation+2.47e-02

Pos logit contributions
 mushroom+0.007
 Charlie+0.006
 owl+0.006
stone+0.006
ados+0.006
Neg logit contributions
 fault-0.011
rou-0.010
aj-0.010
outed-0.009
ours-0.009
Token Can
Token ID1680
Feature activation-1.29e-03

Pos logit contributions
pole+0.021
 warrior+0.020
ickets+0.019
emaker+0.019
ados+0.019
Neg logit contributions
 fault-0.026
 shampoo-0.026
 vinegar-0.025
 common-0.024
 bruises-0.024
Token I
Token ID314
Feature activation-2.76e-02

Pos logit contributions
pole+0.002
emaker+0.002
 warrior+0.002
ickets+0.002
ados+0.002
Neg logit contributions
 shampoo-0.002
 fault-0.002
 vinegar-0.002
 common-0.002
 L-0.002
Token have
Token ID423
Feature activation-2.43e-02

Pos logit contributions
pole+0.039
emaker+0.037
ickets+0.036
 warrior+0.036
umbo+0.036
Neg logit contributions
 fault-0.042
 vinegar-0.039
 shampoo-0.039
 bruises-0.039
aj-0.038
Token a
Token ID257
Feature activation-1.45e-02

Pos logit contributions
on+0.032
ados+0.031
 Charlie+0.028
pole+0.028
ons+0.028
Neg logit contributions
ses-0.039
 fault-0.039
aj-0.037
rou-0.036
 common-0.035
Token cr
Token ID1067
Feature activation-7.45e-02

Pos logit contributions
 warrior+0.019
pole+0.019
 mushroom+0.018
 King+0.017
 eagle+0.017
Neg logit contributions
 bruises-0.022
 L-0.022
 fault-0.021
 shampoo-0.021
 vinegar-0.021
Tokenay
Token ID323
Feature activation-1.25e-01

Pos logit contributions
 warrior+0.079
 trolls+0.072
pole+0.072
 traveller+0.070
ados+0.069
Neg logit contributions
 fault-0.142
 shampoo-0.139
omo-0.133
aj-0.132
 vinegar-0.132
Tokenon
Token ID261
Feature activation-5.82e-02

Pos logit contributions
pole+0.097
 warrior+0.094
 trolls+0.082
 traveller+0.077
stone+0.076
Neg logit contributions
 shampoo-0.281
 vinegar-0.270
 bruises-0.266
 L-0.265
 common-0.261
Token instead
Token ID2427
Feature activation-3.29e-02

Pos logit contributions
pole+0.090
 warrior+0.087
emaker+0.086
ickets+0.083
ados+0.083
Neg logit contributions
 shampoo-0.081
 fault-0.079
 vinegar-0.077
 L-0.076
 common-0.076
Token?"
Token ID1701
Feature activation-7.80e-03

Pos logit contributions
pole+0.050
 warrior+0.049
emaker+0.049
ickets+0.047
ados+0.047
Neg logit contributions
 shampoo-0.046
 fault-0.045
 vinegar-0.044
 common-0.043
 L-0.043
Token Her
Token ID2332
Feature activation+4.73e-03

Pos logit contributions
 Charlie+0.010
ados+0.010
 warrior+0.010
emaker+0.010
pole+0.010
Neg logit contributions
 vinegar-0.012
 fault-0.012
 shampoo-0.012
 common-0.012
 ruined-0.011
Token uncle
Token ID7711
Feature activation+2.10e-02

Pos logit contributions
 vinegar+0.007
 shampoo+0.007
 common+0.006
 fault+0.006
 bruises+0.006
Neg logit contributions
 warrior-0.007
pole-0.007
emaker-0.007
 owl-0.006
 eagle-0.006
Token She
Token ID1375
Feature activation-3.72e-02

Pos logit contributions
 shampoo+0.004
 fault+0.004
 L+0.004
 vinegar+0.004
 common+0.004
Neg logit contributions
pole-0.003
emaker-0.003
 warrior-0.002
ickets-0.002
ados-0.002
Token wanted
Token ID2227
Feature activation-3.51e-02

Pos logit contributions
pole+0.054
 King+0.050
lf+0.050
 warrior+0.049
 owl+0.048
Neg logit contributions
 fault-0.063
 vinegar-0.058
 shampoo-0.055
 bruises-0.055
ours-0.053
Token to
Token ID284
Feature activation-2.97e-02

Pos logit contributions
pole+0.040
ados+0.038
 Charlie+0.038
 trolls+0.038
 King+0.038
Neg logit contributions
aj-0.057
 fault-0.057
 common-0.056
 shampoo-0.056
 vinegar-0.055
Token make
Token ID787
Feature activation-3.60e-02

Pos logit contributions
pole+0.044
 warrior+0.042
emaker+0.042
ickets+0.041
ados+0.040
Neg logit contributions
 fault-0.043
 shampoo-0.043
 vinegar-0.042
 L-0.041
 common-0.041
Token a
Token ID257
Feature activation-5.08e-02

Pos logit contributions
ados+0.053
pole+0.052
stone+0.049
emaker+0.049
 warrior+0.048
Neg logit contributions
 common-0.050
 fault-0.050
 shampoo-0.047
 vinegar-0.046
 bruises-0.046
Token sweet
Token ID6029
Feature activation-1.25e-01

Pos logit contributions
pole+0.074
 warrior+0.071
emaker+0.070
ickets+0.068
ados+0.067
Neg logit contributions
 shampoo-0.075
 fault-0.074
 vinegar-0.072
 common-0.071
 L-0.071
Token perfume
Token ID40094
Feature activation-3.79e-02

Pos logit contributions
emaker+0.213
pole+0.212
 warrior+0.205
ickets+0.205
umbo+0.197
Neg logit contributions
 shampoo-0.164
 vinegar-0.150
 fault-0.145
 common-0.144
 L-0.142
Token for
Token ID329
Feature activation-3.64e-02

Pos logit contributions
emaker+0.061
 warrior+0.060
pole+0.060
ickets+0.058
ados+0.056
Neg logit contributions
 shampoo-0.052
 fault-0.048
 vinegar-0.047
 L-0.047
 common-0.047
Token her
Token ID607
Feature activation-3.07e-02

Pos logit contributions
ados+0.039
pole+0.038
ickets+0.036
emaker+0.036
quet+0.035
Neg logit contributions
 fault-0.068
 shampoo-0.063
 common-0.062
 vinegar-0.062
aj-0.061
Token mom
Token ID1995
Feature activation+1.29e-03

Pos logit contributions
pole+0.036
 angel+0.034
 owl+0.034
ados+0.034
 King+0.034
Neg logit contributions
 vinegar-0.050
ours-0.049
 common-0.048
 shampoo-0.048
 bruises-0.047
Token.
Token ID13
Feature activation+4.13e-03

Pos logit contributions
 shampoo+0.002
 fault+0.002
 vinegar+0.002
 bruises+0.002
 common+0.002
Neg logit contributions
pole-0.001
emaker-0.001
stone-0.001
 warrior-0.001
ickets-0.001
Token happy
Token ID3772
Feature activation-2.06e-02

Pos logit contributions
 fault+0.031
 shampoo+0.030
 vinegar+0.029
 common+0.028
 bruises+0.028
Neg logit contributions
pole-0.023
emaker-0.022
ickets-0.022
 warrior-0.022
umbo-0.020
Token.
Token ID13
Feature activation+5.63e-03

Pos logit contributions
pole+0.033
emaker+0.032
 warrior+0.032
ickets+0.031
umbo+0.030
Neg logit contributions
 shampoo-0.028
 fault-0.028
 L-0.027
 vinegar-0.026
 common-0.026
Token She
Token ID1375
Feature activation-2.25e-02

Pos logit contributions
 shampoo+0.009
 fault+0.009
 L+0.009
 vinegar+0.009
 common+0.008
Neg logit contributions
pole-0.007
emaker-0.007
 warrior-0.007
stone-0.007
ickets-0.007
Token brought
Token ID3181
Feature activation-2.27e-02

Pos logit contributions
pole+0.034
 warrior+0.033
emaker+0.031
 eagle+0.031
 King+0.031
Neg logit contributions
 fault-0.032
 vinegar-0.031
 bruises-0.031
 common-0.031
 shampoo-0.030
Token a
Token ID257
Feature activation-3.06e-02

Pos logit contributions
pole+0.043
 warrior+0.042
emaker+0.041
ickets+0.040
umbo+0.039
Neg logit contributions
 shampoo-0.027
 L-0.025
 fault-0.024
 vinegar-0.024
 common-0.023
Token basket
Token ID7988
Feature activation-1.25e-01

Pos logit contributions
pole+0.043
 warrior+0.042
emaker+0.040
stone+0.040
ickets+0.039
Neg logit contributions
 fault-0.045
 shampoo-0.044
 vinegar-0.044
 L-0.043
 bruises-0.043
Token of
Token ID286
Feature activation-1.79e-02

Pos logit contributions
 warrior+0.250
emaker+0.236
 trolls+0.231
ickets+0.226
 eagle+0.225
Neg logit contributions
 shampoo-0.137
 L-0.131
 cheaper-0.119
 fault-0.117
 Sara-0.117
Token treats
Token ID18432
Feature activation-4.17e-02

Pos logit contributions
pole+0.028
 warrior+0.027
ados+0.027
emaker+0.026
ickets+0.026
Neg logit contributions
 fault-0.025
 shampoo-0.023
 common-0.023
 vinegar-0.023
 L-0.022
Token to
Token ID284
Feature activation+1.25e-02

Pos logit contributions
pole+0.060
 warrior+0.058
emaker+0.058
ickets+0.056
ados+0.055
Neg logit contributions
 shampoo-0.063
 fault-0.061
 vinegar-0.060
 L-0.059
 common-0.059
Token share
Token ID2648
Feature activation-9.18e-03

Pos logit contributions
 fault+0.024
 bruises+0.021
 shampoo+0.021
aj+0.021
 vinegar+0.021
Neg logit contributions
pole-0.015
 warrior-0.013
 King-0.013
emaker-0.013
ados-0.013
Token with
Token ID351
Feature activation-1.17e-02

Pos logit contributions
pole+0.012
emaker+0.011
 warrior+0.011
ados+0.011
ickets+0.011
Neg logit contributions
 fault-0.015
 shampoo-0.015
 vinegar-0.015
 common-0.014
 bruises-0.014
Token,
Token ID11
Feature activation-1.67e-02

Pos logit contributions
 shampoo+0.023
 fault+0.022
 L+0.021
 vinegar+0.021
 common+0.021
Neg logit contributions
pole-0.019
emaker-0.018
 warrior-0.018
ickets-0.018
ados-0.017
Token he
Token ID339
Feature activation-6.06e-03

Pos logit contributions
pole+0.022
 warrior+0.021
emaker+0.021
ados+0.021
stone+0.020
Neg logit contributions
 fault-0.028
 shampoo-0.027
 common-0.026
 vinegar-0.026
aj-0.025
Token finally
Token ID3443
Feature activation+2.41e-02

Pos logit contributions
pole+0.011
 warrior+0.011
emaker+0.011
ickets+0.010
stone+0.010
Neg logit contributions
 shampoo-0.007
 fault-0.007
 common-0.006
 vinegar-0.006
 bruises-0.006
Token made
Token ID925
Feature activation-2.16e-02

Pos logit contributions
 shampoo+0.032
 fault+0.031
 vinegar+0.030
 bruises+0.030
 common+0.030
Neg logit contributions
pole-0.039
 warrior-0.038
emaker-0.038
ickets-0.036
stone-0.036
Token a
Token ID257
Feature activation-3.15e-02

Pos logit contributions
pole+0.034
emaker+0.034
 warrior+0.033
ados+0.033
ickets+0.032
Neg logit contributions
 shampoo-0.028
 fault-0.027
 common-0.027
 vinegar-0.027
 bruises-0.026
Token basket
Token ID7988
Feature activation-1.25e-01

Pos logit contributions
pole+0.052
 warrior+0.051
emaker+0.050
ickets+0.049
ados+0.048
Neg logit contributions
 shampoo-0.040
 fault-0.039
 vinegar-0.038
 common-0.037
 L-0.037
Token!
Token ID0
Feature activation-5.82e-03

Pos logit contributions
 warrior+0.202
emaker+0.194
ados+0.193
 trolls+0.190
ickets+0.189
Neg logit contributions
 shampoo-0.162
 L-0.162
 fault-0.157
 cheaper-0.154
 ruined-0.153
Token He
Token ID679
Feature activation-8.51e-03

Pos logit contributions
pole+0.009
emaker+0.009
 warrior+0.009
ickets+0.009
ados+0.008
Neg logit contributions
 shampoo-0.008
 fault-0.008
 common-0.008
 vinegar-0.008
 bruises-0.007
Token felt
Token ID2936
Feature activation-1.04e-02

Pos logit contributions
pole+0.017
 warrior+0.016
emaker+0.016
stone+0.016
umbo+0.015
Neg logit contributions
 fault-0.008
 shampoo-0.008
 common-0.008
 vinegar-0.008
 bruises-0.007
Token so
Token ID523
Feature activation+7.05e-03

Pos logit contributions
pole+0.014
 warrior+0.013
emaker+0.013
ickets+0.012
ados+0.012
Neg logit contributions
 fault-0.017
 shampoo-0.016
 vinegar-0.016
 common-0.016
aj-0.016
Token happy
Token ID3772
Feature activation-2.94e-02

Pos logit contributions
 shampoo+0.009
 common+0.008
 vinegar+0.008
 L+0.008
 fault+0.008
Neg logit contributions
pole-0.012
emaker-0.012
 warrior-0.012
ados-0.012
ickets-0.012
Token bite
Token ID13197
Feature activation+1.26e-02

Pos logit contributions
pole+0.023
 warrior+0.022
emaker+0.021
ados+0.021
stone+0.020
Neg logit contributions
 fault-0.025
 shampoo-0.025
 bruises-0.024
 L-0.024
 common-0.024
Token and
Token ID290
Feature activation-1.61e-02

Pos logit contributions
 fault+0.022
 common+0.021
aj+0.021
 bruises+0.021
 shampoo+0.021
Neg logit contributions
pole-0.015
emaker-0.015
ickets-0.014
ados-0.014
 warrior-0.014
Token makes
Token ID1838
Feature activation-9.55e-03

Pos logit contributions
 down+0.021
 warrior+0.021
 mushroom+0.021
 King+0.021
 Charlie+0.020
Neg logit contributions
 fault-0.024
aj-0.022
 common-0.022
 injuries-0.021
outed-0.020
Token a
Token ID257
Feature activation-3.79e-02

Pos logit contributions
pole+0.013
 Charlie+0.013
on+0.013
ados+0.013
 King+0.013
Neg logit contributions
 common-0.013
aj-0.013
 bruises-0.013
 fault-0.012
 shampoo-0.012
Token y
Token ID331
Feature activation-1.03e-01

Pos logit contributions
pole+0.054
 warrior+0.053
ickets+0.050
emaker+0.049
 eagle+0.048
Neg logit contributions
 fault-0.056
 shampoo-0.055
 common-0.052
 bruises-0.051
 L-0.051
Tokenummy
Token ID13513
Feature activation-1.25e-01

Pos logit contributions
pole+0.121
 warrior+0.118
emaker+0.110
stone+0.107
 King+0.105
Neg logit contributions
 shampoo-0.188
 vinegar-0.187
 fault-0.183
 common-0.180
omo-0.176
Token sound
Token ID2128
Feature activation-3.44e-02

Pos logit contributions
pole+0.200
emaker+0.193
 warrior+0.193
ickets+0.187
ados+0.185
Neg logit contributions
 shampoo-0.165
 fault-0.163
 vinegar-0.156
 common-0.155
 L-0.154
Token.
Token ID13
Feature activation+4.79e-04

Pos logit contributions
pole+0.050
emaker+0.048
 warrior+0.047
ickets+0.046
ados+0.045
Neg logit contributions
 fault-0.051
 shampoo-0.051
 common-0.050
 vinegar-0.048
 bruises-0.048
Token
Token ID198
Feature activation+7.64e-05

Pos logit contributions
 fault+0.001
 shampoo+0.001
 bruises+0.001
 common+0.001
 ruined+0.001
Neg logit contributions
ickets-0.000
pole-0.000
 warrior-0.000
 Charlie-0.000
ados-0.000
Token
Token ID198
Feature activation-1.20e-03

Pos logit contributions
 shampoo+0.000
 fault+0.000
 vinegar+0.000
 bruises+0.000
 common+0.000
Neg logit contributions
pole-0.000
ickets-0.000
emaker-0.000
 warrior-0.000
umbo-0.000
Token"
Token ID1
Feature activation-3.29e-02

Pos logit contributions
pole+0.002
emaker+0.002
ados+0.002
 warrior+0.002
stone+0.002
Neg logit contributions
 shampoo-0.002
 common-0.002
 L-0.002
 vinegar-0.002
 bruises-0.002
Token some
Token ID617
Feature activation-1.50e-02

Pos logit contributions
pole+0.084
 warrior+0.081
emaker+0.080
ados+0.079
stone+0.078
Neg logit contributions
 shampoo-0.063
 fault-0.062
 vinegar-0.060
 common-0.060
 L-0.059
Token flowers
Token ID12734
Feature activation-6.23e-02

Pos logit contributions
 around+0.017
 mushroom+0.017
 owl+0.017
 angel+0.017
ados+0.017
Neg logit contributions
 fault-0.024
ours-0.023
 L-0.023
omo-0.023
 common-0.023
Token and
Token ID290
Feature activation-3.05e-02

Pos logit contributions
pole+0.088
emaker+0.086
 warrior+0.086
ickets+0.083
umbo+0.081
Neg logit contributions
 shampoo-0.095
 fault-0.093
 vinegar-0.090
 common-0.089
 L-0.088
Token make
Token ID787
Feature activation-3.31e-02

Pos logit contributions
 owl+0.030
 mushroom+0.029
 trolls+0.028
ados+0.027
 dragons+0.026
Neg logit contributions
 fault-0.060
omo-0.057
ours-0.056
aj-0.056
rou-0.056
Token a
Token ID257
Feature activation-4.20e-02

Pos logit contributions
pole+0.045
ados+0.045
ickets+0.041
stone+0.041
 angel+0.040
Neg logit contributions
 common-0.049
omo-0.048
aj-0.048
 fault-0.048
 shampoo-0.046
Token bou
Token ID35833
Feature activation-1.25e-01

Pos logit contributions
pole+0.059
 warrior+0.056
stone+0.053
 mushroom+0.053
emaker+0.053
Neg logit contributions
 fault-0.061
 shampoo-0.060
 vinegar-0.059
 bruises-0.058
 common-0.057
Tokenquet
Token ID21108
Feature activation-1.18e-01

Pos logit contributions
 warrior+0.112
 Charlie+0.094
 ogre+0.090
 eagle+0.090
 trolls+0.088
Neg logit contributions
 shampoo-0.266
 bruises-0.244
aj-0.243
 cheaper-0.241
 towels-0.239
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
pole+0.189
 warrior+0.188
emaker+0.188
ickets+0.181
ados+0.180
Neg logit contributions
 shampoo-0.155
 fault-0.153
 vinegar-0.147
 L-0.147
 common-0.144
Token We
Token ID775
Feature activation+8.96e-04

Pos logit contributions
pole+0.017
 warrior+0.017
ickets+0.016
 Charlie+0.016
ados+0.016
Neg logit contributions
 fault-0.023
 shampoo-0.023
 ruined-0.023
 common-0.023
 arose-0.022
Token can
Token ID460
Feature activation+6.39e-03

Pos logit contributions
aj+0.001
 shampoo+0.001
 fault+0.001
 vinegar+0.001
 L+0.001
Neg logit contributions
pole-0.002
 warrior-0.002
emaker-0.002
stone-0.001
 King-0.001
Token also
Token ID635
Feature activation-2.83e-02

Pos logit contributions
 shampoo+0.008
 fault+0.008
 vinegar+0.008
 common+0.008
 L+0.008
Neg logit contributions
pole-0.011
emaker-0.010
 warrior-0.010
ados-0.010
ickets-0.010
Token time
Token ID640
Feature activation+7.93e-02

Pos logit contributions
 L+0.049
 Sara+0.047
ours+0.047
 Qu+0.047
rou+0.046
Neg logit contributions
 warrior-0.035
lf-0.035
 kingdom-0.034
est-0.034
ados-0.034
Token and
Token ID290
Feature activation+3.65e-03

Pos logit contributions
 Qu+0.137
 shampoo+0.136
 vinegar+0.134
 L+0.134
ses+0.133
Neg logit contributions
pole-0.082
stone-0.079
 around-0.079
emaker-0.078
on-0.077
Token their
Token ID511
Feature activation+3.79e-02

Pos logit contributions
aj+0.006
 common+0.006
 fault+0.005
 Qu+0.005
ours+0.005
Neg logit contributions
 forth-0.005
emaker-0.005
 down-0.005
 around-0.005
lf-0.004
Token new
Token ID649
Feature activation+8.99e-02

Pos logit contributions
ours+0.066
ucker+0.064
 stro+0.064
Does+0.062
 L+0.062
Neg logit contributions
 image-0.038
 King-0.038
 missile-0.038
lf-0.037
 warrior-0.037
Token toy
Token ID13373
Feature activation+7.97e-02

Pos logit contributions
 vinegar+0.161
ours+0.154
 L+0.153
 wasteful+0.151
 bleach+0.150
Neg logit contributions
 warrior-0.093
est-0.088
pole-0.087
 King-0.085
 angel-0.084
Token car
Token ID1097
Feature activation+9.70e-02

Pos logit contributions
 shampoo+0.120
 common+0.120
 vinegar+0.118
 fault+0.116
 L+0.113
Neg logit contributions
pole-0.110
emaker-0.106
 warrior-0.105
stone-0.103
ados-0.102
Token.
Token ID13
Feature activation+4.04e-03

Pos logit contributions
 shampoo+0.155
 common+0.154
 vinegar+0.154
ours+0.149
 Qu+0.147
Neg logit contributions
pole-0.126
emaker-0.120
stone-0.118
 around-0.113
 down-0.111
Token They
Token ID1119
Feature activation-2.47e-03

Pos logit contributions
 shampoo+0.007
rou+0.007
 scar+0.007
aj+0.006
 fault+0.006
Neg logit contributions
 Charlie-0.005
person-0.004
ados-0.004
pole-0.004
 Hope-0.004
Token wished
Token ID16555
Feature activation+6.67e-03

Pos logit contributions
pole+0.004
 warrior+0.003
emaker+0.003
 King+0.003
jack+0.003
Neg logit contributions
 fault-0.004
 common-0.004
aj-0.003
 shampoo-0.003
 vinegar-0.003
Token they
Token ID484
Feature activation-2.33e-02

Pos logit contributions
aj+0.009
 shampoo+0.009
 common+0.009
 fault+0.008
ours+0.008
Neg logit contributions
 Charlie-0.010
 Peter-0.009
ados-0.009
fully-0.009
 King-0.009
Token had
Token ID550
Feature activation+2.10e-02

Pos logit contributions
pole+0.035
emaker+0.035
 warrior+0.033
stone+0.033
person+0.032
Neg logit contributions
 fault-0.033
 shampoo-0.032
 vinegar-0.032
 common-0.031
ours-0.030
Token.
Token ID13
Feature activation+1.45e-02

Pos logit contributions
 common+0.033
 vinegar+0.032
 fault+0.031
 shampoo+0.030
aj+0.030
Neg logit contributions
pole-0.019
 down-0.019
 around-0.017
ring-0.017
string-0.017
Token She
Token ID1375
Feature activation-1.56e-02

Pos logit contributions
 common+0.034
 vinegar+0.034
 cheaper+0.033
 shampoo+0.033
 fault+0.033
Neg logit contributions
ados-0.007
ickets-0.006
 Charlie-0.006
amber-0.005
emaker-0.005
Token cried
Token ID16896
Feature activation+1.36e-02

Pos logit contributions
on+0.014
emaker+0.013
 around+0.013
 owl+0.013
lf+0.013
Neg logit contributions
 fault-0.033
 common-0.032
 theirs-0.029
ours-0.028
 cheaper-0.028
Token louder
Token ID27089
Feature activation+9.97e-02

Pos logit contributions
 shampoo+0.019
 L+0.019
 fault+0.019
 bruises+0.018
 vinegar+0.018
Neg logit contributions
pole-0.022
 warrior-0.021
emaker-0.021
ickets-0.020
stone-0.020
Token and
Token ID290
Feature activation+1.97e-02

Pos logit contributions
 shampoo+0.171
 fault+0.169
 vinegar+0.164
 common+0.164
 bruises+0.157
Neg logit contributions
pole-0.121
emaker-0.117
 warrior-0.115
ickets-0.111
ados-0.110
Token louder
Token ID27089
Feature activation+8.92e-02

Pos logit contributions
 fault+0.036
 common+0.033
 habitats+0.030
omo+0.029
 former+0.029
Neg logit contributions
 down-0.029
 forth-0.026
 owl-0.025
stone-0.023
 around-0.023
Token.
Token ID13
Feature activation+1.97e-02

Pos logit contributions
 shampoo+0.132
 fault+0.130
 common+0.126
 vinegar+0.125
 bruises+0.119
Neg logit contributions
pole-0.128
emaker-0.124
 warrior-0.123
ados-0.119
ickets-0.119
Token Ben
Token ID3932
Feature activation+1.44e-02

Pos logit contributions
 vinegar+0.040
 common+0.040
 cheaper+0.039
 fault+0.039
 shampoo+0.039
Neg logit contributions
ados-0.015
 Charlie-0.014
ickets-0.014
amber-0.013
 Mickey-0.013
Token felt
Token ID2936
Feature activation+2.37e-03

Pos logit contributions
 fault+0.019
 common+0.019
 shampoo+0.018
 vinegar+0.018
 L+0.017
Neg logit contributions
pole-0.023
emaker-0.023
 warrior-0.023
ickets-0.022
stone-0.021
Token sorry
Token ID7926
Feature activation+2.85e-02

Pos logit contributions
aj+0.004
 fault+0.004
 common+0.004
omo+0.004
ours+0.004
Neg logit contributions
 around-0.003
 down-0.003
emaker-0.003
taker-0.003
 alone-0.003
Token and
Token ID290
Feature activation-3.46e-03

Pos logit contributions
 shampoo+0.046
 fault+0.045
 common+0.044
 vinegar+0.044
 bruises+0.043
Neg logit contributions
pole-0.038
emaker-0.036
 warrior-0.036
ickets-0.035
ados-0.034
Token,
Token ID11
Feature activation-8.17e-03

Pos logit contributions
 shampoo+0.074
 fault+0.073
 L+0.071
 common+0.071
 vinegar+0.071
Neg logit contributions
pole-0.056
emaker-0.054
 warrior-0.054
ickets-0.052
ados-0.051
Token there
Token ID612
Feature activation-1.99e-02

Pos logit contributions
pole+0.011
emaker+0.010
 warrior+0.010
stone+0.009
ickets+0.009
Neg logit contributions
 fault-0.013
 shampoo-0.013
 vinegar-0.013
 bruises-0.013
 common-0.012
Token lived
Token ID5615
Feature activation+2.97e-02

Pos logit contributions
on+0.028
pole+0.028
emaker+0.028
est+0.027
he+0.027
Neg logit contributions
aj-0.030
 fault-0.029
 bruises-0.029
 vinegar-0.029
 cheaper-0.028
Token two
Token ID734
Feature activation+2.27e-02

Pos logit contributions
 fault+0.026
 shampoo+0.026
 vinegar+0.025
 common+0.024
 L+0.023
Neg logit contributions
pole-0.061
 warrior-0.059
emaker-0.059
ickets-0.058
ados-0.057
Token friends
Token ID2460
Feature activation-2.73e-02

Pos logit contributions
 shampoo+0.033
 fault+0.032
 vinegar+0.032
 L+0.031
 bruises+0.031
Neg logit contributions
pole-0.034
emaker-0.033
 warrior-0.032
ickets-0.031
stone-0.031
Token named
Token ID3706
Feature activation+9.85e-02

Pos logit contributions
pole+0.048
 warrior+0.047
emaker+0.047
ickets+0.045
ados+0.045
Neg logit contributions
 shampoo-0.033
 fault-0.032
 vinegar-0.031
 L-0.031
 common-0.030
Token Jack
Token ID3619
Feature activation-1.44e-02

Pos logit contributions
 shampoo+0.107
 fault+0.104
 vinegar+0.100
 common+0.099
 L+0.098
Neg logit contributions
pole-0.183
emaker-0.178
 warrior-0.177
ickets-0.173
ados-0.171
Token and
Token ID290
Feature activation+2.72e-02

Pos logit contributions
pole+0.021
emaker+0.020
 warrior+0.020
ickets+0.019
ados+0.019
Neg logit contributions
 shampoo-0.022
 fault-0.021
 vinegar-0.021
 common-0.021
 L-0.021
Token Sally
Token ID25737
Feature activation-2.50e-03

Pos logit contributions
 shampoo+0.036
 fault+0.035
 L+0.035
 common+0.034
 vinegar+0.034
Neg logit contributions
pole-0.044
emaker-0.043
 warrior-0.042
ickets-0.042
ados-0.041
Token.
Token ID13
Feature activation+2.56e-02

Pos logit contributions
pole+0.004
 warrior+0.004
emaker+0.004
ickets+0.004
ados+0.004
Neg logit contributions
 shampoo-0.003
 fault-0.003
 L-0.003
 vinegar-0.003
 common-0.003
Token They
Token ID1119
Feature activation-6.54e-04

Pos logit contributions
 fault+0.023
 shampoo+0.023
 L+0.023
 vinegar+0.022
 common+0.022
Neg logit contributions
pole-0.052
emaker-0.051
 warrior-0.050
stone-0.049
ickets-0.048
Token understand
Token ID1833
Feature activation+6.33e-03

Pos logit contributions
 shampoo+0.012
 fault+0.012
 vinegar+0.012
 common+0.012
 L+0.012
Neg logit contributions
pole-0.012
 warrior-0.012
emaker-0.012
ickets-0.012
ados-0.011
Token the
Token ID262
Feature activation+3.88e-02

Pos logit contributions
ses+0.010
 bruises+0.010
aj+0.010
 fault+0.010
 vinegar+0.010
Neg logit contributions
pole-0.008
ados-0.008
 King-0.007
emaker-0.007
 warrior-0.007
Token world
Token ID995
Feature activation+1.56e-02

Pos logit contributions
 shampoo+0.057
 vinegar+0.055
 fault+0.055
 L+0.055
 common+0.054
Neg logit contributions
pole-0.055
 warrior-0.054
emaker-0.051
ados-0.051
ickets-0.051
Token around
Token ID1088
Feature activation+9.20e-04

Pos logit contributions
 shampoo+0.021
 fault+0.020
 vinegar+0.020
 bruises+0.020
 L+0.019
Neg logit contributions
pole-0.025
 warrior-0.024
emaker-0.023
ickets-0.023
stone-0.023
Token us
Token ID514
Feature activation+6.61e-02

Pos logit contributions
 fault+0.001
 shampoo+0.001
 vinegar+0.001
 bruises+0.001
aj+0.001
Neg logit contributions
pole-0.001
 warrior-0.001
emaker-0.001
ados-0.001
ickets-0.001
Token better
Token ID1365
Feature activation+9.12e-02

Pos logit contributions
 shampoo+0.103
 vinegar+0.100
 fault+0.100
 bruises+0.098
 common+0.097
Neg logit contributions
pole-0.091
 warrior-0.086
ickets-0.084
emaker-0.084
ados-0.081
Token.
Token ID13
Feature activation+9.52e-04

Pos logit contributions
 vinegar+0.156
 shampoo+0.156
 bruises+0.154
 fault+0.151
ours+0.146
Neg logit contributions
 warrior-0.105
pole-0.103
ados-0.100
emaker-0.097
 trolls-0.095
Token Lily
Token ID20037
Feature activation+1.82e-02

Pos logit contributions
 common+0.002
 fault+0.002
 shampoo+0.002
 vinegar+0.002
 bruises+0.002
Neg logit contributions
pole-0.001
umbo-0.001
ados-0.001
 Charlie-0.001
ickets-0.001
Token was
Token ID373
Feature activation+3.33e-02

Pos logit contributions
 shampoo+0.020
 fault+0.020
 vinegar+0.019
 common+0.019
 L+0.018
Neg logit contributions
pole-0.034
 warrior-0.033
emaker-0.032
ickets-0.031
stone-0.031
Token happy
Token ID3772
Feature activation-3.25e-03

Pos logit contributions
 vinegar+0.062
 shampoo+0.060
 common+0.060
 fault+0.059
 bruises+0.057
Neg logit contributions
pole-0.038
 warrior-0.034
 King-0.033
emaker-0.032
 Charlie-0.031
Token to
Token ID284
Feature activation+5.61e-02

Pos logit contributions
pole+0.005
emaker+0.005
 warrior+0.005
ickets+0.005
ados+0.005
Neg logit contributions
 shampoo-0.004
 fault-0.004
 vinegar-0.004
 L-0.004
 common-0.004
Token or
Token ID393
Feature activation+7.93e-03

Pos logit contributions
 bruises+0.013
 shampoo+0.013
 fault+0.013
aj+0.013
 vinegar+0.013
Neg logit contributions
pole-0.013
 warrior-0.012
emaker-0.012
stone-0.012
ickets-0.012
Token frogs
Token ID37475
Feature activation-2.22e-02

Pos logit contributions
 fault+0.012
aj+0.012
omo+0.012
ucker+0.011
rou+0.011
Neg logit contributions
 warrior-0.011
 trolls-0.011
 King-0.011
 mushroom-0.010
 Charlie-0.010
Token or
Token ID393
Feature activation+2.15e-02

Pos logit contributions
pole+0.030
emaker+0.027
 warrior+0.027
ickets+0.027
stone+0.026
Neg logit contributions
 fault-0.035
 shampoo-0.035
 vinegar-0.034
 bruises-0.034
 common-0.033
Token snakes
Token ID26042
Feature activation+2.01e-02

Pos logit contributions
aj+0.035
 fault+0.035
outed+0.035
omo+0.035
ucker+0.034
Neg logit contributions
 warrior-0.028
 mushroom-0.027
 trolls-0.027
 King-0.026
 eagle-0.025
Token.
Token ID13
Feature activation-5.61e-03

Pos logit contributions
 shampoo+0.033
 fault+0.032
 vinegar+0.032
 common+0.032
 bruises+0.032
Neg logit contributions
pole-0.026
emaker-0.023
 warrior-0.023
ickets-0.023
stone-0.022
Token Some
Token ID2773
Feature activation+1.02e-01

Pos logit contributions
pole+0.009
 warrior+0.008
ickets+0.008
ados+0.008
 trolls+0.008
Neg logit contributions
 shampoo-0.008
 fault-0.008
 common-0.008
 bruises-0.007
 ruined-0.007
Token of
Token ID286
Feature activation+1.72e-02

Pos logit contributions
 fault+0.171
aj+0.159
rou+0.152
 shampoo+0.151
 L+0.146
Neg logit contributions
ickets-0.134
pole-0.130
 warrior-0.129
 trolls-0.127
 eagle-0.127
Token them
Token ID606
Feature activation+1.07e-02

Pos logit contributions
aj+0.028
 fault+0.028
 bruises+0.024
outed+0.024
rou+0.024
Neg logit contributions
pole-0.025
ados-0.023
 warrior-0.022
 mushroom-0.022
 Charlie-0.022
Token might
Token ID1244
Feature activation+7.24e-04

Pos logit contributions
 fault+0.013
 shampoo+0.013
 vinegar+0.013
 bruises+0.013
 L+0.013
Neg logit contributions
pole-0.017
 warrior-0.016
ickets-0.016
stone-0.016
emaker-0.015
Token be
Token ID307
Feature activation+1.10e-02

Pos logit contributions
aj+0.001
ours+0.001
 shampoo+0.001
 bruises+0.001
 fault+0.001
Neg logit contributions
pole-0.001
 warrior-0.001
ickets-0.001
 eagle-0.001
 mushroom-0.001
Token friendly
Token ID8030
Feature activation-6.01e-04

Pos logit contributions
 shampoo+0.015
 fault+0.015
ours+0.015
 bruises+0.015
 arose+0.015
Neg logit contributions
pole-0.016
 around-0.014
 warrior-0.014
 down-0.014
 trolls-0.014
Token's
Token ID338
Feature activation+1.07e-02

Pos logit contributions
pole+0.057
 warrior+0.056
emaker+0.055
stone+0.054
ickets+0.053
Neg logit contributions
 shampoo-0.043
 fault-0.042
 vinegar-0.042
 common-0.040
 bruises-0.039
Token ordinary
Token ID8850
Feature activation+4.26e-02

Pos logit contributions
 vinegar+0.021
ours+0.020
 shampoo+0.020
 common+0.019
 L+0.019
Neg logit contributions
 warrior-0.011
 owl-0.011
 King-0.011
 eagle-0.011
 angel-0.010
Token day
Token ID1110
Feature activation+5.62e-02

Pos logit contributions
 shampoo+0.073
 fault+0.072
 vinegar+0.071
 L+0.070
 common+0.070
Neg logit contributions
pole-0.051
 warrior-0.050
emaker-0.049
ickets-0.046
stone-0.046
Token turned
Token ID2900
Feature activation+3.98e-02

Pos logit contributions
 fault+0.088
 shampoo+0.087
 vinegar+0.085
 common+0.083
 bruises+0.081
Neg logit contributions
pole-0.077
emaker-0.074
 warrior-0.074
ickets-0.071
stone-0.071
Token into
Token ID656
Feature activation+5.92e-03

Pos logit contributions
 fault+0.074
 shampoo+0.074
 vinegar+0.073
 common+0.072
 bruises+0.072
Neg logit contributions
pole-0.040
 warrior-0.038
emaker-0.038
ados-0.037
ickets-0.036
Token a
Token ID257
Feature activation+2.25e-02

Pos logit contributions
ours+0.010
outed+0.010
 fault+0.009
aj+0.009
ucker+0.009
Neg logit contributions
 Charlie-0.007
 King-0.007
 mushroom-0.007
 warrior-0.007
ados-0.007
Token wonderful
Token ID7932
Feature activation-2.22e-02

Pos logit contributions
 fault+0.038
 shampoo+0.036
ours+0.036
 vinegar+0.036
 bruises+0.036
Neg logit contributions
 warrior-0.030
pole-0.029
 eagle-0.027
 King-0.026
stone-0.026
Token adventure
Token ID8855
Feature activation-6.48e-03

Pos logit contributions
pole+0.028
 warrior+0.027
emaker+0.026
stone+0.025
ickets+0.025
Neg logit contributions
 shampoo-0.037
 fault-0.037
 vinegar-0.036
 bruises-0.036
 L-0.035
Token!
Token ID0
Feature activation-2.75e-03

Pos logit contributions
pole+0.009
emaker+0.009
 warrior+0.009
ickets+0.008
ados+0.008
Neg logit contributions
 shampoo-0.010
 fault-0.010
 vinegar-0.010
 common-0.010
 bruises-0.009
Token<|endoftext|>
Token ID50256
Feature activation+7.08e-03

Pos logit contributions
pole+0.005
emaker+0.005
 warrior+0.005
ickets+0.005
ados+0.005
Neg logit contributions
 shampoo-0.003
 fault-0.003
 vinegar-0.003
 common-0.003
 L-0.003
TokenOne
Token ID3198
Feature activation+6.91e-02

Pos logit contributions
 fault+0.009
 shampoo+0.009
 vinegar+0.008
 bruises+0.008
 common+0.008
Neg logit contributions
pole-0.012
emaker-0.011
ickets-0.011
 warrior-0.011
umbo-0.011
Token.
Token ID13
Feature activation-6.09e-03

Pos logit contributions
pole+0.069
 warrior+0.068
emaker+0.064
ados+0.064
 down+0.063
Neg logit contributions
 shampoo-0.098
 vinegar-0.097
 fault-0.095
 bruises-0.093
aj-0.091
Token He
Token ID679
Feature activation-5.30e-03

Pos logit contributions
pole+0.007
 warrior+0.007
ickets+0.007
umbo+0.007
emaker+0.007
Neg logit contributions
 shampoo-0.011
 vinegar-0.010
 fault-0.010
 common-0.010
 bruises-0.010
Token realized
Token ID6939
Feature activation+2.02e-02

Pos logit contributions
pole+0.008
 warrior+0.008
 King+0.007
 eagle+0.007
stone+0.007
Neg logit contributions
 fault-0.009
 vinegar-0.008
 shampoo-0.008
 common-0.008
 bruises-0.008
Token the
Token ID262
Feature activation-1.43e-02

Pos logit contributions
 vinegar+0.037
 fault+0.037
ses+0.037
 common+0.036
 shampoo+0.036
Neg logit contributions
 warrior-0.021
 eagle-0.020
pole-0.020
 Charlie-0.020
 King-0.020
Token voice
Token ID3809
Feature activation+2.25e-02

Pos logit contributions
 warrior+0.017
 eagle+0.016
 King+0.016
 owl+0.015
pole+0.015
Neg logit contributions
ours-0.025
aj-0.025
 L-0.024
 fault-0.024
 shampoo-0.024
Token was
Token ID373
Feature activation+1.95e-02

Pos logit contributions
 fault+0.029
 vinegar+0.029
 shampoo+0.029
 common+0.027
aj+0.027
Neg logit contributions
pole-0.038
 warrior-0.036
emaker-0.035
stone-0.035
ickets-0.034
Token right
Token ID826
Feature activation-3.11e-02

Pos logit contributions
ours+0.033
aj+0.032
 fault+0.032
 vinegar+0.032
 bruises+0.031
Neg logit contributions
pole-0.026
 Charlie-0.024
 King-0.024
 warrior-0.023
 around-0.023
Token,
Token ID11
Feature activation-2.45e-02

Pos logit contributions
pole+0.029
 warrior+0.029
 down+0.029
stone+0.027
 around+0.026
Neg logit contributions
 vinegar-0.063
 shampoo-0.062
 bruises-0.061
 fault-0.059
ours-0.058
Token the
Token ID262
Feature activation-1.96e-02

Pos logit contributions
pole+0.028
 warrior+0.026
 eagle+0.025
 Charlie+0.024
 King+0.024
Neg logit contributions
 fault-0.044
 common-0.043
 vinegar-0.043
 shampoo-0.042
ours-0.041
Token stair
Token ID18761
Feature activation-4.32e-02

Pos logit contributions
 warrior+0.021
 King+0.020
 eagle+0.019
 owl+0.019
 angel+0.019
Neg logit contributions
 fault-0.038
ours-0.038
aj-0.036
ucker-0.036
 vinegar-0.036
Token wasn
Token ID2492
Feature activation-2.87e-04

Pos logit contributions
pole+0.077
emaker+0.069
 warrior+0.069
stone+0.068
jack+0.067
Neg logit contributions
 shampoo-0.054
 fault-0.053
 common-0.052
 vinegar-0.052
aj-0.049
Token so
Token ID523
Feature activation-8.46e-03

Pos logit contributions
pole+0.041
 warrior+0.039
emaker+0.037
stone+0.036
 King+0.035
Neg logit contributions
 vinegar-0.055
 fault-0.055
 shampoo-0.055
 bruises-0.052
 common-0.051
Token grateful
Token ID14066
Feature activation-3.80e-02

Pos logit contributions
pole+0.011
 warrior+0.011
emaker+0.010
ickets+0.010
stone+0.010
Neg logit contributions
 shampoo-0.014
 fault-0.014
 vinegar-0.014
 common-0.013
 bruises-0.013
Token to
Token ID284
Feature activation+4.75e-02

Pos logit contributions
pole+0.049
 warrior+0.045
stone+0.045
emaker+0.044
ados+0.043
Neg logit contributions
 shampoo-0.062
 vinegar-0.062
 bruises-0.060
 fault-0.060
 common-0.059
Token the
Token ID262
Feature activation-9.10e-03

Pos logit contributions
 shampoo+0.067
 fault+0.066
 L+0.064
 common+0.064
 vinegar+0.063
Neg logit contributions
pole-0.073
emaker-0.070
 warrior-0.070
ickets-0.068
ados-0.067
Token fairy
Token ID25607
Feature activation+3.50e-02

Pos logit contributions
 warrior+0.011
 eagle+0.011
 King+0.010
pole+0.010
 owl+0.010
Neg logit contributions
ours-0.015
 vinegar-0.015
 fault-0.015
 shampoo-0.015
 L-0.015
Token who
Token ID508
Feature activation+5.03e-02

Pos logit contributions
 shampoo+0.053
 fault+0.052
 vinegar+0.051
 common+0.050
 L+0.049
Neg logit contributions
pole-0.050
 warrior-0.048
emaker-0.048
ickets-0.046
ados-0.045
Token had
Token ID550
Feature activation+3.58e-02

Pos logit contributions
 fault+0.065
 shampoo+0.064
 vinegar+0.063
 bruises+0.059
 common+0.059
Neg logit contributions
pole-0.084
 warrior-0.082
emaker-0.082
stone-0.079
 King-0.077
Token helped
Token ID4193
Feature activation-4.30e-03

Pos logit contributions
 vinegar+0.049
 shampoo+0.049
 fault+0.049
ours+0.046
 L+0.045
Neg logit contributions
pole-0.056
 warrior-0.053
emaker-0.052
stone-0.051
ickets-0.050
Token her
Token ID607
Feature activation-2.40e-02

Pos logit contributions
pole+0.006
emaker+0.006
 warrior+0.006
ickets+0.006
ados+0.006
Neg logit contributions
 shampoo-0.007
 fault-0.006
 vinegar-0.006
 common-0.006
 L-0.006
Token find
Token ID1064
Feature activation-2.41e-02

Pos logit contributions
 warrior+0.028
pole+0.027
 King+0.026
stone+0.026
 kingdom+0.025
Neg logit contributions
 vinegar-0.043
 shampoo-0.041
ours-0.040
 bruises-0.040
 fault-0.040
Token her
Token ID607
Feature activation-1.85e-02

Pos logit contributions
pole+0.036
 warrior+0.034
emaker+0.034
ados+0.033
stone+0.033
Neg logit contributions
 shampoo-0.035
 fault-0.034
 vinegar-0.034
 common-0.033
 bruises-0.032
Token skipped
Token ID26684
Feature activation+5.35e-03

Pos logit contributions
pole+0.004
emaker+0.004
 warrior+0.004
ickets+0.004
stone+0.004
Neg logit contributions
 shampoo-0.003
 fault-0.003
 vinegar-0.003
 common-0.003
 bruises-0.003
Token and
Token ID290
Feature activation+1.97e-02

Pos logit contributions
 L+0.008
 shampoo+0.008
 common+0.008
 Qu+0.007
 their+0.007
Neg logit contributions
emaker-0.009
 warrior-0.008
pole-0.008
ados-0.008
ickets-0.008
Token skipped
Token ID26684
Feature activation+4.15e-03

Pos logit contributions
 fault+0.027
 shampoo+0.026
 vinegar+0.026
 common+0.025
 bruises+0.025
Neg logit contributions
pole-0.031
emaker-0.030
 warrior-0.030
ickets-0.029
stone-0.029
Token until
Token ID1566
Feature activation+2.90e-02

Pos logit contributions
 L+0.007
 shampoo+0.006
 common+0.006
 Qu+0.006
 their+0.006
Neg logit contributions
emaker-0.006
pole-0.006
 warrior-0.006
ados-0.006
ickets-0.006
Token they
Token ID484
Feature activation+1.37e-02

Pos logit contributions
 fault+0.034
 shampoo+0.032
 bruises+0.031
 vinegar+0.031
aj+0.030
Neg logit contributions
pole-0.051
emaker-0.050
 warrior-0.049
ados-0.048
ickets-0.048
Token saw
Token ID2497
Feature activation+3.03e-02

Pos logit contributions
 shampoo+0.018
 fault+0.017
 vinegar+0.017
 common+0.016
 L+0.016
Neg logit contributions
pole-0.023
emaker-0.022
 warrior-0.022
ickets-0.021
ados-0.021
Token the
Token ID262
Feature activation-1.75e-02

Pos logit contributions
aj+0.055
 common+0.049
 bruises+0.048
ucker+0.048
omo+0.048
Neg logit contributions
 Charlie-0.038
 King-0.036
 down-0.035
pole-0.035
 around-0.035
Token boat
Token ID8848
Feature activation+8.34e-03

Pos logit contributions
pole+0.021
 warrior+0.020
 eagle+0.019
ickets+0.018
 King+0.018
Neg logit contributions
 bruises-0.030
 L-0.030
 shampoo-0.030
 fault-0.030
 vinegar-0.029
Token again
Token ID757
Feature activation+4.81e-02

Pos logit contributions
 fault+0.014
 shampoo+0.014
 vinegar+0.013
 bruises+0.013
 common+0.013
Neg logit contributions
pole-0.012
stone-0.010
emaker-0.010
 warrior-0.010
ickets-0.010
Token.
Token ID13
Feature activation+3.21e-03

Pos logit contributions
 fault+0.087
 shampoo+0.084
 vinegar+0.083
 bruises+0.083
ses+0.077
Neg logit contributions
pole-0.057
 warrior-0.051
stone-0.050
 down-0.050
ickets-0.048
Token "
Token ID366
Feature activation-1.24e-02

Pos logit contributions
 shampoo+0.004
 fault+0.004
 vinegar+0.004
 L+0.004
 common+0.004
Neg logit contributions
pole-0.006
emaker-0.005
 warrior-0.005
ickets-0.005
ados-0.005
Token that
Token ID326
Feature activation+1.98e-02

Pos logit contributions
pole+0.056
emaker+0.054
 warrior+0.053
ickets+0.052
ados+0.051
Neg logit contributions
 shampoo-0.049
 fault-0.048
 L-0.047
 vinegar-0.046
 common-0.046
Token she
Token ID673
Feature activation-2.01e-03

Pos logit contributions
 shampoo+0.031
 fault+0.030
 L+0.030
 common+0.029
 vinegar+0.029
Neg logit contributions
pole-0.028
 warrior-0.027
emaker-0.026
ickets-0.026
ados-0.025
Token was
Token ID373
Feature activation+3.78e-02

Pos logit contributions
pole+0.004
emaker+0.004
 warrior+0.004
ados+0.004
ickets+0.004
Neg logit contributions
 shampoo-0.002
 L-0.002
 fault-0.002
 vinegar-0.002
 common-0.002
Token able
Token ID1498
Feature activation-5.08e-02

Pos logit contributions
 shampoo+0.064
 fault+0.062
 L+0.061
 bruises+0.059
 ruined+0.059
Neg logit contributions
pole-0.048
 warrior-0.048
ickets-0.046
emaker-0.046
ados-0.045
Token to
Token ID284
Feature activation-8.19e-04

Pos logit contributions
pole+0.078
emaker+0.075
 warrior+0.075
ickets+0.072
ados+0.072
Neg logit contributions
 shampoo-0.071
 fault-0.069
 vinegar-0.068
 common-0.067
 L-0.066
Token visit
Token ID3187
Feature activation+8.85e-03

Pos logit contributions
pole+0.001
emaker+0.001
 warrior+0.001
ados+0.001
ickets+0.001
Neg logit contributions
 shampoo-0.001
 fault-0.001
 common-0.001
 L-0.001
 vinegar-0.001
Token the
Token ID262
Feature activation-2.09e-02

Pos logit contributions
 shampoo+0.013
 fault+0.013
 vinegar+0.012
 common+0.012
 bruises+0.012
Neg logit contributions
pole-0.013
 warrior-0.013
emaker-0.013
ados-0.012
ickets-0.012
Token library
Token ID5888
Feature activation+5.32e-02

Pos logit contributions
pole+0.037
emaker+0.036
 warrior+0.035
ickets+0.035
ados+0.034
Neg logit contributions
 shampoo-0.025
 fault-0.024
 L-0.024
 common-0.023
 vinegar-0.023
Token and
Token ID290
Feature activation-7.61e-03

Pos logit contributions
 shampoo+0.076
 fault+0.075
 L+0.073
 common+0.072
 vinegar+0.071
Neg logit contributions
pole-0.078
emaker-0.077
 warrior-0.076
ickets-0.074
ados-0.073
Token find
Token ID1064
Feature activation-5.21e-02

Pos logit contributions
pole+0.010
 warrior+0.009
emaker+0.009
 King+0.009
stone+0.009
Neg logit contributions
 fault-0.012
 vinegar-0.012
 shampoo-0.012
 common-0.012
 bruises-0.012
Token the
Token ID262
Feature activation-3.85e-02

Pos logit contributions
pole+0.083
emaker+0.080
 warrior+0.080
ados+0.077
stone+0.077
Neg logit contributions
 fault-0.067
 shampoo-0.067
 vinegar-0.066
 common-0.065
 bruises-0.063
Token immediately
Token ID3393
Feature activation+2.56e-02

Pos logit contributions
pole+0.063
 warrior+0.060
emaker+0.060
ickets+0.058
stone+0.058
Neg logit contributions
 shampoo-0.054
 fault-0.053
 vinegar-0.051
 common-0.051
 bruises-0.050
Token hung
Token ID9174
Feature activation-5.29e-03

Pos logit contributions
 fault+0.038
 shampoo+0.036
 vinegar+0.036
 common+0.035
 bruises+0.034
Neg logit contributions
pole-0.038
 warrior-0.037
stone-0.036
emaker-0.035
person-0.034
Token the
Token ID262
Feature activation-4.09e-02

Pos logit contributions
pole+0.008
emaker+0.008
 warrior+0.008
ickets+0.008
ados+0.007
Neg logit contributions
 shampoo-0.008
 fault-0.007
 L-0.007
 vinegar-0.007
 common-0.007
Token h
Token ID289
Feature activation-1.84e-02

Pos logit contributions
pole+0.052
 warrior+0.051
stone+0.051
emaker+0.049
 eagle+0.047
Neg logit contributions
 fault-0.065
 common-0.063
 vinegar-0.063
 shampoo-0.062
 Qu-0.060
Tokenanger
Token ID2564
Feature activation-5.14e-03

Pos logit contributions
pole+0.027
 warrior+0.026
emaker+0.025
ados+0.024
ickets+0.024
Neg logit contributions
 shampoo-0.028
 fault-0.027
 L-0.027
 vinegar-0.026
 bruises-0.026
Token on
Token ID319
Feature activation-1.01e-02

Pos logit contributions
 warrior+0.007
emaker+0.007
ickets+0.007
umbo+0.006
ados+0.006
Neg logit contributions
 shampoo-0.008
 fault-0.008
 L-0.008
 ruined-0.007
 bruises-0.007
Token the
Token ID262
Feature activation-1.78e-03

Pos logit contributions
pole+0.014
 warrior+0.014
emaker+0.014
ados+0.013
 King+0.013
Neg logit contributions
 fault-0.015
 shampoo-0.015
 vinegar-0.014
aj-0.014
 bruises-0.014
Token wall
Token ID3355
Feature activation+1.96e-03

Pos logit contributions
pole+0.002
emaker+0.002
 warrior+0.002
ickets+0.002
ados+0.002
Neg logit contributions
 shampoo-0.003
 fault-0.003
 vinegar-0.003
 common-0.003
 L-0.003
Token.
Token ID13
Feature activation-3.26e-03

Pos logit contributions
 shampoo+0.003
 fault+0.003
 vinegar+0.003
 common+0.003
 L+0.003
Neg logit contributions
pole-0.003
emaker-0.003
 warrior-0.003
ickets-0.003
ados-0.003
Token He
Token ID679
Feature activation-6.06e-03

Pos logit contributions
pole+0.004
emaker+0.004
 warrior+0.004
ickets+0.004
stone+0.004
Neg logit contributions
 shampoo-0.005
 fault-0.005
 L-0.005
 vinegar-0.005
 common-0.005
Token asked
Token ID1965
Feature activation-2.62e-02

Pos logit contributions
pole+0.010
 warrior+0.009
stone+0.009
emaker+0.009
 King+0.009
Neg logit contributions
 fault-0.009
 vinegar-0.008
 common-0.008
 shampoo-0.008
 bruises-0.008
Token can
Token ID460
Feature activation+4.09e-02

Pos logit contributions
 fault+0.029
 shampoo+0.029
 vinegar+0.029
 bruises+0.029
 common+0.027
Neg logit contributions
pole-0.041
 warrior-0.040
emaker-0.039
ickets-0.038
umbo-0.037
Token take
Token ID1011
Feature activation-2.77e-02

Pos logit contributions
 shampoo+0.057
 fault+0.055
 common+0.053
 L+0.053
 vinegar+0.052
Neg logit contributions
pole-0.064
emaker-0.062
 warrior-0.062
ados-0.060
ickets-0.059
Token care
Token ID1337
Feature activation-3.54e-02

Pos logit contributions
ados+0.038
 warrior+0.038
pole+0.036
emaker+0.036
 King+0.035
Neg logit contributions
 fault-0.041
 vinegar-0.039
ses-0.038
aj-0.038
 bruises-0.037
Token of
Token ID286
Feature activation+1.22e-02

Pos logit contributions
pole+0.035
emaker+0.033
 warrior+0.033
ickets+0.032
stone+0.031
Neg logit contributions
 shampoo-0.068
 fault-0.068
 vinegar-0.066
 common-0.066
 bruises-0.064
Token him
Token ID683
Feature activation+2.11e-02

Pos logit contributions
 fault+0.021
outed+0.021
 vinegar+0.021
aj+0.021
ses+0.020
Neg logit contributions
pole-0.013
 warrior-0.013
 Charlie-0.013
ados-0.013
 King-0.012
Token!
Token ID0
Feature activation-1.18e-02

Pos logit contributions
 shampoo+0.034
 vinegar+0.034
 fault+0.034
 common+0.033
 bruises+0.033
Neg logit contributions
pole-0.028
 warrior-0.026
emaker-0.025
ados-0.025
ickets-0.025
Tokenâ
Token ID22940
Feature activation+6.64e-03

Pos logit contributions
pole+0.015
 warrior+0.015
ickets+0.014
emaker+0.014
umbo+0.014
Neg logit contributions
 fault-0.020
 shampoo-0.019
 vinegar-0.019
 common-0.019
 bruises-0.019
Token
Token ID26391
Feature activation+8.66e-03

Pos logit contributions
 shampoo+0.010
 common+0.010
 fault+0.010
 vinegar+0.010
 L+0.010
Neg logit contributions
pole-0.009
 warrior-0.009
emaker-0.009
ados-0.009
ickets-0.008
Token
Token ID198
Feature activation+9.43e-03

Pos logit contributions
 shampoo+0.013
 fault+0.012
 vinegar+0.012
 common+0.012
 L+0.012
Neg logit contributions
pole-0.013
emaker-0.012
 warrior-0.012
ickets-0.012
ados-0.012
Token
Token ID198
Feature activation+3.52e-03

Pos logit contributions
 fault+0.018
ses+0.017
 vinegar+0.017
 ruined+0.016
 shampoo+0.016
Neg logit contributions
ickets-0.011
pole-0.010
on-0.010
oon-0.010
he-0.010
TokenThe
Token ID464
Feature activation+3.69e-02

Pos logit contributions
 fault+0.007
ses+0.006
 vinegar+0.006
 shampoo+0.006
 common+0.006
Neg logit contributions
pole-0.004
ickets-0.004
 warrior-0.004
emaker-0.004
quet-0.004
Token a
Token ID257
Feature activation+2.15e-02

Pos logit contributions
 vinegar+0.000
 shampoo+0.000
 fault+0.000
aj+0.000
ours+0.000
Neg logit contributions
 warrior-0.000
pole-0.000
ados-0.000
emaker-0.000
stone-0.000
Token long
Token ID890
Feature activation-1.85e-02

Pos logit contributions
 shampoo+0.031
 common+0.030
 cheaper+0.029
 gas+0.029
 L+0.028
Neg logit contributions
emaker-0.033
ickets-0.032
ados-0.032
anes-0.030
pole-0.029
Token journey
Token ID7002
Feature activation-1.93e-02

Pos logit contributions
ickets+0.027
ados+0.026
emaker+0.026
anes+0.025
umbo+0.025
Neg logit contributions
 common-0.028
 shampoo-0.028
 L-0.026
 gas-0.025
 scratches-0.025
Token to
Token ID284
Feature activation+1.91e-02

Pos logit contributions
emaker+0.031
 warrior+0.030
ickets+0.030
pole+0.030
ados+0.029
Neg logit contributions
 shampoo-0.025
 fault-0.025
 L-0.025
 common-0.024
 bruises-0.023
Token find
Token ID1064
Feature activation-4.66e-02

Pos logit contributions
 fault+0.038
 shampoo+0.038
 vinegar+0.037
aj+0.036
 bruises+0.036
Neg logit contributions
pole-0.019
 warrior-0.018
emaker-0.017
stone-0.016
 King-0.016
Token the
Token ID262
Feature activation-3.56e-02

Pos logit contributions
pole+0.079
 warrior+0.076
emaker+0.075
ados+0.073
stone+0.073
Neg logit contributions
 shampoo-0.058
 fault-0.058
 vinegar-0.055
 common-0.055
 bruises-0.053
Token magical
Token ID10883
Feature activation+7.11e-03

Pos logit contributions
pole+0.038
emaker+0.037
 warrior+0.036
ickets+0.035
ados+0.034
Neg logit contributions
 shampoo-0.066
 fault-0.065
 vinegar-0.064
 common-0.063
 L-0.063
Token sword
Token ID8429
Feature activation+1.09e-02

Pos logit contributions
 shampoo+0.014
 fault+0.014
 common+0.013
 vinegar+0.013
 L+0.013
Neg logit contributions
pole-0.007
emaker-0.007
ickets-0.006
ados-0.006
 warrior-0.006
Token.
Token ID13
Feature activation+3.44e-03

Pos logit contributions
 shampoo+0.016
 fault+0.015
 vinegar+0.015
 common+0.015
 L+0.015
Neg logit contributions
pole-0.017
 warrior-0.016
emaker-0.016
ickets-0.015
stone-0.015
Token Along
Token ID17159
Feature activation-1.30e-02

Pos logit contributions
 shampoo+0.005
 fault+0.005
 vinegar+0.005
 common+0.005
 L+0.005
Neg logit contributions
pole-0.005
emaker-0.005
 warrior-0.005
ickets-0.004
ados-0.004
Token the
Token ID262
Feature activation+1.61e-02

Pos logit contributions
pole+0.021
emaker+0.020
 warrior+0.020
ickets+0.019
ados+0.019
Neg logit contributions
 shampoo-0.018
 fault-0.017
 vinegar-0.017
 bruises-0.016
 common-0.016
Token,
Token ID11
Feature activation-1.90e-02

Pos logit contributions
pole+0.045
 warrior+0.044
emaker+0.043
ickets+0.042
ados+0.042
Neg logit contributions
 fault-0.042
 shampoo-0.041
 vinegar-0.040
 common-0.039
 bruises-0.039
Token but
Token ID475
Feature activation-4.83e-02

Pos logit contributions
pole+0.025
 warrior+0.023
ickets+0.023
emaker+0.022
stone+0.022
Neg logit contributions
 shampoo-0.031
 fault-0.031
 vinegar-0.030
 common-0.030
 bruises-0.029
Token he
Token ID339
Feature activation-6.34e-03

Pos logit contributions
pole+0.064
 warrior+0.060
emaker+0.060
ados+0.057
stone+0.056
Neg logit contributions
 shampoo-0.079
 fault-0.079
 vinegar-0.077
 common-0.076
 bruises-0.074
Token didn
Token ID1422
Feature activation-9.02e-03

Pos logit contributions
pole+0.010
 warrior+0.010
emaker+0.010
 eagle+0.010
orn+0.010
Neg logit contributions
 fault-0.008
 vinegar-0.008
 common-0.008
 shampoo-0.008
 bruises-0.008
Token't
Token ID470
Feature activation-1.50e-02

Pos logit contributions
pole+0.012
 warrior+0.012
emaker+0.011
ados+0.011
stone+0.011
Neg logit contributions
 shampoo-0.015
 fault-0.014
 L-0.014
 common-0.014
 vinegar-0.014
Token know
Token ID760
Feature activation-3.32e-02

Pos logit contributions
ados+0.036
pole+0.035
ickets+0.034
stone+0.033
quet+0.033
Neg logit contributions
 L-0.012
 common-0.011
 Sara-0.010
 shampoo-0.010
 don-0.009
Token how
Token ID703
Feature activation+1.50e-02

Pos logit contributions
pole+0.052
emaker+0.050
stone+0.048
ados+0.047
 owl+0.047
Neg logit contributions
 common-0.048
ses-0.044
aj-0.044
 shampoo-0.044
 fault-0.043
Token to
Token ID284
Feature activation+2.83e-02

Pos logit contributions
 shampoo+0.024
 vinegar+0.023
 fault+0.023
 common+0.023
 bruises+0.022
Neg logit contributions
pole-0.018
 warrior-0.018
emaker-0.018
stone-0.018
ados-0.017
Token.
Token ID13
Feature activation+1.11e-03

Pos logit contributions
 shampoo+0.032
 common+0.032
 L+0.032
 Sara+0.029
 gas+0.028
Neg logit contributions
ados-0.055
emaker-0.051
pole-0.051
umbo-0.050
 warrior-0.050
Token
Token ID198
Feature activation+9.98e-03

Pos logit contributions
 fault+0.001
 shampoo+0.001
 L+0.001
 common+0.001
 vinegar+0.001
Neg logit contributions
emaker-0.002
pole-0.002
 warrior-0.002
ickets-0.002
stone-0.002
Token
Token ID198
Feature activation+6.41e-03

Pos logit contributions
 shampoo+0.014
 fault+0.014
 vinegar+0.014
 bruises+0.013
 common+0.013
Neg logit contributions
pole-0.015
emaker-0.014
ickets-0.014
 warrior-0.014
umbo-0.014
Token making
Token ID1642
Feature activation-1.99e-02

Pos logit contributions
 common+0.026
 fault+0.026
 vinegar+0.024
 shampoo+0.024
aj+0.024
Neg logit contributions
pole-0.019
 warrior-0.016
 down-0.016
ados-0.016
 Charlie-0.016
Token it
Token ID340
Feature activation-2.30e-02

Pos logit contributions
pole+0.029
ados+0.028
ickets+0.027
stone+0.027
 warrior+0.027
Neg logit contributions
 common-0.028
 fault-0.027
aj-0.026
 vinegar-0.026
 shampoo-0.026
Token rum
Token ID7440
Feature activation+1.51e-02

Pos logit contributions
pole+0.032
 warrior+0.030
emaker+0.029
ickets+0.029
stone+0.029
Neg logit contributions
 shampoo-0.035
 fault-0.035
 vinegar-0.034
 common-0.034
 bruises-0.033
Tokenble
Token ID903
Feature activation-2.36e-02

Pos logit contributions
 shampoo+0.028
 fault+0.027
 vinegar+0.027
 L+0.027
 bruises+0.026
Neg logit contributions
pole-0.016
 warrior-0.016
emaker-0.015
ickets-0.015
ados-0.014
Token and
Token ID290
Feature activation+1.01e-02

Pos logit contributions
emaker+0.035
 warrior+0.035
pole+0.034
umbo+0.033
ickets+0.033
Neg logit contributions
 shampoo-0.035
 fault-0.033
 L-0.032
 vinegar-0.032
 ruined-0.030
Token wh
Token ID348
Feature activation-2.73e-03

Pos logit contributions
 fault+0.017
 common+0.017
 shampoo+0.015
 vinegar+0.015
aj+0.015
Neg logit contributions
pole-0.013
 down-0.013
 forth-0.012
 around-0.011
stone-0.011
Tokenir
Token ID343
Feature activation-1.05e-02

Pos logit contributions
pole+0.004
emaker+0.004
 warrior+0.004
ickets+0.004
ados+0.003
Neg logit contributions
 shampoo-0.004
 fault-0.004
 vinegar-0.004
 L-0.004
 common-0.004
Token.
Token ID13
Feature activation+1.82e-02

Pos logit contributions
 warrior+0.010
pole+0.009
emaker+0.009
ickets+0.008
ados+0.008
Neg logit contributions
 fault-0.021
 shampoo-0.021
 L-0.020
 vinegar-0.020
 common-0.020
Token
Token ID198
Feature activation+2.06e-02

Pos logit contributions
 shampoo+0.023
 L+0.023
 fault+0.023
 common+0.022
 vinegar+0.021
Neg logit contributions
emaker-0.030
pole-0.030
 warrior-0.030
ickets-0.028
stone-0.028
Token
Token ID198
Feature activation+1.41e-02

Pos logit contributions
 shampoo+0.024
 fault+0.023
 vinegar+0.022
 common+0.022
 L+0.022
Neg logit contributions
pole-0.037
emaker-0.036
 warrior-0.036
ickets-0.035
ados-0.034
Token"
Token ID1
Feature activation-2.63e-02

Pos logit contributions
 shampoo+0.021
 common+0.020
 L+0.020
 bruises+0.019
 ruined+0.018
Neg logit contributions
pole-0.020
emaker-0.020
ados-0.020
 warrior-0.020
umbo-0.019
Token.
Token ID13
Feature activation-2.19e-02

Pos logit contributions
pole+0.005
 warrior+0.005
emaker+0.004
stone+0.004
ados+0.004
Neg logit contributions
 shampoo-0.005
 fault-0.005
 vinegar-0.005
 bruises-0.005
 common-0.005
Token I
Token ID314
Feature activation-3.88e-03

Pos logit contributions
pole+0.029
 warrior+0.028
ickets+0.028
emaker+0.027
ados+0.026
Neg logit contributions
 fault-0.035
 shampoo-0.034
 common-0.034
 vinegar-0.033
 ruined-0.032
Token want
Token ID765
Feature activation-5.65e-02

Pos logit contributions
 warrior+0.004
 around+0.004
est+0.004
pole+0.004
age+0.004
Neg logit contributions
 bruises-0.007
 vinegar-0.006
aj-0.006
 shampoo-0.006
 injuries-0.006
Token to
Token ID284
Feature activation-1.62e-02

Pos logit contributions
ados+0.059
ickets+0.059
pole+0.059
 trolls+0.058
 owl+0.057
Neg logit contributions
 fault-0.097
 common-0.095
aj-0.095
ses-0.092
ours-0.091
Token help
Token ID1037
Feature activation-1.26e-02

Pos logit contributions
pole+0.017
 owl+0.017
ickets+0.017
 warrior+0.017
 King+0.016
Neg logit contributions
ours-0.030
outed-0.028
 vinegar-0.028
 fault-0.028
aj-0.027
Token all
Token ID477
Feature activation-8.27e-02

Pos logit contributions
pole+0.020
 warrior+0.019
emaker+0.019
umbo+0.018
stone+0.018
Neg logit contributions
 shampoo-0.018
 L-0.018
 vinegar-0.017
 common-0.016
 fault-0.016
Token the
Token ID262
Feature activation-8.56e-03

Pos logit contributions
pole+0.130
 warrior+0.127
emaker+0.125
ados+0.120
ickets+0.120
Neg logit contributions
 shampoo-0.115
 L-0.108
 fault-0.108
 vinegar-0.108
 common-0.107
Token animals
Token ID4695
Feature activation-1.22e-02

Pos logit contributions
pole+0.009
 warrior+0.008
ados+0.008
emaker+0.008
ickets+0.008
Neg logit contributions
 fault-0.016
 shampoo-0.016
 vinegar-0.015
 common-0.015
 bruises-0.015
Token,
Token ID11
Feature activation-1.52e-02

Pos logit contributions
pole+0.018
 warrior+0.017
emaker+0.017
ickets+0.016
ados+0.016
Neg logit contributions
 shampoo-0.018
 fault-0.018
 vinegar-0.017
 common-0.017
 bruises-0.017
Token even
Token ID772
Feature activation-1.11e-02

Pos logit contributions
pole+0.019
 warrior+0.017
 owl+0.017
ickets+0.017
 King+0.017
Neg logit contributions
 fault-0.025
 common-0.025
 vinegar-0.025
ours-0.024
 shampoo-0.024
Token the
Token ID262
Feature activation-8.75e-03

Pos logit contributions
 warrior+0.013
pole+0.013
 owl+0.012
 down+0.012
stone+0.012
Neg logit contributions
 fault-0.021
aj-0.019
ses-0.019
omo-0.019
outed-0.018
Token are
Token ID389
Feature activation-1.56e-02

Pos logit contributions
pole+0.014
 warrior+0.014
emaker+0.014
ickets+0.014
stone+0.013
Neg logit contributions
 fault-0.012
 shampoo-0.012
 vinegar-0.012
 common-0.011
 bruises-0.011
Token happy
Token ID3772
Feature activation-1.02e-02

Pos logit contributions
pole+0.024
 warrior+0.023
emaker+0.022
ickets+0.022
ados+0.021
Neg logit contributions
 shampoo-0.022
 fault-0.022
 vinegar-0.021
 common-0.021
 L-0.020
Token.
Token ID13
Feature activation-3.73e-03

Pos logit contributions
ickets+0.012
ados+0.012
 warrior+0.012
pole+0.011
 trolls+0.011
Neg logit contributions
 fault-0.017
 shampoo-0.017
 common-0.017
 vinegar-0.016
 cheaper-0.016
Token They
Token ID1119
Feature activation-9.60e-03

Pos logit contributions
ickets+0.003
 Everyone+0.003
 Everybody+0.003
amber+0.003
 Charlie+0.003
Neg logit contributions
 fault-0.007
rou-0.007
 ruined-0.007
 bruises-0.007
 cheaper-0.006
Token are
Token ID389
Feature activation-1.01e-02

Pos logit contributions
pole+0.017
 warrior+0.017
emaker+0.016
ickets+0.016
stone+0.016
Neg logit contributions
 shampoo-0.011
 fault-0.011
 vinegar-0.010
 common-0.010
 bruises-0.010
Token friends
Token ID2460
Feature activation-7.12e-02

Pos logit contributions
pole+0.015
 warrior+0.014
emaker+0.014
ickets+0.013
ados+0.013
Neg logit contributions
 shampoo-0.015
 fault-0.015
 vinegar-0.014
 common-0.014
 bruises-0.014
Token.
Token ID13
Feature activation-7.48e-03

Pos logit contributions
pole+0.121
emaker+0.117
 warrior+0.117
ickets+0.113
ados+0.112
Neg logit contributions
 shampoo-0.089
 fault-0.087
 L-0.083
 vinegar-0.083
 common-0.083
Token<|endoftext|>
Token ID50256
Feature activation+2.48e-03

Pos logit contributions
ickets+0.007
 Everyone+0.006
 Everybody+0.006
 Charlie+0.006
amber+0.006
Neg logit contributions
 fault-0.015
rou-0.014
 ruined-0.014
 bruises-0.013
 cheaper-0.013
TokenL
Token ID43
Feature activation+2.36e-02

Pos logit contributions
 fault+0.003
 shampoo+0.003
 vinegar+0.003
 bruises+0.003
 common+0.003
Neg logit contributions
pole-0.004
emaker-0.004
ickets-0.004
 warrior-0.004
ados-0.004
Tokenily
Token ID813
Feature activation+1.29e-02

Pos logit contributions
 shampoo+0.021
 fault+0.020
 vinegar+0.019
 L+0.019
 common+0.018
Neg logit contributions
pole-0.049
 warrior-0.048
emaker-0.048
ickets-0.047
ados-0.046
Token and
Token ID290
Feature activation+1.36e-02

Pos logit contributions
 shampoo+0.017
 fault+0.017
 L+0.016
 vinegar+0.016
 common+0.016
Neg logit contributions
pole-0.021
emaker-0.020
 warrior-0.020
ickets-0.020
ados-0.020
Token day
Token ID1110
Feature activation+2.83e-03

Pos logit contributions
 shampoo+0.071
 L+0.067
 fault+0.067
 common+0.067
 vinegar+0.067
Neg logit contributions
pole-0.055
emaker-0.051
 warrior-0.051
ados-0.051
ickets-0.049
Token,
Token ID11
Feature activation-2.87e-02

Pos logit contributions
 L+0.004
 common+0.003
 shampoo+0.003
 gas+0.003
 their+0.003
Neg logit contributions
pole-0.005
emaker-0.005
ickets-0.005
umb-0.005
quet-0.004
Token he
Token ID339
Feature activation-1.36e-02

Pos logit contributions
pole+0.037
emaker+0.036
 warrior+0.036
ickets+0.035
ados+0.034
Neg logit contributions
 shampoo-0.047
 fault-0.046
 vinegar-0.045
 common-0.045
 L-0.044
Token sees
Token ID7224
Feature activation+1.52e-02

Pos logit contributions
 warrior+0.022
pole+0.022
emaker+0.021
ickets+0.021
 trolls+0.020
Neg logit contributions
 shampoo-0.017
 fault-0.017
 vinegar-0.016
 bruises-0.016
 common-0.016
Token a
Token ID257
Feature activation-1.99e-02

Pos logit contributions
 fault+0.025
aj+0.024
 common+0.023
ucker+0.023
ours+0.022
Neg logit contributions
 King-0.020
 Charlie-0.020
on-0.019
 owl-0.019
 warrior-0.019
Token big
Token ID1263
Feature activation-6.95e-02

Pos logit contributions
 warrior+0.026
pole+0.025
 eagle+0.023
 King+0.023
stone+0.023
Neg logit contributions
 fault-0.034
 bruises-0.032
 shampoo-0.031
 vinegar-0.031
 common-0.030
Token building
Token ID2615
Feature activation-1.80e-02

Pos logit contributions
pole+0.097
emaker+0.095
ickets+0.094
 warrior+0.087
ados+0.086
Neg logit contributions
 shampoo-0.112
 vinegar-0.105
 L-0.105
 fault-0.103
 common-0.102
Token far
Token ID1290
Feature activation-3.22e-02

Pos logit contributions
pole+0.024
emaker+0.023
 warrior+0.023
ickets+0.022
ados+0.022
Neg logit contributions
 shampoo-0.029
 fault-0.028
 vinegar-0.028
 L-0.027
 common-0.027
Token away
Token ID1497
Feature activation-5.85e-02

Pos logit contributions
pole+0.035
emaker+0.035
ickets+0.034
 warrior+0.034
ados+0.033
Neg logit contributions
 shampoo-0.060
 common-0.058
 L-0.057
 vinegar-0.056
 fault-0.055
Token.
Token ID13
Feature activation-1.77e-02

Pos logit contributions
pole+0.090
emaker+0.086
 warrior+0.086
ickets+0.083
ados+0.082
Neg logit contributions
 shampoo-0.083
 fault-0.081
 vinegar-0.079
 common-0.079
 L-0.078
Token It
Token ID632
Feature activation-6.31e-03

Pos logit contributions
emaker+0.030
pole+0.029
 warrior+0.027
ickets+0.027
stone+0.027
Neg logit contributions
 L-0.023
 shampoo-0.022
 gas-0.022
 vinegar-0.022
 bruises-0.022
Token.
Token ID13
Feature activation+9.10e-03

Pos logit contributions
 fault+0.058
 shampoo+0.058
 vinegar+0.056
 common+0.056
 bruises+0.056
Neg logit contributions
pole-0.051
emaker-0.044
ados-0.043
ickets-0.043
 down-0.043
Token They
Token ID1119
Feature activation-5.32e-03

Pos logit contributions
 bruises+0.016
 ruined+0.015
 swollen+0.014
 fault+0.014
rou+0.014
Neg logit contributions
 around-0.011
 down-0.011
amber-0.011
 Everybody-0.010
 Everyone-0.010
Token saw
Token ID2497
Feature activation+8.46e-03

Pos logit contributions
pole+0.009
 warrior+0.009
emaker+0.008
umbo+0.008
ickets+0.008
Neg logit contributions
 fault-0.007
 vinegar-0.007
 shampoo-0.007
 common-0.006
 bruises-0.006
Token a
Token ID257
Feature activation-1.77e-02

Pos logit contributions
aj+0.016
 common+0.015
ucker+0.014
 injuries+0.014
 fault+0.013
Neg logit contributions
 owl-0.010
 eagle-0.010
 down-0.009
pole-0.009
ados-0.009
Token big
Token ID1263
Feature activation-6.62e-02

Pos logit contributions
pole+0.024
 warrior+0.023
stone+0.022
emaker+0.022
 eagle+0.021
Neg logit contributions
 fault-0.029
 shampoo-0.027
 vinegar-0.027
 bruises-0.027
 common-0.026
Token pile
Token ID14540
Feature activation-7.99e-02

Pos logit contributions
pole+0.092
emaker+0.091
ickets+0.089
 warrior+0.085
ados+0.083
Neg logit contributions
 shampoo-0.106
 vinegar-0.100
 L-0.099
 fault-0.097
 common-0.097
Token of
Token ID286
Feature activation-1.37e-02

Pos logit contributions
 warrior+0.102
pole+0.099
emaker+0.099
ados+0.095
ickets+0.094
Neg logit contributions
 shampoo-0.132
 vinegar-0.127
 L-0.127
 fault-0.123
 bruises-0.121
Token ash
Token ID12530
Feature activation+2.99e-02

Pos logit contributions
pole+0.018
ados+0.018
 warrior+0.018
 mushroom+0.017
stone+0.017
Neg logit contributions
 fault-0.023
 common-0.021
aj-0.020
 shampoo-0.019
 Qu-0.019
Token near
Token ID1474
Feature activation+2.01e-02

Pos logit contributions
 shampoo+0.044
 fault+0.043
 vinegar+0.043
 L+0.042
 bruises+0.040
Neg logit contributions
emaker-0.043
 warrior-0.043
pole-0.043
ickets-0.041
umbo-0.039
Token a
Token ID257
Feature activation-1.29e-03

Pos logit contributions
aj+0.045
 fault+0.043
 disl+0.040
rou+0.039
ucker+0.038
Neg logit contributions
 down-0.019
 Charlie-0.017
 out-0.017
 through-0.016
 around-0.016
Token bench
Token ID7624
Feature activation-2.31e-02

Pos logit contributions
pole+0.001
 warrior+0.001
emaker+0.001
stone+0.001
ickets+0.001
Neg logit contributions
 fault-0.003
 shampoo-0.003
 common-0.003
 bruises-0.003
 vinegar-0.003
Token nobody
Token ID8168
Feature activation+3.74e-02

Pos logit contributions
pole+0.034
emaker+0.033
lf+0.032
 King+0.032
 warrior+0.031
Neg logit contributions
 fault-0.041
 vinegar-0.040
 common-0.040
 shampoo-0.037
aj-0.036
Token answered
Token ID9373
Feature activation-2.94e-02

Pos logit contributions
 shampoo+0.052
 fault+0.052
 vinegar+0.050
 common+0.049
 bruises+0.048
Neg logit contributions
emaker-0.059
pole-0.059
 warrior-0.057
ickets-0.055
stone-0.054
Token.
Token ID13
Feature activation-1.11e-02

Pos logit contributions
pole+0.031
emaker+0.030
ados+0.028
 down+0.028
fully+0.028
Neg logit contributions
 fault-0.056
 vinegar-0.054
 common-0.054
 shampoo-0.052
 bruises-0.051
Token She
Token ID1375
Feature activation-3.33e-02

Pos logit contributions
pole+0.016
 warrior+0.015
emaker+0.015
ados+0.015
ickets+0.014
Neg logit contributions
 fault-0.016
 shampoo-0.016
 vinegar-0.016
 common-0.016
 bruises-0.016
Token was
Token ID373
Feature activation+1.40e-02

Pos logit contributions
pole+0.046
 warrior+0.046
 eagle+0.045
stone+0.044
 owl+0.043
Neg logit contributions
 fault-0.058
 common-0.051
 vinegar-0.051
 shampoo-0.048
ours-0.047
Token all
Token ID477
Feature activation-9.24e-02

Pos logit contributions
 common+0.021
 fault+0.021
 vinegar+0.021
 shampoo+0.021
aj+0.020
Neg logit contributions
pole-0.020
 warrior-0.018
emaker-0.018
 King-0.017
 Charlie-0.017
Token alone
Token ID3436
Feature activation-1.99e-03

Pos logit contributions
pole+0.044
emaker+0.034
 warrior+0.030
 around+0.028
stone+0.028
Neg logit contributions
 common-0.226
 shampoo-0.225
 fault-0.224
aj-0.223
 vinegar-0.223
Token.
Token ID13
Feature activation-3.56e-03

Pos logit contributions
pole+0.002
 warrior+0.002
emaker+0.002
ados+0.002
stone+0.002
Neg logit contributions
 shampoo-0.004
 fault-0.004
 vinegar-0.004
 common-0.004
 L-0.003
Token Suddenly
Token ID24975
Feature activation+3.68e-02

Pos logit contributions
pole+0.004
emaker+0.004
ados+0.004
 warrior+0.004
ickets+0.004
Neg logit contributions
 vinegar-0.006
 shampoo-0.006
 fault-0.006
 common-0.006
 bruises-0.006
Token,
Token ID11
Feature activation-2.56e-02

Pos logit contributions
 shampoo+0.062
 fault+0.060
 L+0.059
 vinegar+0.058
 common+0.058
Neg logit contributions
pole-0.048
emaker-0.045
 warrior-0.045
ickets-0.044
ados-0.042
Token it
Token ID340
Feature activation-5.38e-03

Pos logit contributions
 King+0.030
 down+0.029
ados+0.029
emaker+0.029
 Charlie+0.029
Neg logit contributions
 fault-0.045
 common-0.042
 vinegar-0.041
aj-0.040
ours-0.039