TOP ACTIVATIONS
MAX = 8.561

be the driver and the passenger . They say , "
, a group of mis chie vous mice came by and
buck led up in the passenger seat . They drove along
was the driver or the passenger . One day
One day , a new passenger climbed aboard . They introduced
know that the friendly new passenger would change their lives forever
For hidden in the friendly passenger 's pocket was something magical
When the friendly new passenger placed the conductor 's hat
the squirrel got a mis chie vous look in its eye
so that no more mis chie vous mice could come in
, " I am the passenger . I look out the
driver . I am the passenger . You have to go
sweet tune , a mis chie vous fox appeared . "
One day a mis chie vous monkey saw the bear
" Let 's go , mate y !" Ben said .
and became a great violin ist . <|endoftext|> Once upon a
But then , a mis chie vous rabbit came and started
finally , the z ig zag had an idea . It
to see the graceful violin ist ." They went
saw something shiny and gl ist ening on the ground -

MIN ACTIVATIONS
MIN = -6.039

. Mom says they are av oc ados . Sara wants
. Lily loved to eat av oc ados , they were
Maybe they could grow more av oc ados and share them
but there were no other av oc ados .
before . The av oc ados were shared with
so happy to have her av oc ados . She thanked
At the or chard , they picked as many
. They forget about the av oc ados . They just
away . She learned that av oc ados are good for
something new ! She thought av oc ados were the most
went to the closest or chard . At the
happy that it produced more av oc ados than ever before
on , whenever they wanted av oc ados , they would
and her mom sorted the av oc ados into piles according
from disturbing the cherry or chard . Had he not been
and shared everything , including av oc ados . They were
every day to supply the av oc ados . And the
weather before he picked his av oc ados . <|endoftext|> Once
says they are av oc ados . Sara wants to try
they had never seen the av oc ados . They wished

INTERVAL 4.911 - 8.561
CONTAINS 0.050%

sun and Boris knew he 'd found a true companion .
thought about it for a moment and realized that the frog
immer ing in the moon light . It was so quiet
world he promised himself he 'd come back soon . <|endoftext|>
shapes . After a few minutes , he saw a bird

INTERVAL 1.261 - 4.911
CONTAINS 12.470%

up the adventure with one final zoom ! <|endoftext|> Once upon
gone on an adventure and rocked on the big white sail
ily smiled and said , " Che ese !" <|endoftext|> S
hands , mom my tried one more time and the door
One day , he stumbled across a big box in his

INTERVAL -2.389 - 1.261
CONTAINS 84.391%

bright pattern in the milk . She feels so happy and
his homework . He went to his room and played with
They keep playing with clay and making different things .
, there were two friends . One day , they decided
, always running and jumping around . One day

INTERVAL -6.039 - -2.389
CONTAINS 3.089%

" Let 's take it home and show it to mom
opl ane crashed on the floor . It broke into pieces
They are fragile and the ground is hard !"
pull it out of the ground and take it home .
zoom and crash on the floor . He also had a
Token be
Token ID307
Feature activation+1.36e+00

Pos logit contributions
 disl+0.010
ados+0.009
 Mickey+0.009
array+0.009
 avocado+0.009
Neg logit contributions
a-0.013
--0.011
ah-0.011
be-0.011
ch-0.010
Token the
Token ID262
Feature activation-9.48e-02

Pos logit contributions
a+0.086
ah+0.081
be+0.074
fly+0.072
iest+0.068
Neg logit contributions
 disl-0.087
ados-0.079
 Mickey-0.078
 vitamins-0.075
 court-0.074
Token driver
Token ID4639
Feature activation+3.84e+00

Pos logit contributions
 avocado+0.006
 disl+0.006
 vitamins+0.006
ados+0.006
 Mickey+0.006
Neg logit contributions
a-0.006
--0.005
be-0.005
ah-0.005
y-0.005
Token and
Token ID290
Feature activation+1.47e-02

Pos logit contributions
a+0.207
ah+0.172
web+0.171
iest+0.171
ch+0.169
Neg logit contributions
 avocado-0.241
 court-0.236
ados-0.236
 disl-0.227
 Mickey-0.222
Token the
Token ID262
Feature activation-1.17e-01

Pos logit contributions
a+0.001
-+0.001
ah+0.001
be+0.001
ch+0.001
Neg logit contributions
 disl-0.001
ados-0.001
 vitamins-0.001
 Mickey-0.001
array-0.001
Token passenger
Token ID11849
Feature activation+8.32e+00

Pos logit contributions
 disl+0.008
 avocado+0.008
ados+0.008
 vitamins+0.007
 Mickey+0.007
Neg logit contributions
a-0.007
--0.006
ah-0.006
be-0.006
y-0.005
Token.
Token ID13
Feature activation+5.65e-02

Pos logit contributions
a+0.479
ch+0.416
less+0.412
ah+0.391
web+0.383
Neg logit contributions
 disl-0.501
 court-0.498
ados-0.468
 avocado-0.457
yard-0.451
Token They
Token ID1119
Feature activation-1.03e+00

Pos logit contributions
a+0.004
ah+0.003
-+0.003
be+0.003
ch+0.003
Neg logit contributions
ados-0.003
 disl-0.003
array-0.003
 vitamins-0.003
 avocado-0.003
Token say
Token ID910
Feature activation+1.57e+00

Pos logit contributions
 disl+0.063
ados+0.059
 vitamins+0.058
 Mickey+0.057
array+0.057
Neg logit contributions
a-0.068
--0.061
be-0.058
ah-0.058
ch-0.054
Token,
Token ID11
Feature activation-4.24e-01

Pos logit contributions
a+0.099
ah+0.085
be+0.081
-+0.081
fly+0.079
Neg logit contributions
 disl-0.104
ados-0.101
 vitamins-0.095
 avocado-0.095
 Mickey-0.094
Token "
Token ID366
Feature activation+2.54e+00

Pos logit contributions
 disl+0.022
ados+0.020
 Mickey+0.019
 avocado+0.019
 Bruce+0.019
Neg logit contributions
a-0.033
ah-0.029
--0.029
be-0.028
iest-0.028
Token,
Token ID11
Feature activation-3.38e-01

Pos logit contributions
a+0.074
ah+0.060
-+0.059
be+0.059
fly+0.053
Neg logit contributions
 disl-0.130
ados-0.130
 Mickey-0.127
array-0.126
 vitamins-0.124
Token a
Token ID257
Feature activation+3.37e-01

Pos logit contributions
 disl+0.018
ados+0.017
 Mickey+0.016
 vitamins+0.016
array+0.016
Neg logit contributions
a-0.026
--0.023
be-0.022
ah-0.022
ch-0.021
Token group
Token ID1448
Feature activation+1.07e+00

Pos logit contributions
a+0.020
be+0.018
ah+0.018
-+0.017
ist+0.017
Neg logit contributions
 avocado-0.021
 Mickey-0.021
 disl-0.020
 av-0.020
 court-0.020
Token of
Token ID286
Feature activation+2.12e+00

Pos logit contributions
a+0.039
ah+0.033
z+0.029
fly+0.029
be+0.027
Neg logit contributions
 court-0.092
 Mickey-0.089
 Bruce-0.088
ados-0.086
array-0.086
Token mis
Token ID2984
Feature activation-5.11e-01

Pos logit contributions
a+0.138
-+0.121
ah+0.119
be+0.117
ch+0.108
Neg logit contributions
 disl-0.131
ados-0.127
 vitamins-0.123
 Mickey-0.120
array-0.120
Tokenchie
Token ID3043
Feature activation+8.17e+00

Pos logit contributions
ados+0.045
 disl+0.044
array+0.043
 av+0.042
 avocado+0.042
Neg logit contributions
a-0.017
ah-0.014
--0.014
ch-0.012
fly-0.012
Tokenvous
Token ID31222
Feature activation+2.86e+00

Pos logit contributions
a+0.471
 closer+0.424
less+0.417
fly+0.414
-+0.412
Neg logit contributions
 disl-0.499
array-0.441
ados-0.430
 vitamins-0.426
 avocado-0.423
Token mice
Token ID10693
Feature activation-1.87e+00

Pos logit contributions
a+0.192
-+0.165
ah+0.163
be+0.162
ch+0.151
Neg logit contributions
 disl-0.173
ados-0.169
 vitamins-0.161
array-0.160
 Mickey-0.158
Token came
Token ID1625
Feature activation+1.81e+00

Pos logit contributions
 disl+0.142
ados+0.138
 vitamins+0.134
 Mickey+0.133
array+0.133
Neg logit contributions
a-0.094
--0.079
ah-0.077
be-0.076
ch-0.070
Token by
Token ID416
Feature activation-2.83e+00

Pos logit contributions
a+0.087
ah+0.076
be+0.071
-+0.068
iest+0.065
Neg logit contributions
 disl-0.134
ados-0.131
 Mickey-0.130
 Bruce-0.126
array-0.125
Token and
Token ID290
Feature activation+1.52e-01

Pos logit contributions
 disl+0.214
ados+0.206
array+0.199
 vitamins+0.199
 Mickey+0.197
Neg logit contributions
a-0.149
--0.125
ah-0.123
be-0.121
ch-0.111
Token buck
Token ID10230
Feature activation+1.38e+00

Pos logit contributions
a+0.035
less+0.031
ah+0.030
-+0.030
ch+0.029
Neg logit contributions
 disl-0.044
array-0.043
 Mickey-0.042
 avocado-0.041
ados-0.041
Tokenled
Token ID992
Feature activation-8.15e-02

Pos logit contributions
a+0.087
be+0.074
-+0.074
ah+0.073
ch+0.070
Neg logit contributions
 disl-0.086
ados-0.085
array-0.081
 vitamins-0.080
 Mickey-0.079
Token up
Token ID510
Feature activation-3.18e+00

Pos logit contributions
ados+0.005
 disl+0.004
 vitamins+0.004
 Mickey+0.004
 avocado+0.004
Neg logit contributions
a-0.006
be-0.005
ah-0.005
--0.005
fly-0.005
Token in
Token ID287
Feature activation-8.02e-02

Pos logit contributions
ados+0.203
 avocado+0.202
 av+0.200
 Mickey+0.194
 Bruce+0.194
Neg logit contributions
a-0.188
be-0.171
ch-0.156
ah-0.153
fly-0.153
Token the
Token ID262
Feature activation-1.89e-01

Pos logit contributions
 disl+0.004
 vitamins+0.004
array+0.004
ados+0.004
 avocado+0.004
Neg logit contributions
a-0.006
fly-0.005
ah-0.005
be-0.005
--0.005
Token passenger
Token ID11849
Feature activation+8.15e+00

Pos logit contributions
 avocado+0.011
 disl+0.011
array+0.010
ados+0.010
 vitamins+0.010
Neg logit contributions
a-0.014
--0.011
ah-0.011
be-0.011
as-0.011
Token seat
Token ID5852
Feature activation+2.41e+00

Pos logit contributions
a+0.496
ch+0.447
less+0.446
fly+0.431
web+0.422
Neg logit contributions
 court-0.439
yard-0.426
 Her-0.420
 avocado-0.420
array-0.418
Token.
Token ID13
Feature activation+2.08e-01

Pos logit contributions
a+0.132
ch+0.120
fly+0.113
be+0.112
ah+0.108
Neg logit contributions
ados-0.142
yard-0.139
 court-0.138
 avocado-0.135
 herself-0.134
Token They
Token ID1119
Feature activation-8.07e-01

Pos logit contributions
a+0.007
 of+0.007
-+0.006
ch+0.005
y+0.005
Neg logit contributions
ados-0.018
 disl-0.018
 vitamins-0.018
 av-0.017
 avocado-0.017
Token drove
Token ID10357
Feature activation+2.88e+00

Pos logit contributions
 Mickey+0.041
 disl+0.040
array+0.039
 Bruce+0.039
 court+0.038
Neg logit contributions
a-0.054
--0.049
less-0.048
fly-0.046
ah-0.045
Token along
Token ID1863
Feature activation-2.00e-02

Pos logit contributions
a+0.204
fly+0.195
ah+0.173
web+0.173
rot+0.169
Neg logit contributions
 Jack-0.146
 Jerry-0.141
 Bruce-0.140
ados-0.139
 Mickey-0.138
Token was
Token ID373
Feature activation-4.98e-01

Pos logit contributions
a+0.017
less+0.015
ah+0.015
be+0.014
-+0.014
Neg logit contributions
 disl-0.020
 vitamins-0.019
array-0.019
ados-0.019
 court-0.018
Token the
Token ID262
Feature activation-2.54e-01

Pos logit contributions
 disl+0.028
 Mickey+0.026
ados+0.026
 vitamins+0.025
 court+0.025
Neg logit contributions
a-0.033
ah-0.031
be-0.029
--0.028
y-0.027
Token driver
Token ID4639
Feature activation+3.60e+00

Pos logit contributions
 vitamins+0.014
 court+0.014
 disl+0.014
 Mickey+0.013
array+0.013
Neg logit contributions
a-0.015
--0.014
ry-0.013
less-0.013
y-0.013
Token or
Token ID393
Feature activation-1.40e+00

Pos logit contributions
a+0.182
less+0.151
 closer+0.147
be+0.147
ah+0.146
Neg logit contributions
 avocado-0.222
ados-0.215
 Mickey-0.214
 court-0.204
 disl-0.203
Token the
Token ID262
Feature activation-2.89e-01

Pos logit contributions
 disl+0.099
ados+0.096
 vitamins+0.093
array+0.092
 Mickey+0.091
Neg logit contributions
a-0.080
--0.069
ah-0.066
be-0.066
ch-0.061
Token passenger
Token ID11849
Feature activation+8.08e+00

Pos logit contributions
 disl+0.018
 vitamins+0.017
 court+0.017
array+0.017
 Mickey+0.016
Neg logit contributions
a-0.018
--0.016
ah-0.015
y-0.015
be-0.014
Token.
Token ID13
Feature activation+7.08e-02

Pos logit contributions
a+0.508
less+0.433
ch+0.405
web+0.399
ah+0.396
Neg logit contributions
 court-0.442
 disl-0.429
 Everyone-0.406
 sidewalk-0.402
yard-0.397
Token
Token ID198
Feature activation-7.13e-01

Pos logit contributions
a+0.005
be+0.004
ah+0.004
ch+0.004
-+0.004
Neg logit contributions
 disl-0.004
ados-0.004
 vitamins-0.004
array-0.004
 avocado-0.004
Token
Token ID198
Feature activation-6.70e-01

Pos logit contributions
ados+0.050
 disl+0.050
 vitamins+0.047
array+0.046
 avocado+0.046
Neg logit contributions
a-0.044
--0.037
be-0.036
ah-0.035
ch-0.034
TokenOne
Token ID3198
Feature activation+6.41e-01

Pos logit contributions
 disl+0.050
ados+0.049
 vitamins+0.047
 Mickey+0.046
array+0.046
Neg logit contributions
a-0.038
--0.031
be-0.030
ah-0.030
ch-0.028
Token day
Token ID1110
Feature activation+9.46e-01

Pos logit contributions
fly+0.058
king+0.056
cher+0.056
rot+0.055
flake+0.052
Neg logit contributions
 Every-0.013
 Everyone-0.012
 One-0.011
 Sundays-0.011
 disl-0.010
TokenOne
Token ID3198
Feature activation+6.85e-01

Pos logit contributions
 disl+0.019
array+0.018
 vitamins+0.017
ados+0.017
 Mickey+0.017
Neg logit contributions
a-0.023
--0.021
ah-0.020
be-0.020
less-0.019
Token day
Token ID1110
Feature activation+9.00e-01

Pos logit contributions
cher+0.059
fly+0.056
king+0.055
ist+0.055
chers+0.055
Neg logit contributions
 Every-0.014
 Billy-0.013
 Everyone-0.013
 disl-0.012
 avocado-0.012
Token,
Token ID11
Feature activation-3.40e-01

Pos logit contributions
a+0.049
be+0.041
ah+0.041
fly+0.038
-+0.037
Neg logit contributions
ados-0.063
 Mickey-0.062
 disl-0.061
 avocado-0.060
 Bruce-0.060
Token a
Token ID257
Feature activation+6.34e-01

Pos logit contributions
 Mickey+0.020
ados+0.019
 avocado+0.018
 Bruce+0.018
 av+0.018
Neg logit contributions
a-0.023
ah-0.021
be-0.021
--0.020
fly-0.019
Token new
Token ID649
Feature activation-4.41e-01

Pos logit contributions
a+0.042
z+0.041
ah+0.040
ac+0.040
ist+0.040
Neg logit contributions
 Mickey-0.032
 courtroom-0.029
 court-0.029
 avocado-0.029
 Bruce-0.029
Token passenger
Token ID11849
Feature activation+8.07e+00

Pos logit contributions
 disl+0.023
 court+0.023
 sidewalk+0.022
 courtroom+0.022
 squash+0.021
Neg logit contributions
a-0.024
less-0.022
pr-0.022
as-0.022
light-0.022
Token climbed
Token ID19952
Feature activation+5.56e-02

Pos logit contributions
a+0.496
less+0.470
ch+0.417
as+0.405
 closer+0.399
Neg logit contributions
 court-0.425
 disl-0.404
array-0.404
 courtroom-0.396
yard-0.386
Token aboard
Token ID15500
Feature activation+1.29e+00

Pos logit contributions
a+0.004
be+0.003
as+0.003
less+0.003
ah+0.003
Neg logit contributions
ados-0.003
 av-0.003
 Bruce-0.003
 Mickey-0.003
array-0.003
Token.
Token ID13
Feature activation+2.45e-01

Pos logit contributions
a+0.075
be+0.068
ah+0.063
ch+0.062
-+0.060
Neg logit contributions
 court-0.081
 Bruce-0.081
 Mickey-0.081
 avocado-0.079
ados-0.079
Token They
Token ID1119
Feature activation-7.77e-01

Pos logit contributions
a+0.017
-+0.016
ch+0.016
ah+0.015
 of+0.015
Neg logit contributions
 disl-0.014
ados-0.012
 vitamins-0.012
array-0.012
 avocado-0.011
Token introduced
Token ID5495
Feature activation+2.44e-01

Pos logit contributions
 disl+0.047
 Mickey+0.046
ados+0.046
array+0.046
 Bruce+0.045
Neg logit contributions
a-0.048
--0.042
ah-0.040
be-0.040
less-0.039
Token know
Token ID760
Feature activation+6.66e-01

Pos logit contributions
a+0.044
-+0.039
be+0.037
ah+0.037
ch+0.035
Neg logit contributions
 disl-0.041
ados-0.039
 vitamins-0.038
 Mickey-0.037
array-0.037
Token that
Token ID326
Feature activation+4.36e-02

Pos logit contributions
a+0.041
ah+0.036
be+0.035
-+0.035
ch+0.033
Neg logit contributions
 disl-0.044
ados-0.042
 vitamins-0.041
 Mickey-0.040
 avocado-0.040
Token the
Token ID262
Feature activation-1.21e-01

Pos logit contributions
a+0.003
-+0.002
ah+0.002
be+0.002
ch+0.002
Neg logit contributions
 disl-0.003
ados-0.003
 vitamins-0.003
 Mickey-0.003
array-0.003
Token friendly
Token ID8030
Feature activation+2.73e-01

Pos logit contributions
 disl+0.007
 vitamins+0.006
 court+0.006
 sidewalk+0.006
 courtroom+0.006
Neg logit contributions
a-0.008
ah-0.008
y-0.008
fly-0.008
light-0.007
Token new
Token ID649
Feature activation-4.32e-01

Pos logit contributions
a+0.016
ah+0.014
fly+0.014
light+0.013
pr+0.013
Neg logit contributions
 disl-0.017
 court-0.016
 courtroom-0.016
 Everyone-0.015
 vitamins-0.015
Token passenger
Token ID11849
Feature activation+8.01e+00

Pos logit contributions
 disl+0.027
 court+0.025
 vitamins+0.024
 Everyone+0.023
 courtroom+0.023
Neg logit contributions
a-0.024
fly-0.023
light-0.022
ah-0.022
less-0.022
Token would
Token ID561
Feature activation+2.46e+00

Pos logit contributions
a+0.445
less+0.395
ch+0.391
be+0.371
ah+0.370
Neg logit contributions
 disl-0.509
 Mickey-0.457
ados-0.457
 vitamins-0.456
 avocado-0.456
Token change
Token ID1487
Feature activation+2.59e+00

Pos logit contributions
a+0.144
-+0.124
ah+0.118
be+0.118
ch+0.110
Neg logit contributions
 disl-0.171
ados-0.161
 vitamins-0.159
 Mickey-0.158
array-0.156
Token their
Token ID511
Feature activation+1.36e+00

Pos logit contributions
a+0.151
ah+0.139
be+0.136
ch+0.127
-+0.124
Neg logit contributions
 disl-0.173
ados-0.160
 vitamins-0.160
 Mickey-0.156
 avocado-0.154
Token lives
Token ID3160
Feature activation+7.54e-02

Pos logit contributions
a+0.107
ah+0.097
be+0.091
-+0.089
ch+0.089
Neg logit contributions
 disl-0.069
 vitamins-0.063
ados-0.060
array-0.058
 avocado-0.057
Token forever
Token ID8097
Feature activation+3.06e-01

Pos logit contributions
ah+0.004
a+0.003
ch+0.003
be+0.003
fly+0.003
Neg logit contributions
 court-0.005
 disl-0.005
 av-0.005
 vitamins-0.004
 avocado-0.004
Token For
Token ID1114
Feature activation+7.78e-01

Pos logit contributions
a+0.028
-+0.025
be+0.025
ch+0.024
ah+0.024
Neg logit contributions
 disl-0.019
ados-0.018
 vitamins-0.017
array-0.017
 avocado-0.016
Token hidden
Token ID7104
Feature activation-1.03e+00

Pos logit contributions
a+0.051
ah+0.043
-+0.043
be+0.042
less+0.041
Neg logit contributions
 disl-0.049
 vitamins-0.046
ados-0.046
 Mickey-0.045
 Bruce-0.044
Token in
Token ID287
Feature activation+5.37e-02

Pos logit contributions
 disl+0.055
ados+0.053
 vitamins+0.052
 Mickey+0.048
 Bruce+0.048
Neg logit contributions
a-0.075
be-0.071
ah-0.069
ch-0.064
less-0.064
Token the
Token ID262
Feature activation-1.17e-01

Pos logit contributions
a+0.004
ah+0.003
be+0.003
-+0.003
ch+0.003
Neg logit contributions
 disl-0.003
 vitamins-0.003
 Mickey-0.003
 court-0.003
array-0.003
Token friendly
Token ID8030
Feature activation+2.64e-01

Pos logit contributions
array+0.006
 disl+0.006
 vitamins+0.006
 court+0.006
 courtroom+0.005
Neg logit contributions
a-0.009
fly-0.008
ah-0.007
--0.007
ba-0.007
Token passenger
Token ID11849
Feature activation+7.99e+00

Pos logit contributions
a+0.018
ah+0.015
fly+0.015
ba+0.014
vy+0.014
Neg logit contributions
 disl-0.015
array-0.014
 court-0.014
 vitamins-0.014
 courtroom-0.014
Token's
Token ID338
Feature activation-7.47e-01

Pos logit contributions
a+0.444
ch+0.391
less+0.391
ah+0.386
be+0.359
Neg logit contributions
 disl-0.502
 court-0.489
ados-0.471
 Mickey-0.471
array-0.465
Token pocket
Token ID10000
Feature activation-2.71e+00

Pos logit contributions
 disl+0.043
 vitamins+0.039
ados+0.038
 court+0.037
array+0.037
Neg logit contributions
a-0.053
ah-0.048
ch-0.044
ba-0.043
be-0.043
Token was
Token ID373
Feature activation-3.18e-01

Pos logit contributions
 disl+0.196
ados+0.192
 Mickey+0.189
 vitamins+0.189
 avocado+0.186
Neg logit contributions
a-0.133
ah-0.120
be-0.114
ch-0.107
--0.101
Token something
Token ID1223
Feature activation-1.09e+00

Pos logit contributions
 disl+0.020
 Mickey+0.020
 vitamins+0.019
 Bruce+0.019
 avocado+0.019
Neg logit contributions
a-0.019
ah-0.017
be-0.016
--0.016
ch-0.015
Token magical
Token ID10883
Feature activation+7.19e-01

Pos logit contributions
 disl+0.066
 vitamins+0.063
 avocado+0.061
 Mickey+0.060
 Bruce+0.060
Neg logit contributions
a-0.071
ah-0.066
be-0.065
--0.058
z-0.058
Token
Token ID198
Feature activation-1.76e-01

Pos logit contributions
 disl+0.011
ados+0.010
 vitamins+0.010
array+0.010
 Mickey+0.010
Neg logit contributions
a-0.012
--0.010
ah-0.010
be-0.010
ch-0.009
TokenWhen
Token ID2215
Feature activation-2.43e-01

Pos logit contributions
 disl+0.012
 Mickey+0.011
array+0.011
ados+0.011
 vitamins+0.011
Neg logit contributions
a-0.010
--0.009
ah-0.009
be-0.009
less-0.008
Token the
Token ID262
Feature activation-9.42e-02

Pos logit contributions
 Mickey+0.014
ados+0.013
 Bruce+0.013
 disl+0.013
 avocado+0.013
Neg logit contributions
a-0.018
ah-0.015
--0.015
be-0.014
as-0.014
Token friendly
Token ID8030
Feature activation+2.71e-01

Pos logit contributions
 disl+0.005
 court+0.005
 sidewalk+0.005
 Mickey+0.005
 vitamins+0.005
Neg logit contributions
a-0.006
fly-0.005
y-0.005
less-0.005
ah-0.005
Token new
Token ID649
Feature activation-4.34e-01

Pos logit contributions
a+0.016
ah+0.013
pr+0.013
less+0.013
vy+0.012
Neg logit contributions
 disl-0.017
 Mickey-0.016
 court-0.016
 Everyone-0.016
 sidewalk-0.016
Token passenger
Token ID11849
Feature activation+7.98e+00

Pos logit contributions
 disl+0.025
 court+0.025
 Everyone+0.024
 requests+0.024
 vitamins+0.024
Neg logit contributions
a-0.024
less-0.021
fly-0.021
ifying-0.021
ah-0.019
Token placed
Token ID4624
Feature activation+7.11e-01

Pos logit contributions
a+0.475
less+0.445
ch+0.408
be+0.383
 closer+0.382
Neg logit contributions
 disl-0.445
 Mickey-0.435
 court-0.426
 From-0.422
array-0.421
Token the
Token ID262
Feature activation-8.76e-02

Pos logit contributions
a+0.047
be+0.042
ah+0.040
-+0.039
ch+0.036
Neg logit contributions
ados-0.044
 Mickey-0.042
 disl-0.041
 Bruce-0.041
 avocado-0.040
Token conductor
Token ID39206
Feature activation+3.80e+00

Pos logit contributions
 vitamins+0.005
 disl+0.005
 court+0.004
 avocado+0.004
 mischief+0.004
Neg logit contributions
a-0.005
fly-0.005
y-0.005
ah-0.005
ist-0.005
Token's
Token ID338
Feature activation-7.51e-01

Pos logit contributions
a+0.204
ah+0.185
less+0.173
ch+0.165
be+0.160
Neg logit contributions
 Mickey-0.225
 avocado-0.222
 av-0.221
ados-0.220
 disl-0.220
Token hat
Token ID6877
Feature activation+1.15e+00

Pos logit contributions
 vitamins+0.045
 disl+0.045
 avocado+0.042
ados+0.042
 court+0.041
Neg logit contributions
a-0.044
ah-0.040
be-0.038
y-0.038
fly-0.037
Token the
Token ID262
Feature activation-2.05e-02

Pos logit contributions
 disl+0.004
ados+0.004
 Mickey+0.004
 vitamins+0.004
array+0.004
Neg logit contributions
a-0.006
--0.006
be-0.006
ah-0.006
ch-0.005
Token squirrel
Token ID33039
Feature activation+2.28e-01

Pos logit contributions
 disl+0.002
ados+0.002
array+0.001
 vitamins+0.001
 Mickey+0.001
Neg logit contributions
a-0.001
--0.001
be-0.001
ah-0.001
ch-0.001
Token got
Token ID1392
Feature activation-3.10e-01

Pos logit contributions
a+0.013
ah+0.011
be+0.011
-+0.011
less+0.010
Neg logit contributions
 disl-0.015
 Mickey-0.015
ados-0.015
array-0.014
 avocado-0.014
Token a
Token ID257
Feature activation+6.63e-01

Pos logit contributions
 disl+0.024
ados+0.023
array+0.023
 vitamins+0.023
 Mickey+0.021
Neg logit contributions
a-0.016
--0.014
be-0.013
ah-0.013
 closer-0.012
Token mis
Token ID2984
Feature activation-5.05e-01

Pos logit contributions
a+0.045
be+0.039
ah+0.039
as+0.038
iest+0.038
Neg logit contributions
 avocado-0.037
 Mickey-0.036
 disl-0.035
 av-0.035
 court-0.034
Tokenchie
Token ID3043
Feature activation+7.96e+00

Pos logit contributions
ados+0.043
 disl+0.043
array+0.041
 avocado+0.041
 av+0.041
Neg logit contributions
a-0.017
--0.014
ah-0.014
ch-0.012
fly-0.011
Tokenvous
Token ID31222
Feature activation+2.88e+00

Pos logit contributions
a+0.541
fly+0.482
 steering+0.479
less+0.478
be+0.467
Neg logit contributions
 disl-0.424
 avocado-0.353
array-0.353
 vitamins-0.347
ados-0.344
Token look
Token ID804
Feature activation+1.79e+00

Pos logit contributions
a+0.182
be+0.148
ah+0.143
-+0.142
as+0.136
Neg logit contributions
 disl-0.187
ados-0.180
 avocado-0.178
 vitamins-0.174
 Mickey-0.173
Token in
Token ID287
Feature activation-1.99e-01

Pos logit contributions
a+0.090
be+0.076
ah+0.075
fly+0.073
 passenger+0.066
Neg logit contributions
 disl-0.129
ados-0.128
 avocado-0.127
 av-0.123
 vitamins-0.122
Token its
Token ID663
Feature activation+8.84e-01

Pos logit contributions
 disl+0.014
ados+0.013
 vitamins+0.013
array+0.013
 Mickey+0.013
Neg logit contributions
a-0.012
--0.010
ah-0.010
be-0.009
ch-0.009
Token eye
Token ID4151
Feature activation+7.94e-01

Pos logit contributions
a+0.058
-+0.049
be+0.049
ah+0.049
ch+0.045
Neg logit contributions
 disl-0.056
ados-0.054
 vitamins-0.051
 Mickey-0.051
array-0.051
Token so
Token ID523
Feature activation-1.55e+00

Pos logit contributions
a+0.036
ah+0.031
be+0.030
fly+0.027
ch+0.027
Neg logit contributions
ados-0.050
 disl-0.049
 Mickey-0.049
 avocado-0.048
 Bruce-0.048
Token that
Token ID326
Feature activation+1.08e-01

Pos logit contributions
 disl+0.098
ados+0.094
 vitamins+0.091
array+0.090
 Mickey+0.089
Neg logit contributions
a-0.100
--0.087
ah-0.085
be-0.084
ch-0.079
Token no
Token ID645
Feature activation+1.54e+00

Pos logit contributions
a+0.007
-+0.006
ah+0.006
be+0.006
ch+0.005
Neg logit contributions
 disl-0.007
ados-0.007
 vitamins-0.006
array-0.006
 Mickey-0.006
Token more
Token ID517
Feature activation-6.19e-02

Pos logit contributions
a+0.094
be+0.079
as+0.076
ah+0.074
fly+0.074
Neg logit contributions
 avocado-0.095
 disl-0.095
 vitamins-0.094
array-0.091
 Mickey-0.091
Token mis
Token ID2984
Feature activation-5.30e-01

Pos logit contributions
 disl+0.004
ados+0.004
 vitamins+0.004
array+0.004
 avocado+0.004
Neg logit contributions
a-0.004
ah-0.003
be-0.003
--0.003
ch-0.003
Tokenchie
Token ID3043
Feature activation+7.92e+00

Pos logit contributions
ados+0.043
 disl+0.043
array+0.041
 avocado+0.040
 av+0.040
Neg logit contributions
a-0.022
ah-0.018
--0.018
ch-0.015
less-0.015
Tokenvous
Token ID31222
Feature activation+2.61e+00

Pos logit contributions
a+0.510
fly+0.464
 closer+0.453
less+0.452
 steering+0.447
Neg logit contributions
 disl-0.428
 vitamins-0.369
array-0.365
 avocado-0.360
ados-0.353
Token mice
Token ID10693
Feature activation-2.07e+00

Pos logit contributions
a+0.167
ah+0.138
be+0.137
-+0.136
fly+0.125
Neg logit contributions
 disl-0.169
ados-0.162
 vitamins-0.161
 avocado-0.156
array-0.156
Token could
Token ID714
Feature activation-1.33e-02

Pos logit contributions
 disl+0.156
ados+0.147
 Mickey+0.146
 vitamins+0.146
 Bruce+0.143
Neg logit contributions
a-0.103
ah-0.088
--0.086
be-0.084
ch-0.078
Token come
Token ID1282
Feature activation+2.87e+00

Pos logit contributions
 disl+0.001
ados+0.001
 vitamins+0.001
array+0.001
 Mickey+0.001
Neg logit contributions
a-0.001
--0.001
ah-0.001
be-0.001
ch-0.001
Token in
Token ID287
Feature activation-2.23e-01

Pos logit contributions
a+0.143
ah+0.129
be+0.115
-+0.108
ch+0.107
Neg logit contributions
 Mickey-0.208
 disl-0.208
ados-0.203
 Bruce-0.197
 avocado-0.195
Token,
Token ID11
Feature activation-4.39e-01

Pos logit contributions
ados+0.055
 disl+0.055
 avocado+0.052
 vitamins+0.051
 av+0.050
Neg logit contributions
a-0.049
ah-0.043
be-0.042
fly-0.041
mer-0.041
Token "
Token ID366
Feature activation+2.46e+00

Pos logit contributions
 disl+0.022
ados+0.021
 Mickey+0.020
 avocado+0.019
 Bruce+0.019
Neg logit contributions
a-0.034
ah-0.030
--0.029
iest-0.029
be-0.028
TokenI
Token ID40
Feature activation-5.33e-01

Pos logit contributions
a+0.185
-+0.172
ah+0.159
less+0.155
fly+0.154
Neg logit contributions
 disl-0.128
 vitamins-0.113
ados-0.111
array-0.110
 Mickey-0.103
Token am
Token ID716
Feature activation+1.76e+00

Pos logit contributions
 disl+0.029
 vitamins+0.024
 earn+0.022
 court+0.021
array+0.021
Neg logit contributions
web-0.033
fly-0.032
a-0.031
king-0.030
leon-0.029
Token the
Token ID262
Feature activation-3.24e-01

Pos logit contributions
a+0.115
ah+0.104
-+0.102
be+0.099
y+0.097
Neg logit contributions
 disl-0.104
 Mickey-0.100
ados-0.097
 avocado-0.095
 Bruce-0.094
Token passenger
Token ID11849
Feature activation+7.90e+00

Pos logit contributions
 avocado+0.019
 vitamins+0.019
 court+0.019
 Mickey+0.018
 disl+0.018
Neg logit contributions
a-0.019
--0.019
y-0.017
less-0.017
ry-0.017
Token.
Token ID13
Feature activation+9.08e-02

Pos logit contributions
a+0.546
ch+0.517
less+0.509
vy+0.504
pr+0.493
Neg logit contributions
 court-0.284
 avocado-0.266
ados-0.252
 Everyone-0.251
 This-0.237
Token I
Token ID314
Feature activation-1.13e-01

Pos logit contributions
a+0.008
-+0.007
ah+0.007
be+0.007
y+0.006
Neg logit contributions
 disl-0.004
ados-0.004
 vitamins-0.004
 Mickey-0.004
array-0.003
Token look
Token ID804
Feature activation+1.61e+00

Pos logit contributions
 disl+0.007
 vitamins+0.006
 earn+0.005
 court+0.005
array+0.005
Neg logit contributions
a-0.006
fly-0.006
less-0.006
king-0.006
--0.006
Token out
Token ID503
Feature activation+6.87e-01

Pos logit contributions
a+0.095
fly+0.090
ah+0.089
be+0.084
web+0.080
Neg logit contributions
 disl-0.096
 avocado-0.096
 vitamins-0.094
 Bruce-0.093
ados-0.093
Token the
Token ID262
Feature activation-3.39e-01

Pos logit contributions
a+0.045
fly+0.043
ah+0.043
be+0.040
man+0.038
Neg logit contributions
ados-0.037
 avocado-0.036
 vitamins-0.036
 av-0.035
 oranges-0.034
Token driver
Token ID4639
Feature activation+3.55e+00

Pos logit contributions
 disl+0.015
ados+0.015
 vitamins+0.014
 avocado+0.014
 Mickey+0.014
Neg logit contributions
a-0.013
--0.012
ah-0.011
be-0.011
less-0.011
Token.
Token ID13
Feature activation+3.45e-01

Pos logit contributions
a+0.198
less+0.180
ah+0.179
 steering+0.179
 souven+0.177
Neg logit contributions
 avocado-0.196
 Mickey-0.180
 av-0.179
 disl-0.176
ados-0.173
Token I
Token ID314
Feature activation-1.03e-01

Pos logit contributions
a+0.025
-+0.023
ah+0.022
be+0.022
ch+0.021
Neg logit contributions
 disl-0.018
ados-0.018
array-0.017
 vitamins-0.017
 av-0.016
Token am
Token ID716
Feature activation+1.76e+00

Pos logit contributions
 disl+0.006
 vitamins+0.005
array+0.005
 Mickey+0.005
 Bruce+0.005
Neg logit contributions
a-0.006
--0.006
be-0.006
ah-0.005
less-0.005
Token the
Token ID262
Feature activation-2.29e-01

Pos logit contributions
a+0.108
ah+0.095
-+0.094
be+0.093
y+0.086
Neg logit contributions
 disl-0.114
 Mickey-0.108
ados-0.107
 avocado-0.105
 vitamins-0.105
Token passenger
Token ID11849
Feature activation+7.74e+00

Pos logit contributions
 disl+0.016
 avocado+0.015
 vitamins+0.015
ados+0.015
 Mickey+0.015
Neg logit contributions
a-0.013
--0.011
ah-0.010
be-0.010
less-0.010
Token.
Token ID13
Feature activation+3.58e-01

Pos logit contributions
a+0.494
ch+0.469
less+0.462
ah+0.451
fly+0.424
Neg logit contributions
 avocado-0.355
 court-0.355
ados-0.329
 disl-0.320
 Mickey-0.316
Token You
Token ID921
Feature activation-9.93e-01

Pos logit contributions
a+0.026
-+0.023
be+0.023
ah+0.023
ch+0.022
Neg logit contributions
 disl-0.019
ados-0.019
array-0.018
 vitamins-0.018
 avocado-0.017
Token have
Token ID423
Feature activation+1.63e+00

Pos logit contributions
 disl+0.062
 Mickey+0.058
 vitamins+0.057
ados+0.057
array+0.056
Neg logit contributions
a-0.061
--0.055
ah-0.053
be-0.051
less-0.051
Token to
Token ID284
Feature activation-1.23e-01

Pos logit contributions
a+0.092
ah+0.080
-+0.079
be+0.076
fly+0.072
Neg logit contributions
 disl-0.114
 vitamins-0.112
ados-0.110
array-0.106
 avocado-0.105
Token go
Token ID467
Feature activation+1.28e-01

Pos logit contributions
 disl+0.008
ados+0.008
 vitamins+0.007
array+0.007
 Mickey+0.007
Neg logit contributions
a-0.008
--0.007
ah-0.006
be-0.006
ch-0.006
Token sweet
Token ID6029
Feature activation-4.00e-03

Pos logit contributions
a+0.036
fly+0.034
ah+0.033
be+0.033
ilot+0.032
Neg logit contributions
 avocado-0.035
 court-0.035
 disl-0.034
 av-0.031
 Mickey-0.031
Token tune
Token ID14009
Feature activation+2.65e+00

Pos logit contributions
 avocado+0.000
 disl+0.000
ados+0.000
 Mickey+0.000
 av+0.000
Neg logit contributions
a-0.000
be-0.000
as-0.000
ah-0.000
 passenger-0.000
Token,
Token ID11
Feature activation-2.37e-01

Pos logit contributions
a+0.147
be+0.125
mer+0.123
vy+0.123
ah+0.123
Neg logit contributions
ados-0.163
 disl-0.155
 avocado-0.155
 Mickey-0.152
 herself-0.145
Token a
Token ID257
Feature activation+6.14e-01

Pos logit contributions
 disl+0.013
ados+0.013
 Mickey+0.012
 vitamins+0.012
array+0.012
Neg logit contributions
a-0.017
--0.015
be-0.015
ah-0.015
ch-0.014
Token mis
Token ID2984
Feature activation-7.36e-01

Pos logit contributions
a+0.036
ah+0.033
ac+0.031
z+0.031
as+0.030
Neg logit contributions
 avocado-0.036
 disl-0.035
 Mickey-0.035
 courtroom-0.034
 av-0.034
Tokenchie
Token ID3043
Feature activation+7.67e+00

Pos logit contributions
ados+0.060
 disl+0.060
array+0.059
 avocado+0.057
 Mickey+0.056
Neg logit contributions
a-0.024
--0.022
ah-0.021
ch-0.019
less-0.019
Tokenvous
Token ID31222
Feature activation+2.60e+00

Pos logit contributions
a+0.510
less+0.475
fly+0.464
 steering+0.462
 closer+0.457
Neg logit contributions
 disl-0.403
array-0.335
 vitamins-0.320
 avocado-0.314
iveness-0.304
Token fox
Token ID21831
Feature activation+9.25e-01

Pos logit contributions
a+0.152
be+0.123
as+0.120
z+0.119
-+0.113
Neg logit contributions
 disl-0.173
 avocado-0.173
 Mickey-0.166
ados-0.165
 Bruce-0.163
Token appeared
Token ID4120
Feature activation+2.38e+00

Pos logit contributions
a+0.048
ah+0.040
be+0.039
-+0.039
less+0.039
Neg logit contributions
 disl-0.063
 Mickey-0.062
ados-0.061
array-0.059
 av-0.059
Token.
Token ID13
Feature activation+3.04e-01

Pos logit contributions
a+0.118
be+0.105
ah+0.105
ch+0.092
 passenger+0.090
Neg logit contributions
ados-0.170
 Mickey-0.164
 av-0.164
 avocado-0.162
 Bruce-0.159
Token "
Token ID366
Feature activation+2.64e+00

Pos logit contributions
a+0.022
-+0.020
ah+0.019
ch+0.018
be+0.018
Neg logit contributions
 disl-0.016
 vitamins-0.016
ados-0.016
array-0.015
 avocado-0.014
Token
Token ID198
Feature activation-4.09e-01

Pos logit contributions
 disl+0.026
ados+0.026
 vitamins+0.025
array+0.024
 Mickey+0.024
Neg logit contributions
a-0.028
--0.024
ah-0.023
be-0.023
ch-0.022
TokenOne
Token ID3198
Feature activation+8.02e-01

Pos logit contributions
 disl+0.027
ados+0.026
 vitamins+0.025
array+0.025
 Mickey+0.024
Neg logit contributions
a-0.026
--0.023
ah-0.022
be-0.022
ch-0.020
Token day
Token ID1110
Feature activation+1.00e+00

Pos logit contributions
be+0.060
a+0.060
 steering+0.059
ist+0.059
cher+0.057
Neg logit contributions
 avocado-0.032
 Mickey-0.028
 Freddy-0.027
 disl-0.026
 broccoli-0.025
Token a
Token ID257
Feature activation+6.57e-01

Pos logit contributions
a+0.054
be+0.044
ah+0.043
-+0.041
fly+0.039
Neg logit contributions
ados-0.073
 Mickey-0.072
 disl-0.071
 avocado-0.070
 Bruce-0.070
Token mis
Token ID2984
Feature activation-7.31e-01

Pos logit contributions
a+0.041
ist+0.036
be+0.035
ah+0.035
as+0.035
Neg logit contributions
 Mickey-0.041
 avocado-0.039
 av-0.037
 disl-0.037
 Bruce-0.037
Tokenchie
Token ID3043
Feature activation+7.63e+00

Pos logit contributions
ados+0.061
 disl+0.060
 avocado+0.059
array+0.058
 vitamins+0.058
Neg logit contributions
a-0.024
--0.021
ah-0.019
ch-0.019
less-0.018
Tokenvous
Token ID31222
Feature activation+2.56e+00

Pos logit contributions
a+0.513
less+0.473
 closer+0.463
fly+0.462
 steering+0.461
Neg logit contributions
 disl-0.394
array-0.335
 vitamins-0.331
 avocado-0.322
ados-0.308
Token monkey
Token ID21657
Feature activation+1.16e+00

Pos logit contributions
a+0.147
be+0.121
-+0.113
as+0.109
z+0.109
Neg logit contributions
 disl-0.176
 Mickey-0.173
 avocado-0.173
ados-0.171
 av-0.165
Token saw
Token ID2497
Feature activation+1.07e+00

Pos logit contributions
a+0.058
be+0.048
-+0.048
ah+0.047
less+0.045
Neg logit contributions
 disl-0.085
ados-0.083
 Mickey-0.082
array-0.081
 avocado-0.080
Token the
Token ID262
Feature activation-8.83e-02

Pos logit contributions
a+0.047
-+0.043
ah+0.037
ch+0.034
 of+0.034
Neg logit contributions
 disl-0.089
array-0.086
 vitamins-0.086
ados-0.084
 courtroom-0.079
Token bear
Token ID6842
Feature activation+1.28e+00

Pos logit contributions
 disl+0.006
ados+0.006
 avocado+0.006
array+0.006
 vitamins+0.006
Neg logit contributions
a-0.005
--0.004
be-0.004
ah-0.004
ch-0.004
Token"
Token ID1
Feature activation+1.49e+00

Pos logit contributions
 disl+0.124
ados+0.122
array+0.121
 vitamins+0.119
 Mickey+0.114
Neg logit contributions
a-0.050
--0.043
ah-0.034
be-0.032
 of-0.031
TokenLet
Token ID5756
Feature activation+4.82e-01

Pos logit contributions
a+0.093
-+0.078
be+0.076
ah+0.075
ch+0.069
Neg logit contributions
 disl-0.100
ados-0.099
 vitamins-0.094
array-0.094
 Mickey-0.091
Token's
Token ID338
Feature activation-7.04e-01

Pos logit contributions
a+0.028
-+0.024
be+0.023
ah+0.023
ch+0.021
Neg logit contributions
 disl-0.034
ados-0.033
 vitamins-0.033
array-0.032
 Mickey-0.031
Token go
Token ID467
Feature activation-2.02e-01

Pos logit contributions
 disl+0.049
ados+0.048
 vitamins+0.047
array+0.046
 Mickey+0.044
Neg logit contributions
a-0.041
--0.036
be-0.034
ah-0.033
ch-0.031
Token,
Token ID11
Feature activation-3.54e-01

Pos logit contributions
 Bruce+0.012
 Mickey+0.012
 court+0.012
 disl+0.012
array+0.011
Neg logit contributions
a-0.012
ah-0.010
fly-0.009
web-0.009
as-0.009
Token mate
Token ID16133
Feature activation+7.62e+00

Pos logit contributions
 disl+0.018
ados+0.017
 Mickey+0.017
 avocado+0.016
 vitamins+0.016
Neg logit contributions
a-0.027
--0.025
ah-0.024
be-0.024
ch-0.023
Tokeny
Token ID88
Feature activation+3.71e+00

Pos logit contributions
ch+0.294
a+0.286
 spe+0.262
br+0.251
be+0.247
Neg logit contributions
 disl-0.562
ados-0.531
 vitamins-0.524
 avocado-0.507
 Freddy-0.505
Token!"
Token ID2474
Feature activation-2.96e+00

Pos logit contributions
a+0.205
ah+0.178
be+0.177
-+0.173
ch+0.165
Neg logit contributions
 disl-0.250
ados-0.240
 vitamins-0.239
 Mickey-0.237
 Bruce-0.230
Token Ben
Token ID3932
Feature activation-1.46e+00

Pos logit contributions
 disl+0.192
ados+0.183
 vitamins+0.181
array+0.181
 avocado+0.170
Neg logit contributions
a-0.192
--0.166
be-0.157
ah-0.157
ch-0.146
Token said
Token ID531
Feature activation-2.72e-02

Pos logit contributions
 disl+0.085
ados+0.083
array+0.078
 vitamins+0.078
 avocado+0.075
Neg logit contributions
a-0.106
--0.093
ah-0.089
be-0.089
ch-0.082
Token.
Token ID13
Feature activation+3.42e-02

Pos logit contributions
 disl+0.002
ados+0.002
 Mickey+0.002
 Bruce+0.002
 Freddy+0.002
Neg logit contributions
a-0.001
ah-0.001
be-0.001
ch-0.001
fly-0.001
Token and
Token ID290
Feature activation+2.37e-01

Pos logit contributions
a+0.095
ah+0.084
be+0.079
fly+0.076
-+0.075
Neg logit contributions
 disl-0.106
ados-0.103
array-0.098
 Mickey-0.098
 court-0.097
Token became
Token ID2627
Feature activation-4.22e-01

Pos logit contributions
a+0.014
-+0.012
ah+0.012
be+0.011
ch+0.011
Neg logit contributions
 disl-0.016
ados-0.016
array-0.015
 vitamins-0.015
 Mickey-0.015
Token a
Token ID257
Feature activation+6.44e-01

Pos logit contributions
 disl+0.028
ados+0.028
 Mickey+0.027
 vitamins+0.027
 avocado+0.026
Neg logit contributions
a-0.025
ah-0.022
--0.021
be-0.021
fly-0.020
Token great
Token ID1049
Feature activation+3.73e-01

Pos logit contributions
a+0.039
ah+0.036
fly+0.036
ist+0.035
iest+0.035
Neg logit contributions
 court-0.035
 disl-0.035
 courtroom-0.035
 Mickey-0.035
 avocado-0.034
Token violin
Token ID38283
Feature activation-1.31e+00

Pos logit contributions
a+0.023
fly+0.019
ah+0.019
be+0.019
ch+0.018
Neg logit contributions
 disl-0.023
 Mickey-0.022
 avocado-0.022
 court-0.022
array-0.022
Tokenist
Token ID396
Feature activation+7.62e+00

Pos logit contributions
ados+0.081
 court+0.081
 Mickey+0.080
 avocado+0.077
 av+0.075
Neg logit contributions
a-0.074
be-0.063
ah-0.062
fly-0.060
ba-0.058
Token.
Token ID13
Feature activation+4.11e-01

Pos logit contributions
a+0.493
be+0.422
ah+0.398
fly+0.395
ch+0.393
Neg logit contributions
 disl-0.475
ados-0.450
 avocado-0.412
 vitamins-0.411
array-0.410
Token<|endoftext|>
Token ID50256
Feature activation+1.43e+00

Pos logit contributions
a+0.021
 of+0.019
ah+0.018
-+0.017
ch+0.017
Neg logit contributions
 disl-0.030
 vitamins-0.029
array-0.029
ados-0.028
 av-0.027
TokenOnce
Token ID7454
Feature activation+5.76e-01

Pos logit contributions
a+0.098
-+0.087
ah+0.084
be+0.084
ch+0.078
Neg logit contributions
 disl-0.084
ados-0.081
 vitamins-0.078
array-0.077
 Mickey-0.076
Token upon
Token ID2402
Feature activation+1.54e+00

Pos logit contributions
a+0.022
-+0.018
be+0.017
ah+0.017
ch+0.015
Neg logit contributions
 disl-0.050
ados-0.049
 Mickey-0.048
 avocado-0.047
 vitamins-0.047
Token a
Token ID257
Feature activation+6.43e-01

Pos logit contributions
a+0.087
-+0.075
be+0.074
ah+0.074
fly+0.067
Neg logit contributions
 disl-0.106
ados-0.101
 vitamins-0.100
 avocado-0.100
 Mickey-0.099
TokenBut
Token ID1537
Feature activation+8.39e-01

Pos logit contributions
 disl+0.019
ados+0.018
 vitamins+0.018
array+0.018
 Mickey+0.017
Neg logit contributions
a-0.013
--0.011
be-0.011
ah-0.011
ch-0.010
Token then
Token ID788
Feature activation-8.11e-03

Pos logit contributions
a+0.049
be+0.042
-+0.042
ah+0.041
ch+0.039
Neg logit contributions
 disl-0.055
ados-0.055
 Mickey-0.055
 avocado-0.053
 Bruce-0.053
Token,
Token ID11
Feature activation-2.18e-01

Pos logit contributions
 disl+0.001
ados+0.001
 Mickey+0.001
array+0.001
 vitamins+0.001
Neg logit contributions
a-0.000
--0.000
be-0.000
ah-0.000
ch-0.000
Token a
Token ID257
Feature activation+6.30e-01

Pos logit contributions
 disl+0.013
ados+0.013
 Mickey+0.013
 avocado+0.013
 Bruce+0.012
Neg logit contributions
a-0.014
be-0.012
ah-0.012
--0.012
ch-0.011
Token mis
Token ID2984
Feature activation-6.90e-01

Pos logit contributions
a+0.040
ah+0.035
z+0.035
ba+0.034
be+0.034
Neg logit contributions
 avocado-0.037
 av-0.036
 Mickey-0.035
 disl-0.035
 courtroom-0.035
Tokenchie
Token ID3043
Feature activation+7.62e+00

Pos logit contributions
ados+0.053
 disl+0.053
array+0.051
 avocado+0.051
 courtroom+0.050
Neg logit contributions
a-0.024
--0.022
ah-0.022
ch-0.021
man-0.020
Tokenvous
Token ID31222
Feature activation+2.59e+00

Pos logit contributions
a+0.509
less+0.476
 steering+0.470
fly+0.455
 passenger+0.454
Neg logit contributions
 disl-0.394
array-0.324
 avocado-0.310
 vitamins-0.307
iveness-0.297
Token rabbit
Token ID22746
Feature activation+5.18e-01

Pos logit contributions
a+0.149
be+0.125
z+0.117
-+0.115
as+0.113
Neg logit contributions
 disl-0.176
 avocado-0.171
ados-0.167
 Mickey-0.166
 Bruce-0.164
Token came
Token ID1625
Feature activation+1.75e+00

Pos logit contributions
a+0.027
be+0.023
-+0.022
ah+0.022
less+0.021
Neg logit contributions
 Mickey-0.037
ados-0.035
 disl-0.035
 Bruce-0.035
 Freddy-0.034
Token and
Token ID290
Feature activation+2.56e-01

Pos logit contributions
a+0.091
ah+0.082
be+0.078
iest+0.076
ber+0.073
Neg logit contributions
ados-0.113
 Mickey-0.113
 Bruce-0.109
 disl-0.108
 Freddy-0.107
Token started
Token ID2067
Feature activation-6.65e-03

Pos logit contributions
a+0.016
-+0.014
ah+0.013
be+0.013
ch+0.012
Neg logit contributions
 disl-0.017
ados-0.017
 vitamins-0.016
array-0.016
 Mickey-0.016
Token finally
Token ID3443
Feature activation+2.23e+00

Pos logit contributions
a+0.044
-+0.037
be+0.036
ah+0.036
ch+0.033
Neg logit contributions
 disl-0.058
ados-0.056
 Mickey-0.054
array-0.054
 vitamins-0.053
Token,
Token ID11
Feature activation+1.97e-01

Pos logit contributions
a+0.096
-+0.080
ah+0.075
be+0.072
ch+0.065
Neg logit contributions
 disl-0.190
ados-0.186
 vitamins-0.183
array-0.180
 Mickey-0.177
Token the
Token ID262
Feature activation+3.82e-01

Pos logit contributions
a+0.012
-+0.011
ah+0.010
be+0.010
ch+0.010
Neg logit contributions
 disl-0.013
ados-0.012
 vitamins-0.012
array-0.012
 Mickey-0.012
Token z
Token ID1976
Feature activation+1.73e+00

Pos logit contributions
a+0.022
-+0.019
ah+0.018
be+0.018
ch+0.016
Neg logit contributions
 disl-0.026
ados-0.025
 avocado-0.025
 vitamins-0.025
 Mickey-0.024
Tokenig
Token ID328
Feature activation+5.68e+00

Pos logit contributions
a+0.079
 closer+0.075
less+0.074
y+0.074
fly+0.073
Neg logit contributions
ados-0.102
 disl-0.102
 court-0.101
 courtroom-0.097
azes-0.095
Tokenzag
Token ID50183
Feature activation+7.61e+00

Pos logit contributions
a+0.283
ah+0.239
ch+0.238
be+0.237
-+0.232
Neg logit contributions
 disl-0.391
ados-0.367
array-0.353
 Mickey-0.348
 avocado-0.346
Token had
Token ID550
Feature activation+8.16e-01

Pos logit contributions
a+0.418
ah+0.351
-+0.346
less+0.338
be+0.338
Neg logit contributions
 disl-0.512
ados-0.471
array-0.467
 vitamins-0.459
 avocado-0.456
Token an
Token ID281
Feature activation-3.80e-01

Pos logit contributions
a+0.045
-+0.039
be+0.037
ah+0.037
ch+0.033
Neg logit contributions
 disl-0.059
ados-0.058
array-0.055
 vitamins-0.055
 Mickey-0.055
Token idea
Token ID2126
Feature activation-5.48e-01

Pos logit contributions
 disl+0.024
ados+0.023
 vitamins+0.022
array+0.022
 Mickey+0.022
Neg logit contributions
a-0.024
--0.022
ah-0.021
be-0.021
ch-0.019
Token.
Token ID13
Feature activation+5.32e-01

Pos logit contributions
 disl+0.036
ados+0.034
 court+0.033
 vitamins+0.033
 Mickey+0.033
Neg logit contributions
a-0.032
ah-0.028
be-0.027
ch-0.027
fly-0.025
Token It
Token ID632
Feature activation+8.94e-01

Pos logit contributions
a+0.039
-+0.033
be+0.033
ah+0.033
ch+0.031
Neg logit contributions
 disl-0.029
 vitamins-0.028
ados-0.028
array-0.027
 avocado-0.026
Token to
Token ID284
Feature activation-3.50e-01

Pos logit contributions
a+0.011
-+0.009
be+0.009
ah+0.008
ch+0.008
Neg logit contributions
 disl-0.024
ados-0.024
array-0.023
 vitamins-0.023
 Mickey-0.022
Token see
Token ID766
Feature activation+1.49e+00

Pos logit contributions
 disl+0.025
ados+0.024
 vitamins+0.023
array+0.023
 Mickey+0.023
Neg logit contributions
a-0.020
--0.017
ah-0.017
be-0.017
ch-0.015
Token the
Token ID262
Feature activation-1.98e-01

Pos logit contributions
a+0.091
-+0.078
ah+0.077
be+0.077
ch+0.070
Neg logit contributions
 disl-0.099
ados-0.097
 vitamins-0.093
 Mickey-0.092
array-0.091
Token graceful
Token ID44363
Feature activation+1.32e-02

Pos logit contributions
 disl+0.012
 vitamins+0.012
ados+0.012
 avocado+0.012
 av+0.011
Neg logit contributions
a-0.012
--0.011
ah-0.011
be-0.011
ch-0.010
Token violin
Token ID38283
Feature activation-1.25e+00

Pos logit contributions
a+0.001
be+0.001
ah+0.001
less+0.001
-+0.001
Neg logit contributions
 disl-0.001
ados-0.001
 avocado-0.001
 vitamins-0.001
array-0.001
Tokenist
Token ID396
Feature activation+7.60e+00

Pos logit contributions
ados+0.080
 avocado+0.078
 disl+0.078
 vitamins+0.076
 Mickey+0.076
Neg logit contributions
a-0.071
ah-0.062
be-0.061
less-0.057
--0.057
Token."
Token ID526
Feature activation-1.53e+00

Pos logit contributions
a+0.427
be+0.355
-+0.349
ah+0.341
less+0.323
Neg logit contributions
 disl-0.547
ados-0.515
 vitamins-0.489
 avocado-0.481
array-0.478
Token
Token ID198
Feature activation-6.02e-01

Pos logit contributions
 vitamins+0.103
 disl+0.103
array+0.100
ados+0.097
 avocado+0.091
Neg logit contributions
a-0.092
--0.080
be-0.075
ah-0.075
fly-0.070
Token
Token ID198
Feature activation-5.73e-01

Pos logit contributions
 disl+0.040
ados+0.040
 vitamins+0.039
array+0.038
 avocado+0.036
Neg logit contributions
a-0.038
--0.033
be-0.031
ah-0.031
ch-0.029
TokenThey
Token ID2990
Feature activation+4.43e-01

Pos logit contributions
 disl+0.040
ados+0.038
 Mickey+0.037
array+0.036
 vitamins+0.036
Neg logit contributions
a-0.032
--0.029
ah-0.028
be-0.027
less-0.026
Token went
Token ID1816
Feature activation-1.72e+00

Pos logit contributions
a+0.029
-+0.026
be+0.025
ah+0.025
ch+0.024
Neg logit contributions
 disl-0.026
ados-0.025
 Mickey-0.025
array-0.024
 vitamins-0.024
Token saw
Token ID2497
Feature activation+1.17e+00

Pos logit contributions
a+0.050
-+0.043
ah+0.042
be+0.041
ch+0.038
Neg logit contributions
 disl-0.068
ados-0.066
array-0.064
 vitamins-0.064
 Mickey-0.063
Token something
Token ID1223
Feature activation-1.27e+00

Pos logit contributions
a+0.060
-+0.051
ah+0.047
be+0.046
ch+0.043
Neg logit contributions
 disl-0.090
ados-0.089
 vitamins-0.086
array-0.085
 Mickey-0.083
Token shiny
Token ID22441
Feature activation-2.14e+00

Pos logit contributions
 disl+0.080
 avocado+0.077
 Mickey+0.076
ados+0.076
 vitamins+0.075
Neg logit contributions
a-0.078
ah-0.069
be-0.069
--0.063
 passenger-0.061
Token and
Token ID290
Feature activation+1.88e-01

Pos logit contributions
ados+0.177
 avocado+0.176
 av+0.171
 vitamins+0.167
 Mickey+0.164
Neg logit contributions
a-0.096
be-0.078
ah-0.071
ch-0.066
as-0.065
Token gl
Token ID1278
Feature activation+1.00e+00

Pos logit contributions
a+0.010
-+0.009
ah+0.008
be+0.008
ch+0.007
Neg logit contributions
 disl-0.014
ados-0.014
 vitamins-0.013
array-0.013
 Mickey-0.013
Tokenist
Token ID396
Feature activation+7.60e+00

Pos logit contributions
a+0.052
ch+0.049
be+0.048
ah+0.046
 plane+0.046
Neg logit contributions
 disl-0.062
ados-0.060
 av-0.055
array-0.055
 Bruce-0.055
Tokenening
Token ID3101
Feature activation+1.20e+00

Pos logit contributions
a+0.555
-+0.474
be+0.474
ah+0.469
ch+0.448
Neg logit contributions
 disl-0.412
ados-0.399
 vitamins-0.375
array-0.373
 avocado-0.370
Token on
Token ID319
Feature activation+4.96e-01

Pos logit contributions
a+0.051
be+0.041
ah+0.041
ch+0.035
-+0.035
Neg logit contributions
ados-0.101
 avocado-0.098
 av-0.096
 vitamins-0.096
 disl-0.096
Token the
Token ID262
Feature activation-1.14e-01

Pos logit contributions
a+0.027
-+0.024
ah+0.023
be+0.022
ch+0.020
Neg logit contributions
 disl-0.037
ados-0.035
array-0.034
 vitamins-0.034
 Mickey-0.033
Token ground
Token ID2323
Feature activation-3.45e+00

Pos logit contributions
 disl+0.005
ados+0.005
 vitamins+0.004
 avocado+0.004
array+0.004
Neg logit contributions
a-0.010
--0.009
ah-0.009
be-0.009
ch-0.008
Token -
Token ID532
Feature activation-1.05e+00

Pos logit contributions
ados+0.247
 disl+0.243
 avocado+0.239
array+0.237
 Mickey+0.236
Neg logit contributions
a-0.180
ah-0.150
be-0.148
--0.144
ch-0.134
Token.
Token ID13
Feature activation+2.52e-01

Pos logit contributions
ados+0.358
 disl+0.352
 vitamins+0.345
 avocado+0.344
 Mickey+0.341
Neg logit contributions
a-0.163
ah-0.125
be-0.122
--0.122
ch-0.107
Token Mom
Token ID11254
Feature activation+3.08e-01

Pos logit contributions
a+0.016
-+0.016
 of+0.014
y+0.013
 in+0.013
Neg logit contributions
 disl-0.016
array-0.014
 Mickey-0.014
Mic-0.014
handed-0.013
Token says
Token ID1139
Feature activation-8.26e-01

Pos logit contributions
a+0.023
-+0.021
ah+0.020
be+0.020
y+0.019
Neg logit contributions
 disl-0.017
ados-0.016
 vitamins-0.015
array-0.015
 Mickey-0.015
Token they
Token ID484
Feature activation+4.04e-01

Pos logit contributions
ados+0.065
 disl+0.064
 vitamins+0.063
 avocado+0.062
 Mickey+0.062
Neg logit contributions
a-0.040
ah-0.033
--0.033
be-0.032
ch-0.029
Token are
Token ID389
Feature activation+1.29e+00

Pos logit contributions
a+0.015
be+0.012
-+0.012
ah+0.011
 closer+0.010
Neg logit contributions
 disl-0.037
ados-0.036
array-0.035
 vitamins-0.034
 Mickey-0.033
Token av
Token ID1196
Feature activation-5.91e+00

Pos logit contributions
a+0.080
-+0.070
be+0.066
ah+0.065
ch+0.061
Neg logit contributions
 disl-0.087
ados-0.083
array-0.081
 vitamins-0.080
 Mickey-0.078
Tokenoc
Token ID420
Feature activation+5.22e-01

Pos logit contributions
ados+0.418
 disl+0.414
 vitamins+0.400
 Mickey+0.397
array+0.394
Neg logit contributions
a-0.323
--0.267
ah-0.262
be-0.261
ch-0.244
Tokenados
Token ID22484
Feature activation-5.81e+00

Pos logit contributions
-+0.055
a+0.053
ah+0.050
be+0.049
man+0.048
Neg logit contributions
 disl-0.010
array-0.009
 mischief-0.007
 vitamins-0.007
 Mickey-0.006
Token.
Token ID13
Feature activation+2.50e-01

Pos logit contributions
ados+0.415
 Mickey+0.404
 disl+0.401
 avocado+0.400
 vitamins+0.399
Neg logit contributions
a-0.292
ah-0.264
be-0.263
ch-0.246
--0.239
Token Sara
Token ID24799
Feature activation+1.23e+00

Pos logit contributions
a+0.013
-+0.011
 of+0.011
be+0.010
 closer+0.010
Neg logit contributions
 disl-0.019
array-0.018
 Mickey-0.018
ados-0.017
 vitamins-0.017
Token wants
Token ID3382
Feature activation-2.77e+00

Pos logit contributions
a+0.075
-+0.066
be+0.058
ah+0.058
y+0.055
Neg logit contributions
 disl-0.089
ados-0.088
 Mickey-0.083
 Bruce-0.081
array-0.081
Token.
Token ID13
Feature activation+3.09e-01

Pos logit contributions
 disl+0.093
 Mickey+0.088
 avocado+0.087
ados+0.087
array+0.087
Neg logit contributions
a-0.060
ah-0.051
be-0.050
ch-0.048
--0.048
Token Lily
Token ID20037
Feature activation-1.22e+00

Pos logit contributions
a+0.023
 of+0.022
y+0.021
-+0.021
ch+0.020
Neg logit contributions
 disl-0.017
ados-0.015
handed-0.014
array-0.014
 courtroom-0.014
Token loved
Token ID6151
Feature activation-9.92e-01

Pos logit contributions
ados+0.094
 disl+0.093
 vitamins+0.088
array+0.087
 Mickey+0.086
Neg logit contributions
a-0.065
--0.057
be-0.051
ah-0.051
y-0.047
Token to
Token ID284
Feature activation-5.81e-02

Pos logit contributions
 disl+0.098
array+0.094
 Bruce+0.092
ados+0.092
handed+0.092
Neg logit contributions
--0.024
a-0.021
be-0.017
ch-0.017
 on-0.014
Token eat
Token ID4483
Feature activation-1.27e+00

Pos logit contributions
ados+0.004
 disl+0.004
 vitamins+0.004
array+0.004
 Mickey+0.004
Neg logit contributions
a-0.003
--0.003
ah-0.003
be-0.003
ch-0.003
Token av
Token ID1196
Feature activation-5.87e+00

Pos logit contributions
 disl+0.079
array+0.071
 courtroom+0.069
handed+0.066
 weaknesses+0.066
Neg logit contributions
--0.089
a-0.079
 on-0.073
 of-0.071
 in-0.069
Tokenoc
Token ID420
Feature activation+6.52e-01

Pos logit contributions
 disl+0.505
array+0.467
ados+0.461
 vitamins+0.461
 Bruce+0.452
Neg logit contributions
a-0.258
--0.243
ah-0.215
be-0.206
ch-0.187
Tokenados
Token ID22484
Feature activation-5.76e+00

Pos logit contributions
-+0.059
rot+0.045
be+0.043
man+0.043
a+0.043
Neg logit contributions
 disl-0.024
array-0.024
 mischief-0.021
 vitamins-0.020
 Afterwards-0.019
Token,
Token ID11
Feature activation-4.28e-01

Pos logit contributions
 disl+0.489
ados+0.475
 vitamins+0.462
array+0.461
 Mickey+0.455
Neg logit contributions
a-0.249
--0.204
ah-0.192
be-0.191
ch-0.169
Token they
Token ID484
Feature activation+5.02e-01

Pos logit contributions
 disl+0.035
array+0.033
ados+0.032
 vitamins+0.031
iveness+0.031
Neg logit contributions
a-0.019
--0.017
 of-0.016
be-0.016
ah-0.016
Token were
Token ID547
Feature activation-1.51e-01

Pos logit contributions
a+0.023
-+0.019
be+0.019
ah+0.019
y+0.017
Neg logit contributions
 disl-0.043
ados-0.040
array-0.040
 vitamins-0.038
 Mickey-0.037
Token Maybe
Token ID6674
Feature activation-9.37e-01

Pos logit contributions
a+0.023
-+0.021
be+0.020
ah+0.020
ch+0.019
Neg logit contributions
ados-0.012
 disl-0.012
array-0.011
 vitamins-0.011
 avocado-0.010
Token they
Token ID484
Feature activation+4.64e-01

Pos logit contributions
 disl+0.061
ados+0.059
 vitamins+0.058
 Mickey+0.057
 avocado+0.057
Neg logit contributions
a-0.058
ah-0.051
be-0.050
--0.049
ch-0.046
Token could
Token ID714
Feature activation-1.98e-01

Pos logit contributions
a+0.022
-+0.018
ah+0.017
be+0.017
ch+0.016
Neg logit contributions
 disl-0.037
ados-0.036
 vitamins-0.035
 Mickey-0.035
array-0.034
Token grow
Token ID1663
Feature activation-5.80e-01

Pos logit contributions
ados+0.013
 disl+0.013
array+0.013
 vitamins+0.013
 courtroom+0.012
Neg logit contributions
a-0.012
--0.010
be-0.010
ah-0.009
 closer-0.009
Token more
Token ID517
Feature activation-6.73e-02

Pos logit contributions
 avocado+0.039
 av+0.039
ados+0.039
 vitamins+0.039
 disl+0.038
Neg logit contributions
a-0.033
ah-0.031
be-0.029
 passenger-0.026
ch-0.026
Token av
Token ID1196
Feature activation-5.86e+00

Pos logit contributions
 disl+0.004
array+0.004
ados+0.004
 Mickey+0.004
 vitamins+0.004
Neg logit contributions
a-0.004
--0.004
be-0.004
 of-0.004
ah-0.004
Tokenoc
Token ID420
Feature activation+5.95e-01

Pos logit contributions
 disl+0.458
ados+0.443
 vitamins+0.431
array+0.429
 Mickey+0.423
Neg logit contributions
a-0.293
--0.249
ah-0.236
be-0.235
ch-0.212
Tokenados
Token ID22484
Feature activation-5.74e+00

Pos logit contributions
-+0.064
a+0.059
be+0.056
ah+0.056
less+0.054
Neg logit contributions
array-0.012
 disl-0.012
 mischief-0.009
 Mickey-0.008
 vitamins-0.008
Token and
Token ID290
Feature activation+2.80e-01

Pos logit contributions
ados+0.421
 avocado+0.416
 disl+0.413
 av+0.413
 Mickey+0.407
Neg logit contributions
a-0.280
ah-0.251
be-0.232
--0.222
ch-0.219
Token share
Token ID2648
Feature activation-1.52e+00

Pos logit contributions
a+0.016
-+0.014
be+0.014
ah+0.013
 closer+0.013
Neg logit contributions
 disl-0.019
ados-0.019
array-0.018
 vitamins-0.017
 Mickey-0.017
Token them
Token ID606
Feature activation-3.64e-01

Pos logit contributions
 disl+0.109
ados+0.106
array+0.104
 vitamins+0.103
 Mickey+0.101
Neg logit contributions
a-0.084
--0.073
be-0.068
ah-0.067
ch-0.062
Token but
Token ID475
Feature activation+1.80e+00

Pos logit contributions
 disl+0.022
ados+0.022
 vitamins+0.021
array+0.021
 Mickey+0.020
Neg logit contributions
a-0.023
--0.020
ah-0.019
be-0.019
ch-0.018
Token there
Token ID612
Feature activation+4.05e-01

Pos logit contributions
a+0.109
-+0.094
ah+0.091
be+0.090
ch+0.083
Neg logit contributions
 disl-0.122
ados-0.118
 vitamins-0.114
array-0.114
 Mickey-0.112
Token were
Token ID547
Feature activation-6.91e-02

Pos logit contributions
a+0.022
-+0.018
ah+0.018
be+0.018
ch+0.016
Neg logit contributions
 disl-0.029
ados-0.029
 vitamins-0.028
 Mickey-0.028
array-0.028
Token no
Token ID645
Feature activation+1.61e+00

Pos logit contributions
 disl+0.004
 vitamins+0.004
ados+0.004
 avocado+0.004
 Mickey+0.004
Neg logit contributions
a-0.004
--0.004
ah-0.004
be-0.004
ch-0.003
Token other
Token ID584
Feature activation-1.10e+00

Pos logit contributions
a+0.091
-+0.086
be+0.077
ah+0.077
 of+0.073
Neg logit contributions
 disl-0.115
ados-0.106
array-0.105
 Mickey-0.103
 vitamins-0.101
Token av
Token ID1196
Feature activation-5.86e+00

Pos logit contributions
 disl+0.070
array+0.067
ados+0.066
 Mickey+0.065
 vitamins+0.063
Neg logit contributions
a-0.068
--0.063
be-0.057
ah-0.056
 of-0.054
Tokenoc
Token ID420
Feature activation+6.01e-01

Pos logit contributions
 disl+0.444
ados+0.434
 vitamins+0.419
array+0.417
 Mickey+0.413
Neg logit contributions
a-0.304
--0.256
ah-0.246
be-0.244
ch-0.222
Tokenados
Token ID22484
Feature activation-5.74e+00

Pos logit contributions
-+0.061
a+0.055
be+0.054
ah+0.054
less+0.052
Neg logit contributions
 disl-0.014
array-0.013
 mischief-0.010
 vitamins-0.010
 Mickey-0.009
Token.
Token ID13
Feature activation+3.83e-01

Pos logit contributions
 disl+0.460
ados+0.456
 vitamins+0.442
 Mickey+0.437
array+0.435
Neg logit contributions
a-0.264
ah-0.216
--0.213
be-0.209
ch-0.191
Token
Token ID198
Feature activation-2.32e-01

Pos logit contributions
a+0.022
be+0.020
 of+0.020
-+0.019
ch+0.019
Neg logit contributions
 disl-0.026
 vitamins-0.024
ados-0.023
array-0.022
 avocado-0.022
Token
Token ID198
Feature activation-2.16e-01

Pos logit contributions
 disl+0.015
ados+0.015
 vitamins+0.014
array+0.014
 avocado+0.014
Neg logit contributions
a-0.015
--0.013
be-0.012
ah-0.012
ch-0.012
Token before
Token ID878
Feature activation-1.83e+00

Pos logit contributions
a+0.116
-+0.096
ah+0.093
be+0.093
ch+0.085
Neg logit contributions
 disl-0.180
ados-0.175
 vitamins-0.172
array-0.169
 Mickey-0.167
Token.
Token ID13
Feature activation+3.61e-01

Pos logit contributions
 disl+0.172
ados+0.164
array+0.161
 vitamins+0.160
 Mickey+0.156
Neg logit contributions
a-0.061
--0.054
be-0.045
ah-0.041
y-0.037
Token
Token ID198
Feature activation-2.09e-01

Pos logit contributions
a+0.022
ah+0.019
 of+0.019
-+0.019
be+0.018
Neg logit contributions
 disl-0.024
array-0.023
ados-0.022
 vitamins-0.022
 avocado-0.020
Token
Token ID198
Feature activation-2.06e-01

Pos logit contributions
 disl+0.014
ados+0.014
array+0.013
 vitamins+0.013
 Mickey+0.013
Neg logit contributions
a-0.013
--0.011
ah-0.011
be-0.011
ch-0.010
TokenThe
Token ID464
Feature activation+6.31e-01

Pos logit contributions
 disl+0.014
ados+0.013
 vitamins+0.013
 Mickey+0.013
 avocado+0.012
Neg logit contributions
a-0.012
--0.011
ah-0.010
be-0.010
less-0.010
Token av
Token ID1196
Feature activation-5.85e+00

Pos logit contributions
a+0.034
-+0.034
be+0.029
ah+0.029
 of+0.029
Neg logit contributions
 disl-0.044
array-0.043
 vitamins-0.039
ados-0.038
 Bruce-0.035
Tokenoc
Token ID420
Feature activation+7.06e-01

Pos logit contributions
 disl+0.447
ados+0.436
 vitamins+0.422
array+0.419
 Mickey+0.416
Neg logit contributions
a-0.300
--0.252
ah-0.241
be-0.240
ch-0.218
Tokenados
Token ID22484
Feature activation-5.75e+00

Pos logit contributions
-+0.073
a+0.067
man+0.067
fly+0.065
ah+0.065
Neg logit contributions
array-0.016
 disl-0.014
 vitamins-0.014
 mischief-0.013
 Mickey-0.009
Token were
Token ID547
Feature activation-6.46e-02

Pos logit contributions
 disl+0.361
ados+0.357
 avocado+0.346
 Mickey+0.345
 vitamins+0.340
Neg logit contributions
a-0.353
--0.304
ah-0.297
be-0.291
ch-0.288
Token shared
Token ID4888
Feature activation-8.03e-01

Pos logit contributions
 disl+0.004
ados+0.004
 vitamins+0.004
 avocado+0.004
 Mickey+0.004
Neg logit contributions
a-0.004
--0.003
ah-0.003
be-0.003
ch-0.003
Token with
Token ID351
Feature activation-1.78e+00

Pos logit contributions
 disl+0.069
ados+0.067
 vitamins+0.065
array+0.065
 Mickey+0.064
Neg logit contributions
a-0.034
--0.028
ah-0.026
be-0.026
ch-0.023
Token so
Token ID523
Feature activation-1.36e+00

Pos logit contributions
 Mickey+0.023
array+0.023
 avocado+0.023
 disl+0.023
 Bruce+0.022
Neg logit contributions
a-0.026
ah-0.025
--0.023
ch-0.023
iest-0.023
Token happy
Token ID3772
Feature activation+4.92e-01

Pos logit contributions
 disl+0.098
ados+0.093
 vitamins+0.090
array+0.090
 Mickey+0.089
Neg logit contributions
a-0.074
ah-0.065
--0.064
be-0.062
ch-0.058
Token to
Token ID284
Feature activation-1.21e-01

Pos logit contributions
a+0.026
ah+0.022
be+0.021
ch+0.019
 passenger+0.019
Neg logit contributions
 disl-0.038
ados-0.037
array-0.035
 Mickey-0.035
 avocado-0.034
Token have
Token ID423
Feature activation+1.72e+00

Pos logit contributions
 disl+0.008
ados+0.008
 vitamins+0.008
array+0.008
 Mickey+0.008
Neg logit contributions
a-0.007
--0.006
be-0.006
ah-0.006
ch-0.005
Token her
Token ID607
Feature activation+9.84e-03

Pos logit contributions
a+0.110
-+0.098
be+0.092
ah+0.092
ch+0.086
Neg logit contributions
 disl-0.111
ados-0.107
 vitamins-0.103
array-0.102
 avocado-0.099
Token av
Token ID1196
Feature activation-5.85e+00

Pos logit contributions
-+0.001
a+0.001
be+0.001
ah+0.001
 of+0.001
Neg logit contributions
 disl-0.001
array-0.001
 vitamins-0.001
iveness-0.000
ados-0.000
Tokenoc
Token ID420
Feature activation+7.30e-01

Pos logit contributions
 disl+0.447
ados+0.436
 vitamins+0.422
array+0.419
 Mickey+0.415
Neg logit contributions
a-0.300
--0.253
ah-0.242
be-0.241
ch-0.219
Tokenados
Token ID22484
Feature activation-5.72e+00

Pos logit contributions
-+0.076
man+0.068
a+0.068
ah+0.067
be+0.066
Neg logit contributions
 disl-0.016
array-0.015
 vitamins-0.013
 mischief-0.013
 Bruce-0.011
Token.
Token ID13
Feature activation+2.74e-01

Pos logit contributions
ados+0.400
 avocado+0.398
 av+0.395
 Mickey+0.393
 court+0.391
Neg logit contributions
a-0.310
ah-0.272
be-0.270
ch-0.260
--0.234
Token She
Token ID1375
Feature activation-4.82e-01

Pos logit contributions
-+0.012
 and+0.011
 to+0.010
 of+0.010
 too+0.010
Neg logit contributions
affles-0.019
 disl-0.019
 vitamins-0.019
handed-0.018
ados-0.018
Token thanked
Token ID26280
Feature activation-1.31e+00

Pos logit contributions
ados+0.037
 disl+0.036
array+0.034
 vitamins+0.034
iveness+0.032
Neg logit contributions
a-0.027
--0.024
ah-0.021
be-0.021
ch-0.019
Token
Token ID198
Feature activation-2.45e-01

Pos logit contributions
a+0.021
 of+0.019
ch+0.017
be+0.017
-+0.017
Neg logit contributions
 disl-0.024
 vitamins-0.023
array-0.022
ados-0.021
 av-0.020
Token
Token ID198
Feature activation-2.37e-01

Pos logit contributions
 disl+0.017
ados+0.017
 vitamins+0.017
array+0.016
 avocado+0.016
Neg logit contributions
a-0.015
--0.013
be-0.012
ah-0.012
ch-0.011
TokenAt
Token ID2953
Feature activation+1.04e+00

Pos logit contributions
 disl+0.017
ados+0.016
 vitamins+0.016
array+0.016
 Mickey+0.016
Neg logit contributions
a-0.013
--0.012
ah-0.011
be-0.011
fly-0.010
Token the
Token ID262
Feature activation-1.06e-01

Pos logit contributions
a+0.064
-+0.055
be+0.054
ah+0.053
ch+0.049
Neg logit contributions
ados-0.067
 disl-0.066
 Mickey-0.066
 avocado-0.064
 Bruce-0.064
Token or
Token ID393
Feature activation-9.34e-01

Pos logit contributions
 disl+0.008
ados+0.008
 vitamins+0.008
array+0.007
 Mickey+0.007
Neg logit contributions
a-0.006
--0.005
ah-0.005
be-0.005
ch-0.004
Tokenchard
Token ID30215
Feature activation-5.85e+00

Pos logit contributions
 disl+0.034
ados+0.033
 Mickey+0.030
 vitamins+0.030
array+0.030
Neg logit contributions
a-0.084
--0.077
ah-0.076
be-0.075
ch-0.072
Token,
Token ID11
Feature activation-3.08e-01

Pos logit contributions
 disl+0.465
ados+0.455
 Mickey+0.444
array+0.441
 vitamins+0.438
Neg logit contributions
a-0.268
--0.221
ah-0.217
be-0.213
ch-0.201
Token they
Token ID484
Feature activation+6.31e-01

Pos logit contributions
ados+0.020
 Mickey+0.019
 disl+0.019
 avocado+0.019
 Bruce+0.019
Neg logit contributions
a-0.019
ah-0.017
be-0.017
--0.016
ch-0.015
Token picked
Token ID6497
Feature activation-1.60e+00

Pos logit contributions
a+0.038
-+0.033
ah+0.032
be+0.032
ch+0.030
Neg logit contributions
 disl-0.042
ados-0.041
 vitamins-0.039
array-0.039
 Mickey-0.039
Token as
Token ID355
Feature activation-8.15e-01

Pos logit contributions
 disl+0.123
array+0.116
 vitamins+0.108
ados+0.105
 courtroom+0.104
Neg logit contributions
a-0.089
--0.082
ah-0.071
 closer-0.070
y-0.066
Token many
Token ID867
Feature activation-1.65e+00

Pos logit contributions
 disl+0.042
ados+0.041
 vitamins+0.040
 avocado+0.039
 Mickey+0.039
Neg logit contributions
a-0.061
--0.054
be-0.054
ah-0.054
ch-0.050
Token.
Token ID13
Feature activation+9.53e-02

Pos logit contributions
a+0.034
fly+0.027
ah+0.027
iest+0.026
be+0.026
Neg logit contributions
 court-0.030
ados-0.028
 avocado-0.028
array-0.026
 oranges-0.026
Token They
Token ID1119
Feature activation-1.05e+00

Pos logit contributions
a+0.007
-+0.006
be+0.006
ch+0.006
ah+0.006
Neg logit contributions
ados-0.005
 disl-0.005
 Mickey-0.005
 av-0.005
array-0.005
Token forget
Token ID6044
Feature activation+9.55e-01

Pos logit contributions
 disl+0.070
ados+0.066
 vitamins+0.065
array+0.064
 Mickey+0.064
Neg logit contributions
a-0.064
--0.056
be-0.053
ah-0.053
ch-0.049
Token about
Token ID546
Feature activation+9.83e-01

Pos logit contributions
a+0.061
-+0.053
ah+0.052
be+0.051
ch+0.048
Neg logit contributions
 disl-0.062
ados-0.059
 vitamins-0.058
array-0.057
 Mickey-0.056
Token the
Token ID262
Feature activation-3.22e-01

Pos logit contributions
a+0.050
-+0.044
ah+0.040
be+0.040
ch+0.036
Neg logit contributions
 disl-0.074
ados-0.073
array-0.071
 vitamins-0.070
 Mickey-0.069
Token av
Token ID1196
Feature activation-5.85e+00

Pos logit contributions
 disl+0.022
ados+0.021
array+0.020
 Mickey+0.020
 vitamins+0.020
Neg logit contributions
a-0.019
--0.017
ah-0.016
be-0.016
ch-0.015
Tokenoc
Token ID420
Feature activation+7.15e-01

Pos logit contributions
 disl+0.428
ados+0.420
 vitamins+0.405
 Mickey+0.402
array+0.401
Neg logit contributions
a-0.315
--0.260
be-0.252
ah-0.251
ch-0.229
Tokenados
Token ID22484
Feature activation-5.68e+00

Pos logit contributions
-+0.074
man+0.067
a+0.066
be+0.066
fly+0.065
Neg logit contributions
array-0.015
 disl-0.015
 vitamins-0.012
 mischief-0.012
 Mickey-0.009
Token.
Token ID13
Feature activation+1.10e-01

Pos logit contributions
ados+0.386
 court+0.386
 disl+0.386
 avocado+0.381
 vitamins+0.377
Neg logit contributions
a-0.308
ah-0.275
be-0.254
ch-0.246
--0.243
Token They
Token ID1119
Feature activation-1.01e+00

Pos logit contributions
a+0.008
-+0.007
be+0.007
ch+0.007
ah+0.007
Neg logit contributions
ados-0.006
 disl-0.006
array-0.005
 Mickey-0.005
 av-0.005
Token just
Token ID655
Feature activation+2.51e+00

Pos logit contributions
 disl+0.070
ados+0.069
array+0.066
 vitamins+0.066
 Mickey+0.065
Neg logit contributions
a-0.059
--0.051
ah-0.050
be-0.049
ch-0.045
Token away
Token ID1497
Feature activation+6.84e-01

Pos logit contributions
 disl+0.140
ados+0.136
 vitamins+0.133
array+0.132
 Mickey+0.130
Neg logit contributions
a-0.065
--0.053
ah-0.049
be-0.049
ch-0.043
Token.
Token ID13
Feature activation+4.17e-01

Pos logit contributions
a+0.034
ah+0.029
be+0.027
-+0.026
ch+0.026
Neg logit contributions
 disl-0.052
ados-0.051
 avocado-0.050
 Mickey-0.049
array-0.049
Token She
Token ID1375
Feature activation-4.54e-01

Pos logit contributions
a+0.016
-+0.015
 of+0.015
 and+0.014
ch+0.012
Neg logit contributions
 vitamins-0.033
ados-0.032
 disl-0.032
 av-0.032
array-0.031
Token learned
Token ID4499
Feature activation-1.65e+00

Pos logit contributions
 disl+0.033
ados+0.033
 vitamins+0.031
array+0.031
 Mickey+0.031
Neg logit contributions
a-0.025
--0.022
ah-0.021
be-0.020
ch-0.019
Token that
Token ID326
Feature activation+1.72e-02

Pos logit contributions
 disl+0.141
array+0.141
ados+0.141
 vitamins+0.137
 Mickey+0.133
Neg logit contributions
a-0.068
--0.061
 of-0.049
be-0.046
 closer-0.046
Token av
Token ID1196
Feature activation-5.84e+00

Pos logit contributions
a+0.001
-+0.001
 of+0.001
 on+0.001
 closer+0.001
Neg logit contributions
 disl-0.001
ados-0.001
array-0.001
 courtroom-0.001
handed-0.001
Tokenoc
Token ID420
Feature activation+6.54e-01

Pos logit contributions
 disl+0.458
ados+0.445
 vitamins+0.431
array+0.431
 Mickey+0.423
Neg logit contributions
a-0.291
--0.246
ah-0.235
be-0.232
ch-0.210
Tokenados
Token ID22484
Feature activation-5.74e+00

Pos logit contributions
-+0.065
ah+0.056
man+0.056
a+0.056
rot+0.054
Neg logit contributions
array-0.019
 mischief-0.016
 disl-0.016
 vitamins-0.013
 Afterwards-0.012
Token are
Token ID389
Feature activation+1.52e+00

Pos logit contributions
 disl+0.408
ados+0.395
 vitamins+0.383
array+0.377
 Mickey+0.377
Neg logit contributions
a-0.322
--0.275
ah-0.270
be-0.265
ch-0.245
Token good
Token ID922
Feature activation-3.61e-01

Pos logit contributions
a+0.097
ah+0.085
-+0.084
be+0.083
ch+0.076
Neg logit contributions
 disl-0.097
ados-0.093
 vitamins-0.093
 Mickey-0.091
 avocado-0.089
Token for
Token ID329
Feature activation-1.20e-01

Pos logit contributions
 disl+0.031
ados+0.031
 vitamins+0.030
array+0.030
 Mickey+0.030
Neg logit contributions
a-0.015
ah-0.011
--0.011
be-0.011
ch-0.010
Token something
Token ID1223
Feature activation-1.03e+00

Pos logit contributions
 disl+0.118
ados+0.115
array+0.114
 vitamins+0.111
 Mickey+0.109
Neg logit contributions
a-0.087
--0.076
ah-0.067
be-0.064
 closer-0.062
Token new
Token ID649
Feature activation-4.36e-01

Pos logit contributions
 disl+0.070
ados+0.068
 vitamins+0.066
 avocado+0.065
 Mickey+0.065
Neg logit contributions
a-0.060
be-0.053
ah-0.053
--0.051
ch-0.049
Token!
Token ID0
Feature activation-1.25e-01

Pos logit contributions
 disl+0.031
ados+0.030
 vitamins+0.029
 avocado+0.029
 court+0.028
Neg logit contributions
a-0.023
be-0.022
ch-0.021
ah-0.020
 passenger-0.018
Token She
Token ID1375
Feature activation-4.04e-01

Pos logit contributions
 disl+0.007
array+0.007
ados+0.006
 vitamins+0.006
 av+0.006
Neg logit contributions
a-0.010
--0.008
ah-0.008
 of-0.008
be-0.008
Token thought
Token ID1807
Feature activation-1.03e+00

Pos logit contributions
 disl+0.030
ados+0.030
array+0.029
 vitamins+0.028
 Mickey+0.027
Neg logit contributions
a-0.022
--0.019
ah-0.018
be-0.018
ch-0.016
Token av
Token ID1196
Feature activation-5.84e+00

Pos logit contributions
 disl+0.072
ados+0.070
 vitamins+0.068
array+0.068
 Mickey+0.067
Neg logit contributions
a-0.059
--0.051
ah-0.049
be-0.049
ch-0.045
Tokenoc
Token ID420
Feature activation+7.15e-01

Pos logit contributions
 disl+0.455
ados+0.443
 vitamins+0.429
array+0.428
 Mickey+0.422
Neg logit contributions
a-0.292
--0.247
ah-0.236
be-0.233
ch-0.211
Tokenados
Token ID22484
Feature activation-5.77e+00

Pos logit contributions
-+0.074
a+0.069
ah+0.066
man+0.064
fly+0.064
Neg logit contributions
array-0.018
 mischief-0.014
 disl-0.014
 vitamins-0.013
 court-0.012
Token were
Token ID547
Feature activation-3.23e-02

Pos logit contributions
 disl+0.368
ados+0.356
 vitamins+0.344
 Mickey+0.342
 avocado+0.339
Neg logit contributions
a-0.357
be-0.308
--0.307
ah-0.304
ch-0.292
Token the
Token ID262
Feature activation-5.96e-02

Pos logit contributions
 disl+0.002
ados+0.002
array+0.002
 vitamins+0.002
 Mickey+0.002
Neg logit contributions
a-0.002
--0.001
ah-0.001
be-0.001
ch-0.001
Token most
Token ID749
Feature activation+3.02e-01

Pos logit contributions
 disl+0.005
ados+0.005
array+0.004
 vitamins+0.004
 Mickey+0.004
Neg logit contributions
a-0.003
--0.003
ah-0.002
be-0.002
ch-0.002
Token went
Token ID1816
Feature activation-1.54e+00

Pos logit contributions
 disl+0.016
 Mickey+0.016
ados+0.016
 avocado+0.015
 Bruce+0.015
Neg logit contributions
a-0.019
--0.017
be-0.017
ah-0.017
ch-0.016
Token to
Token ID284
Feature activation-2.58e-02

Pos logit contributions
 court+0.099
 Bruce+0.094
ados+0.094
 Mickey+0.093
 Freddy+0.090
Neg logit contributions
a-0.093
ah-0.083
be-0.079
iest-0.078
fly-0.076
Token the
Token ID262
Feature activation-1.32e-01

Pos logit contributions
ados+0.002
 vitamins+0.002
 disl+0.002
array+0.002
iveness+0.002
Neg logit contributions
a-0.001
--0.001
 closer-0.001
ah-0.001
be-0.001
Token closest
Token ID11706
Feature activation+1.30e+00

Pos logit contributions
 disl+0.007
ados+0.007
 vitamins+0.007
array+0.007
 Mickey+0.006
Neg logit contributions
a-0.010
--0.009
be-0.008
ah-0.008
ch-0.008
Token or
Token ID393
Feature activation-9.22e-01

Pos logit contributions
a+0.094
ah+0.085
be+0.082
-+0.080
ch+0.079
Neg logit contributions
ados-0.069
 court-0.068
 Mickey-0.067
 avocado-0.067
 disl-0.066
Tokenchard
Token ID30215
Feature activation-5.84e+00

Pos logit contributions
 disl+0.035
ados+0.033
 vitamins+0.031
 Mickey+0.031
array+0.030
Neg logit contributions
a-0.082
--0.076
ah-0.074
be-0.074
ch-0.070
Token.
Token ID13
Feature activation+3.52e-01

Pos logit contributions
ados+0.436
 Mickey+0.434
 avocado+0.432
 disl+0.432
 court+0.432
Neg logit contributions
a-0.261
ah-0.235
ch-0.233
be-0.222
--0.208
Token
Token ID198
Feature activation-2.45e-01

Pos logit contributions
a+0.021
 of+0.019
ch+0.017
be+0.017
-+0.017
Neg logit contributions
 disl-0.024
 vitamins-0.023
array-0.022
ados-0.021
 av-0.020
Token
Token ID198
Feature activation-2.37e-01

Pos logit contributions
 disl+0.017
ados+0.017
 vitamins+0.017
array+0.016
 avocado+0.016
Neg logit contributions
a-0.015
--0.013
be-0.012
ah-0.012
ch-0.011
TokenAt
Token ID2953
Feature activation+1.04e+00

Pos logit contributions
 disl+0.017
ados+0.016
 vitamins+0.016
array+0.016
 Mickey+0.016
Neg logit contributions
a-0.013
--0.012
ah-0.011
be-0.011
fly-0.010
Token the
Token ID262
Feature activation-1.06e-01

Pos logit contributions
a+0.064
-+0.055
be+0.054
ah+0.053
ch+0.049
Neg logit contributions
ados-0.067
 disl-0.066
 Mickey-0.066
 avocado-0.064
 Bruce-0.064
Token happy
Token ID3772
Feature activation+4.85e-01

Pos logit contributions
 disl+0.103
ados+0.101
array+0.098
 vitamins+0.097
 Mickey+0.095
Neg logit contributions
a-0.073
--0.062
be-0.059
ah-0.058
ch-0.052
Token that
Token ID326
Feature activation-5.17e-02

Pos logit contributions
a+0.028
ah+0.024
be+0.024
ch+0.021
 passenger+0.021
Neg logit contributions
 disl-0.034
ados-0.033
 vitamins-0.032
 Mickey-0.032
 avocado-0.031
Token it
Token ID340
Feature activation-6.76e-01

Pos logit contributions
 disl+0.004
ados+0.004
array+0.004
 vitamins+0.004
 avocado+0.003
Neg logit contributions
a-0.003
--0.002
ah-0.002
be-0.002
ch-0.002
Token produced
Token ID4635
Feature activation+9.93e-01

Pos logit contributions
 disl+0.051
ados+0.049
 vitamins+0.048
 Mickey+0.048
array+0.047
Neg logit contributions
a-0.035
--0.029
ah-0.029
be-0.028
ch-0.026
Token more
Token ID517
Feature activation-2.99e-02

Pos logit contributions
a+0.054
-+0.047
be+0.043
ah+0.043
ch+0.039
Neg logit contributions
 disl-0.074
ados-0.070
array-0.070
 vitamins-0.067
 Mickey-0.066
Token av
Token ID1196
Feature activation-5.84e+00

Pos logit contributions
 disl+0.002
array+0.002
ados+0.001
 Mickey+0.001
 courtroom+0.001
Neg logit contributions
--0.002
a-0.002
 of-0.002
be-0.002
iest-0.002
Tokenoc
Token ID420
Feature activation+7.45e-01

Pos logit contributions
 disl+0.473
ados+0.450
array+0.445
 vitamins+0.443
 Mickey+0.430
Neg logit contributions
a-0.278
--0.241
be-0.223
ah-0.222
ch-0.198
Tokenados
Token ID22484
Feature activation-5.73e+00

Pos logit contributions
-+0.079
a+0.072
be+0.069
ah+0.068
man+0.066
Neg logit contributions
array-0.017
 disl-0.016
 mischief-0.012
 vitamins-0.011
 court-0.010
Token than
Token ID621
Feature activation+1.94e-01

Pos logit contributions
ados+0.445
 disl+0.443
 Mickey+0.431
 avocado+0.428
 vitamins+0.426
Neg logit contributions
a-0.274
ah-0.233
be-0.223
--0.214
ch-0.211
Token ever
Token ID1683
Feature activation+2.31e+00

Pos logit contributions
a+0.011
-+0.010
ah+0.009
be+0.009
ch+0.008
Neg logit contributions
 disl-0.014
ados-0.013
array-0.013
 vitamins-0.013
 Mickey-0.012
Token before
Token ID878
Feature activation-1.83e+00

Pos logit contributions
a+0.116
-+0.096
ah+0.093
be+0.093
ch+0.085
Neg logit contributions
 disl-0.180
ados-0.175
 vitamins-0.172
array-0.169
 Mickey-0.167
Token on
Token ID319
Feature activation+4.28e-01

Pos logit contributions
ados+0.013
 Mickey+0.012
 vitamins+0.012
 avocado+0.012
array+0.012
Neg logit contributions
a-0.005
fly-0.003
--0.003
be-0.003
ah-0.003
Token,
Token ID11
Feature activation-2.49e-01

Pos logit contributions
a+0.019
be+0.016
ah+0.016
-+0.015
ch+0.014
Neg logit contributions
ados-0.035
 disl-0.035
 Mickey-0.034
 vitamins-0.033
array-0.033
Token whenever
Token ID8797
Feature activation-2.14e+00

Pos logit contributions
 disl+0.014
ados+0.014
 vitamins+0.013
 Mickey+0.013
array+0.013
Neg logit contributions
a-0.018
--0.016
ah-0.015
be-0.015
ch-0.014
Token they
Token ID484
Feature activation+8.28e-01

Pos logit contributions
 disl+0.142
ados+0.138
 vitamins+0.133
array+0.133
 avocado+0.126
Neg logit contributions
a-0.132
--0.116
ah-0.109
be-0.108
ch-0.102
Token wanted
Token ID2227
Feature activation-2.38e+00

Pos logit contributions
a+0.040
-+0.036
ah+0.035
be+0.033
y+0.033
Neg logit contributions
 disl-0.066
ados-0.064
 vitamins-0.062
array-0.061
 Mickey-0.059
Token av
Token ID1196
Feature activation-5.83e+00

Pos logit contributions
 disl+0.220
array+0.214
 vitamins+0.205
ados+0.205
iveness+0.194
Neg logit contributions
--0.073
a-0.070
 of-0.058
 closer-0.053
be-0.049
Tokenoc
Token ID420
Feature activation+8.84e-01

Pos logit contributions
 disl+0.468
ados+0.446
 vitamins+0.439
array+0.439
 Mickey+0.424
Neg logit contributions
a-0.281
--0.244
ah-0.230
be-0.225
ch-0.203
Tokenados
Token ID22484
Feature activation-5.69e+00

Pos logit contributions
-+0.085
ah+0.071
be+0.071
a+0.071
man+0.070
Neg logit contributions
array-0.027
 disl-0.023
 mischief-0.022
 vitamins-0.020
 Penny-0.019
Token,
Token ID11
Feature activation-2.61e-01

Pos logit contributions
 disl+0.455
ados+0.453
 Mickey+0.439
 avocado+0.434
 av+0.427
Neg logit contributions
a-0.264
ah-0.214
be-0.212
--0.207
ch-0.190
Token they
Token ID484
Feature activation+8.02e-01

Pos logit contributions
 disl+0.018
ados+0.017
 vitamins+0.016
 Mickey+0.016
array+0.016
Neg logit contributions
a-0.016
--0.014
ah-0.013
be-0.013
ch-0.012
Token would
Token ID561
Feature activation+2.40e+00

Pos logit contributions
a+0.035
-+0.028
ah+0.027
be+0.026
ch+0.023
Neg logit contributions
 disl-0.068
ados-0.067
array-0.065
 vitamins-0.065
 Mickey-0.063
Token and
Token ID290
Feature activation+3.67e-01

Pos logit contributions
a+0.119
ah+0.101
-+0.099
be+0.097
ch+0.094
Neg logit contributions
 disl-0.159
ados-0.156
array-0.151
 vitamins-0.151
 Mickey-0.149
Token her
Token ID607
Feature activation+2.57e-02

Pos logit contributions
a+0.023
-+0.022
 of+0.020
be+0.019
ah+0.019
Neg logit contributions
 disl-0.024
 vitamins-0.023
array-0.022
ados-0.021
 Bruce-0.020
Token mom
Token ID1995
Feature activation+1.56e-01

Pos logit contributions
a+0.001
-+0.001
 of+0.001
be+0.001
 friend+0.001
Neg logit contributions
 disl-0.002
array-0.002
 vitamins-0.002
ados-0.002
iveness-0.002
Token sorted
Token ID23243
Feature activation+9.05e-01

Pos logit contributions
a+0.011
ah+0.009
-+0.009
be+0.009
fly+0.009
Neg logit contributions
ados-0.009
 disl-0.009
array-0.008
 Mickey-0.008
 vitamins-0.008
Token the
Token ID262
Feature activation-1.78e-01

Pos logit contributions
a+0.046
-+0.041
be+0.036
ah+0.035
 closer+0.033
Neg logit contributions
 disl-0.072
ados-0.066
 vitamins-0.066
array-0.066
 Mickey-0.063
Token av
Token ID1196
Feature activation-5.83e+00

Pos logit contributions
 disl+0.009
array+0.007
 Afterwards+0.007
irs+0.006
 Bruce+0.006
Neg logit contributions
--0.014
a-0.013
 of-0.013
be-0.012
 in-0.012
Tokenoc
Token ID420
Feature activation+5.99e-01

Pos logit contributions
 disl+0.464
array+0.425
ados+0.425
 vitamins+0.424
 Bruce+0.410
Neg logit contributions
a-0.298
--0.267
be-0.242
ah-0.238
ch-0.215
Tokenados
Token ID22484
Feature activation-5.74e+00

Pos logit contributions
-+0.060
a+0.053
man+0.052
ah+0.051
be+0.051
Neg logit contributions
 disl-0.017
array-0.016
 mischief-0.013
 vitamins-0.013
 Afterwards-0.011
Token into
Token ID656
Feature activation-2.47e+00

Pos logit contributions
ados+0.481
 disl+0.472
 vitamins+0.458
 Mickey+0.457
 avocado+0.457
Neg logit contributions
a-0.241
ah-0.202
be-0.187
--0.186
ch-0.175
Token piles
Token ID30935
Feature activation-3.62e+00

Pos logit contributions
 disl+0.194
ados+0.182
 vitamins+0.177
array+0.177
 Mickey+0.169
Neg logit contributions
a-0.128
--0.108
be-0.101
ah-0.093
 closer-0.090
Token according
Token ID1864
Feature activation-5.01e-01

Pos logit contributions
ados+0.259
 avocado+0.248
 av+0.242
 vitamins+0.240
 disl+0.235
Neg logit contributions
a-0.193
ah-0.179
ch-0.166
be-0.160
fly-0.158
Token from
Token ID422
Feature activation-3.28e+00

Pos logit contributions
ados+0.166
 disl+0.165
 Mickey+0.165
 court+0.161
 avocado+0.160
Neg logit contributions
a-0.111
ah-0.096
--0.091
be-0.089
ch-0.085
Token disturbing
Token ID14851
Feature activation+1.96e+00

Pos logit contributions
 disl+0.236
ados+0.227
 vitamins+0.220
array+0.219
 Mickey+0.212
Neg logit contributions
a-0.183
--0.161
be-0.150
ah-0.148
ch-0.138
Token the
Token ID262
Feature activation-1.21e-01

Pos logit contributions
a+0.118
-+0.104
be+0.098
ah+0.097
ch+0.091
Neg logit contributions
 disl-0.132
ados-0.127
 vitamins-0.123
array-0.123
 Mickey-0.120
Token cherry
Token ID23612
Feature activation-2.79e-01

Pos logit contributions
 disl+0.007
ados+0.007
array+0.007
 vitamins+0.007
 Mickey+0.006
Neg logit contributions
a-0.008
--0.007
be-0.007
ah-0.007
ch-0.007
Token or
Token ID393
Feature activation-8.75e-01

Pos logit contributions
 disl+0.020
ados+0.020
 Mickey+0.019
 vitamins+0.019
 avocado+0.019
Neg logit contributions
a-0.015
--0.013
ah-0.012
be-0.012
ch-0.011
Tokenchard
Token ID30215
Feature activation-5.83e+00

Pos logit contributions
 disl+0.060
ados+0.058
array+0.056
 vitamins+0.056
 Mickey+0.054
Neg logit contributions
a-0.051
--0.044
be-0.042
ah-0.040
 closer-0.039
Token.
Token ID13
Feature activation+5.17e-01

Pos logit contributions
 disl+0.451
ados+0.447
 Mickey+0.435
 avocado+0.431
 vitamins+0.430
Neg logit contributions
a-0.275
ah-0.232
be-0.224
--0.220
ch-0.214
Token Had
Token ID11161
Feature activation+8.70e-01

Pos logit contributions
a+0.030
-+0.025
ah+0.025
be+0.024
 of+0.024
Neg logit contributions
 disl-0.036
array-0.035
ados-0.034
 vitamins-0.034
 avocado-0.032
Token he
Token ID339
Feature activation-1.04e-01

Pos logit contributions
a+0.053
-+0.046
ah+0.044
be+0.044
ch+0.040
Neg logit contributions
 disl-0.059
ados-0.057
 vitamins-0.055
array-0.054
 Mickey-0.054
Token not
Token ID407
Feature activation-9.41e-01

Pos logit contributions
 disl+0.007
ados+0.007
 vitamins+0.007
array+0.007
 Mickey+0.007
Neg logit contributions
a-0.006
--0.005
ah-0.005
be-0.005
ch-0.004
Token been
Token ID587
Feature activation+2.15e+00

Pos logit contributions
 disl+0.058
ados+0.056
 vitamins+0.054
array+0.053
 Mickey+0.053
Neg logit contributions
a-0.062
--0.054
ah-0.053
be-0.052
ch-0.049
Token and
Token ID290
Feature activation+3.87e-01

Pos logit contributions
 disl+0.077
ados+0.075
 vitamins+0.073
 avocado+0.073
 Mickey+0.073
Neg logit contributions
a-0.050
ah-0.043
be-0.041
ch-0.039
--0.039
Token shared
Token ID4888
Feature activation-7.49e-01

Pos logit contributions
a+0.020
-+0.018
ah+0.017
be+0.017
y+0.015
Neg logit contributions
 disl-0.029
ados-0.028
array-0.028
 vitamins-0.027
 Mickey-0.026
Token everything
Token ID2279
Feature activation-4.27e-01

Pos logit contributions
 disl+0.057
array+0.056
ados+0.054
 vitamins+0.054
 Mickey+0.052
Neg logit contributions
a-0.038
--0.035
be-0.028
ah-0.028
 of-0.027
Token,
Token ID11
Feature activation-3.15e-01

Pos logit contributions
 disl+0.034
ados+0.034
 avocado+0.032
 vitamins+0.032
 Mickey+0.032
Neg logit contributions
a-0.019
ah-0.017
be-0.016
--0.015
ch-0.015
Token including
Token ID1390
Feature activation+7.13e-02

Pos logit contributions
 disl+0.024
ados+0.024
array+0.023
 vitamins+0.023
 Mickey+0.022
Neg logit contributions
a-0.016
--0.014
ah-0.013
be-0.013
ch-0.011
Token av
Token ID1196
Feature activation-5.83e+00

Pos logit contributions
a+0.004
-+0.004
be+0.004
ah+0.004
 of+0.003
Neg logit contributions
 disl-0.005
array-0.004
ados-0.004
 vitamins-0.004
 Mickey-0.004
Tokenoc
Token ID420
Feature activation+6.74e-01

Pos logit contributions
 disl+0.475
ados+0.453
array+0.448
 vitamins+0.445
 Mickey+0.432
Neg logit contributions
a-0.273
--0.239
ah-0.221
be-0.220
ch-0.193
Tokenados
Token ID22484
Feature activation-5.73e+00

Pos logit contributions
-+0.066
be+0.055
man+0.054
a+0.054
ah+0.053
Neg logit contributions
array-0.019
 mischief-0.019
 court-0.016
 disl-0.016
 vitamins-0.015
Token.
Token ID13
Feature activation+4.44e-01

Pos logit contributions
 disl+0.449
ados+0.447
 vitamins+0.430
 avocado+0.429
 Mickey+0.425
Neg logit contributions
a-0.276
ah-0.232
be-0.224
--0.217
ch-0.213
Token They
Token ID1119
Feature activation-6.54e-01

Pos logit contributions
a+0.027
 of+0.025
-+0.025
ch+0.025
ah+0.025
Neg logit contributions
ados-0.026
 disl-0.026
array-0.025
 av-0.024
handed-0.023
Token were
Token ID547
Feature activation-7.53e-02

Pos logit contributions
 disl+0.052
ados+0.051
array+0.051
 vitamins+0.048
 mischief+0.047
Neg logit contributions
a-0.033
ah-0.028
--0.026
be-0.025
y-0.024
Token every
Token ID790
Feature activation-8.04e-01

Pos logit contributions
ados+0.102
 disl+0.100
 Mickey+0.099
 avocado+0.098
 court+0.096
Neg logit contributions
a-0.077
ah-0.064
be-0.063
--0.062
ch-0.060
Token day
Token ID1110
Feature activation+7.93e-01

Pos logit contributions
ados+0.051
 disl+0.051
 avocado+0.051
 Mickey+0.050
 vitamins+0.049
Neg logit contributions
a-0.050
be-0.042
--0.041
ah-0.041
ch-0.038
Token to
Token ID284
Feature activation-8.52e-02

Pos logit contributions
a+0.039
ah+0.032
be+0.030
-+0.029
ch+0.029
Neg logit contributions
ados-0.061
 disl-0.059
 Mickey-0.059
 avocado-0.058
 vitamins-0.058
Token supply
Token ID5127
Feature activation+2.11e+00

Pos logit contributions
ados+0.006
array+0.006
 disl+0.005
 vitamins+0.005
 Mickey+0.005
Neg logit contributions
a-0.005
--0.004
ah-0.004
 closer-0.004
 of-0.004
Token the
Token ID262
Feature activation-1.76e-01

Pos logit contributions
a+0.113
-+0.108
 of+0.091
be+0.087
 closer+0.084
Neg logit contributions
 disl-0.158
array-0.153
 vitamins-0.141
ados-0.140
 courtroom-0.135
Token av
Token ID1196
Feature activation-5.83e+00

Pos logit contributions
 disl+0.011
array+0.010
 Afterwards+0.009
ados+0.009
 vitamins+0.009
Neg logit contributions
a-0.011
--0.011
be-0.010
 of-0.009
 closer-0.009
Tokenoc
Token ID420
Feature activation+7.80e-01

Pos logit contributions
 disl+0.491
array+0.463
ados+0.459
 vitamins+0.456
 Mickey+0.438
Neg logit contributions
a-0.265
--0.234
be-0.209
ah-0.207
y-0.183
Tokenados
Token ID22484
Feature activation-5.71e+00

Pos logit contributions
-+0.082
a+0.075
man+0.073
be+0.072
fly+0.072
Neg logit contributions
 disl-0.018
array-0.017
 vitamins-0.014
 mischief-0.013
 Bruce-0.010
Token.
Token ID13
Feature activation+3.27e-01

Pos logit contributions
ados+0.450
 disl+0.447
 avocado+0.433
 vitamins+0.433
 Mickey+0.430
Neg logit contributions
a-0.266
ah-0.227
be-0.218
--0.213
ch-0.208
Token And
Token ID843
Feature activation+1.08e+00

Pos logit contributions
a+0.023
ah+0.022
 of+0.021
ch+0.021
-+0.021
Neg logit contributions
 disl-0.017
array-0.016
ados-0.015
 vitamins-0.015
 av-0.013
Token the
Token ID262
Feature activation-1.87e-01

Pos logit contributions
a+0.066
ah+0.057
-+0.057
be+0.057
ch+0.054
Neg logit contributions
 disl-0.070
ados-0.068
 vitamins-0.066
 Mickey-0.066
 avocado-0.065
Token weather
Token ID6193
Feature activation-8.28e-01

Pos logit contributions
 disl+0.009
array+0.008
 vitamins+0.007
ados+0.007
 Bruce+0.007
Neg logit contributions
a-0.009
--0.009
be-0.009
ah-0.008
 closer-0.008
Token before
Token ID878
Feature activation-1.82e+00

Pos logit contributions
ados+0.059
 Mickey+0.058
 avocado+0.057
 disl+0.056
 av+0.055
Neg logit contributions
a-0.043
be-0.036
ah-0.035
--0.032
ch-0.031
Token he
Token ID339
Feature activation-1.27e-01

Pos logit contributions
 disl+0.125
ados+0.118
 vitamins+0.115
array+0.113
 avocado+0.109
Neg logit contributions
a-0.101
--0.099
be-0.090
ah-0.089
ch-0.088
Token picked
Token ID6497
Feature activation-1.60e+00

Pos logit contributions
 disl+0.009
ados+0.009
 vitamins+0.008
array+0.008
 Mickey+0.008
Neg logit contributions
a-0.007
--0.007
ah-0.006
be-0.006
ch-0.006
Token his
Token ID465
Feature activation+6.21e-01

Pos logit contributions
 disl+0.127
array+0.121
 vitamins+0.113
ados+0.111
 courtroom+0.109
Neg logit contributions
--0.077
a-0.077
ah-0.062
 closer-0.061
 on-0.059
Token av
Token ID1196
Feature activation-5.81e+00

Pos logit contributions
-+0.049
a+0.045
 closer+0.041
 on+0.041
ah+0.041
Neg logit contributions
 disl-0.030
array-0.030
 vitamins-0.026
 Bruce-0.024
iveness-0.023
Tokenoc
Token ID420
Feature activation+6.44e-01

Pos logit contributions
 disl+0.469
ados+0.449
 vitamins+0.441
array+0.439
 Mickey+0.427
Neg logit contributions
a-0.278
--0.241
ah-0.227
be-0.222
ch-0.200
Tokenados
Token ID22484
Feature activation-5.73e+00

Pos logit contributions
-+0.067
ah+0.058
a+0.057
man+0.057
be+0.056
Neg logit contributions
array-0.016
 disl-0.015
 vitamins-0.012
 mischief-0.012
 Bruce-0.011
Token.
Token ID13
Feature activation+4.69e-01

Pos logit contributions
 disl+0.468
ados+0.464
 vitamins+0.447
 Mickey+0.446
array+0.444
Neg logit contributions
a-0.258
--0.207
ah-0.205
be-0.202
ch-0.182
Token<|endoftext|>
Token ID50256
Feature activation+1.59e+00

Pos logit contributions
a+0.030
-+0.030
ah+0.028
be+0.028
ch+0.027
Neg logit contributions
 disl-0.027
array-0.027
ados-0.026
 vitamins-0.025
 av-0.024
TokenOnce
Token ID7454
Feature activation+4.52e-01

Pos logit contributions
a+0.110
-+0.097
ah+0.095
be+0.095
ch+0.088
Neg logit contributions
 disl-0.091
ados-0.088
 vitamins-0.084
array-0.084
 Mickey-0.083
Token says
Token ID1139
Feature activation-8.26e-01

Pos logit contributions
a+0.023
-+0.021
ah+0.020
be+0.020
y+0.019
Neg logit contributions
 disl-0.017
ados-0.016
 vitamins-0.015
array-0.015
 Mickey-0.015
Token they
Token ID484
Feature activation+4.04e-01

Pos logit contributions
ados+0.065
 disl+0.064
 vitamins+0.063
 avocado+0.062
 Mickey+0.062
Neg logit contributions
a-0.040
ah-0.033
--0.033
be-0.032
ch-0.029
Token are
Token ID389
Feature activation+1.29e+00

Pos logit contributions
a+0.015
be+0.012
-+0.012
ah+0.011
 closer+0.010
Neg logit contributions
 disl-0.037
ados-0.036
array-0.035
 vitamins-0.034
 Mickey-0.033
Token av
Token ID1196
Feature activation-5.91e+00

Pos logit contributions
a+0.080
-+0.070
be+0.066
ah+0.065
ch+0.061
Neg logit contributions
 disl-0.087
ados-0.083
array-0.081
 vitamins-0.080
 Mickey-0.078
Tokenoc
Token ID420
Feature activation+5.22e-01

Pos logit contributions
ados+0.418
 disl+0.414
 vitamins+0.400
 Mickey+0.397
array+0.394
Neg logit contributions
a-0.323
--0.267
ah-0.262
be-0.261
ch-0.244
Tokenados
Token ID22484
Feature activation-5.81e+00

Pos logit contributions
-+0.055
a+0.053
ah+0.050
be+0.049
man+0.048
Neg logit contributions
 disl-0.010
array-0.009
 mischief-0.007
 vitamins-0.007
 Mickey-0.006
Token.
Token ID13
Feature activation+2.50e-01

Pos logit contributions
ados+0.415
 Mickey+0.404
 disl+0.401
 avocado+0.400
 vitamins+0.399
Neg logit contributions
a-0.292
ah-0.264
be-0.263
ch-0.246
--0.239
Token Sara
Token ID24799
Feature activation+1.23e+00

Pos logit contributions
a+0.013
-+0.011
 of+0.011
be+0.010
 closer+0.010
Neg logit contributions
 disl-0.019
array-0.018
 Mickey-0.018
ados-0.017
 vitamins-0.017
Token wants
Token ID3382
Feature activation-2.77e+00

Pos logit contributions
a+0.075
-+0.066
be+0.058
ah+0.058
y+0.055
Neg logit contributions
 disl-0.089
ados-0.088
 Mickey-0.083
 Bruce-0.081
array-0.081
Token to
Token ID284
Feature activation-1.66e-01

Pos logit contributions
 disl+0.283
array+0.274
ados+0.255
 mischief+0.250
 vitamins+0.249
Neg logit contributions
a-0.065
--0.060
 closer-0.048
 of-0.047
be-0.042
Token try
Token ID1949
Feature activation+6.90e-01

Pos logit contributions
array+0.012
ados+0.011
 disl+0.011
 vitamins+0.011
 Bruce+0.010
Neg logit contributions
a-0.009
--0.008
 of-0.008
ah-0.008
be-0.008
Token they
Token ID484
Feature activation+5.59e-01

Pos logit contributions
 disl+0.119
ados+0.116
 Mickey+0.112
 vitamins+0.111
 avocado+0.109
Neg logit contributions
a-0.119
be-0.101
ah-0.101
--0.099
ch-0.092
Token had
Token ID550
Feature activation+3.07e-01

Pos logit contributions
a+0.031
ah+0.028
-+0.028
ch+0.027
be+0.026
Neg logit contributions
 disl-0.036
 Mickey-0.036
 vitamins-0.035
ados-0.035
 Bruce-0.035
Token never
Token ID1239
Feature activation+1.09e+00

Pos logit contributions
a+0.019
-+0.016
be+0.015
ah+0.015
ch+0.014
Neg logit contributions
 disl-0.021
ados-0.020
array-0.019
 vitamins-0.019
 Mickey-0.019
Token seen
Token ID1775
Feature activation+1.72e+00

Pos logit contributions
a+0.068
-+0.059
ah+0.057
be+0.056
ch+0.052
Neg logit contributions
 disl-0.071
ados-0.069
 vitamins-0.067
array-0.066
 Mickey-0.065
Token the
Token ID262
Feature activation-1.54e-01

Pos logit contributions
a+0.071
-+0.069
ah+0.059
 closer+0.058
 of+0.057
Neg logit contributions
 disl-0.139
array-0.135
 vitamins-0.126
ados-0.122
 courtroom-0.121
Token av
Token ID1196
Feature activation-5.80e+00

Pos logit contributions
 disl+0.010
ados+0.010
array+0.009
 vitamins+0.009
 Mickey+0.009
Neg logit contributions
a-0.010
--0.009
ah-0.008
be-0.008
ch-0.008
Tokenoc
Token ID420
Feature activation+8.79e-01

Pos logit contributions
 disl+0.450
ados+0.437
 vitamins+0.425
array+0.422
 Mickey+0.416
Neg logit contributions
a-0.292
--0.247
ah-0.236
be-0.234
ch-0.212
Tokenados
Token ID22484
Feature activation-5.65e+00

Pos logit contributions
-+0.088
a+0.082
ah+0.081
be+0.080
man+0.080
Neg logit contributions
 disl-0.021
array-0.020
 vitamins-0.019
 mischief-0.015
 Mickey-0.014
Token.
Token ID13
Feature activation+2.92e-01

Pos logit contributions
 avocado+0.410
ados+0.409
 court+0.399
 disl+0.398
 Mickey+0.397
Neg logit contributions
a-0.296
ah-0.245
be-0.237
--0.234
ch-0.226
Token They
Token ID1119
Feature activation-8.88e-01

Pos logit contributions
a+0.017
-+0.015
be+0.014
 passenger+0.014
 too+0.013
Neg logit contributions
ados-0.019
 av-0.019
 avocado-0.018
 disl-0.017
 vitamins-0.017
Token wished
Token ID16555
Feature activation-1.88e+00

Pos logit contributions
 disl+0.048
ados+0.047
 vitamins+0.044
array+0.043
 avocado+0.042
Neg logit contributions
a-0.067
--0.059
be-0.058
ah-0.057
ch-0.053
Token sun
Token ID4252
Feature activation+4.97e-01

Pos logit contributions
 disl+0.003
 avocado+0.003
ados+0.003
array+0.003
 Mickey+0.003
Neg logit contributions
a-0.004
ah-0.003
--0.003
be-0.003
ba-0.003
Token and
Token ID290
Feature activation+1.01e-01

Pos logit contributions
a+0.027
ah+0.021
vy+0.020
ch+0.020
 racer+0.020
Neg logit contributions
ados-0.033
 Mickey-0.032
 avocado-0.031
array-0.030
yard-0.030
Token Boris
Token ID25026
Feature activation-9.32e-02

Pos logit contributions
a+0.006
-+0.005
ah+0.005
be+0.005
ch+0.005
Neg logit contributions
 disl-0.007
ados-0.006
 Mickey-0.006
 vitamins-0.006
 avocado-0.006
Token knew
Token ID2993
Feature activation+8.20e-02

Pos logit contributions
 disl+0.006
 Mickey+0.005
array+0.005
 vitamins+0.005
 Bruce+0.005
Neg logit contributions
a-0.005
ah-0.004
ch-0.004
less-0.004
--0.004
Token he
Token ID339
Feature activation+5.91e-02

Pos logit contributions
a+0.006
be+0.005
ah+0.005
-+0.005
ch+0.005
Neg logit contributions
 disl-0.005
ados-0.004
 Mickey-0.004
 Bruce-0.004
 vitamins-0.004
Token'd
Token ID1549
Feature activation+5.07e+00

Pos logit contributions
a+0.003
be+0.003
ch+0.003
ah+0.003
 passenger+0.003
Neg logit contributions
 Mickey-0.004
 disl-0.004
 vitamins-0.004
 Bruce-0.003
 avocado-0.003
Token found
Token ID1043
Feature activation-6.81e-01

Pos logit contributions
a+0.323
-+0.286
be+0.273
ah+0.273
ch+0.261
Neg logit contributions
 disl-0.327
 vitamins-0.306
array-0.290
 Mickey-0.289
 avocado-0.289
Token a
Token ID257
Feature activation+6.27e-01

Pos logit contributions
ados+0.040
 disl+0.039
 vitamins+0.039
 Mickey+0.039
 avocado+0.039
Neg logit contributions
a-0.044
be-0.041
ah-0.039
--0.037
ch-0.036
Token true
Token ID2081
Feature activation-5.88e-03

Pos logit contributions
a+0.040
be+0.036
ah+0.035
-+0.035
as+0.035
Neg logit contributions
 avocado-0.035
 Mickey-0.035
 disl-0.035
 Bruce-0.032
 av-0.032
Token companion
Token ID15185
Feature activation+2.50e+00

Pos logit contributions
 avocado+0.000
 av+0.000
 Mickey+0.000
 vitamins+0.000
 Bruce+0.000
Neg logit contributions
a-0.000
be-0.000
as-0.000
Rex-0.000
z-0.000
Token.
Token ID13
Feature activation+3.68e-01

Pos logit contributions
a+0.136
be+0.119
ch+0.119
ah+0.116
-+0.107
Neg logit contributions
 Bruce-0.162
ados-0.157
 Mickey-0.157
 avocado-0.153
 court-0.151
Token thought
Token ID1807
Feature activation-1.13e+00

Pos logit contributions
a+0.062
-+0.054
be+0.054
ah+0.053
less+0.052
Neg logit contributions
 disl-0.063
ados-0.061
 Mickey-0.060
 avocado-0.059
array-0.059
Token about
Token ID546
Feature activation+1.13e+00

Pos logit contributions
 disl+0.078
ados+0.077
 vitamins+0.076
 Mickey+0.076
 avocado+0.075
Neg logit contributions
a-0.062
be-0.056
ah-0.050
fly-0.049
--0.048
Token it
Token ID340
Feature activation-6.47e-01

Pos logit contributions
a+0.062
-+0.054
ah+0.051
be+0.049
ch+0.046
Neg logit contributions
 disl-0.081
ados-0.080
array-0.078
 vitamins-0.077
 Mickey-0.074
Token for
Token ID329
Feature activation-4.89e-01

Pos logit contributions
 Mickey+0.048
ados+0.048
 disl+0.047
 avocado+0.047
 vitamins+0.046
Neg logit contributions
a-0.032
be-0.027
ah-0.025
--0.024
ch-0.024
Token a
Token ID257
Feature activation+4.34e-01

Pos logit contributions
 disl+0.035
ados+0.035
 Mickey+0.033
 vitamins+0.033
array+0.033
Neg logit contributions
a-0.027
--0.023
be-0.022
ah-0.022
ch-0.020
Token moment
Token ID2589
Feature activation+4.95e+00

Pos logit contributions
a+0.019
-+0.016
be+0.016
as+0.015
web+0.015
Neg logit contributions
 disl-0.033
 Mickey-0.032
 Bruce-0.032
 avocado-0.032
 court-0.031
Token and
Token ID290
Feature activation+1.05e-01

Pos logit contributions
a+0.291
ah+0.247
be+0.247
 passenger+0.241
ch+0.238
Neg logit contributions
 avocado-0.301
ados-0.296
 Mickey-0.291
 disl-0.290
 court-0.289
Token realized
Token ID6939
Feature activation-1.54e+00

Pos logit contributions
a+0.007
-+0.006
be+0.006
ah+0.006
ch+0.005
Neg logit contributions
 disl-0.007
ados-0.007
 vitamins-0.006
 Mickey-0.006
array-0.006
Token that
Token ID326
Feature activation+7.29e-02

Pos logit contributions
 disl+0.104
ados+0.101
 vitamins+0.097
 Mickey+0.096
array+0.095
Neg logit contributions
a-0.093
--0.079
be-0.079
ah-0.078
ch-0.072
Token the
Token ID262
Feature activation-1.83e-01

Pos logit contributions
a+0.004
-+0.004
ah+0.004
be+0.003
ch+0.003
Neg logit contributions
 disl-0.005
ados-0.005
array-0.005
 vitamins-0.005
 Mickey-0.005
Token frog
Token ID21264
Feature activation+1.58e+00

Pos logit contributions
 disl+0.013
ados+0.012
 vitamins+0.012
 avocado+0.012
array+0.012
Neg logit contributions
a-0.011
--0.009
ah-0.009
be-0.009
ch-0.008
Tokenimmer
Token ID10957
Feature activation+2.33e+00

Pos logit contributions
a+0.039
 plane+0.036
 racer+0.035
be+0.035
 cloud+0.035
Neg logit contributions
 disl-0.041
ados-0.041
array-0.037
iveness-0.036
issors-0.035
Tokening
Token ID278
Feature activation-3.21e-02

Pos logit contributions
a+0.124
 passenger+0.114
be+0.110
ah+0.109
fly+0.108
Neg logit contributions
ados-0.146
 av-0.139
 avocado-0.134
 oranges-0.126
 onions-0.125
Token in
Token ID287
Feature activation+1.61e-01

Pos logit contributions
ados+0.002
 avocado+0.002
 av+0.002
array+0.002
 Mickey+0.002
Neg logit contributions
a-0.002
be-0.001
ah-0.001
as-0.001
ber-0.001
Token the
Token ID262
Feature activation-3.35e-02

Pos logit contributions
a+0.010
-+0.009
be+0.009
ah+0.009
ch+0.008
Neg logit contributions
 disl-0.010
ados-0.010
 Mickey-0.010
array-0.010
 vitamins-0.010
Token moon
Token ID8824
Feature activation+1.90e+00

Pos logit contributions
 disl+0.002
ados+0.002
array+0.002
 vitamins+0.002
 avocado+0.002
Neg logit contributions
a-0.003
--0.002
ah-0.002
be-0.002
ch-0.002
Tokenlight
Token ID2971
Feature activation+5.65e+00

Pos logit contributions
a+0.097
vy+0.077
ah+0.076
ber+0.075
 racer+0.072
Neg logit contributions
ados-0.124
 avocado-0.121
array-0.121
 Mickey-0.116
 disl-0.115
Token.
Token ID13
Feature activation+5.56e-01

Pos logit contributions
a+0.339
ah+0.287
ber+0.283
 racer+0.280
ang+0.274
Neg logit contributions
 disl-0.325
array-0.317
ados-0.315
 vitamins-0.304
 avocado-0.304
Token It
Token ID632
Feature activation+6.30e-01

Pos logit contributions
a+0.035
-+0.033
be+0.031
 of+0.030
ah+0.029
Neg logit contributions
 disl-0.034
 vitamins-0.033
ados-0.033
array-0.030
 avocado-0.029
Token was
Token ID373
Feature activation-2.34e-01

Pos logit contributions
a+0.035
be+0.029
less+0.029
-+0.028
ah+0.028
Neg logit contributions
 disl-0.042
 Mickey-0.042
ados-0.040
 avocado-0.039
 av-0.039
Token so
Token ID523
Feature activation-1.27e+00

Pos logit contributions
 disl+0.015
 Mickey+0.015
ados+0.015
 avocado+0.015
 vitamins+0.015
Neg logit contributions
a-0.014
be-0.012
--0.012
ah-0.012
mer-0.011
Token quiet
Token ID5897
Feature activation+1.53e+00

Pos logit contributions
ados+0.103
 disl+0.101
array+0.099
 vitamins+0.098
 Mickey+0.093
Neg logit contributions
a-0.062
--0.052
ah-0.046
be-0.046
ch-0.044
Token world
Token ID995
Feature activation-3.94e-01

Pos logit contributions
a+0.002
-+0.002
ah+0.002
be+0.002
ch+0.002
Neg logit contributions
 disl-0.003
ados-0.003
 vitamins-0.003
array-0.003
 Mickey-0.003
Token he
Token ID339
Feature activation+5.75e-02

Pos logit contributions
 Mickey+0.026
 Bruce+0.026
ados+0.026
 disl+0.026
 court+0.026
Neg logit contributions
a-0.022
be-0.018
ah-0.018
ch-0.016
as-0.016
Token promised
Token ID8072
Feature activation-1.51e+00

Pos logit contributions
a+0.003
less+0.003
be+0.003
ah+0.003
-+0.003
Neg logit contributions
 Mickey-0.003
 disl-0.003
 Bruce-0.003
array-0.003
 court-0.003
Token himself
Token ID2241
Feature activation-3.35e+00

Pos logit contributions
 disl+0.105
ados+0.102
 Mickey+0.098
 vitamins+0.097
array+0.096
Neg logit contributions
a-0.087
ah-0.072
be-0.072
--0.069
ch-0.067
Token he
Token ID339
Feature activation+8.72e-02

Pos logit contributions
 disl+0.224
ados+0.221
 Bruce+0.216
 Mickey+0.215
 vitamins+0.215
Neg logit contributions
a-0.184
be-0.167
ah-0.163
ch-0.159
fly-0.151
Token'd
Token ID1549
Feature activation+5.06e+00

Pos logit contributions
a+0.004
be+0.004
ch+0.003
ah+0.003
-+0.003
Neg logit contributions
 disl-0.006
 vitamins-0.006
 Mickey-0.006
 Bruce-0.006
ados-0.006
Token come
Token ID1282
Feature activation+2.86e+00

Pos logit contributions
a+0.321
-+0.280
be+0.269
ah+0.264
ch+0.258
Neg logit contributions
 disl-0.326
 vitamins-0.306
 court-0.289
array-0.288
 Mickey-0.287
Token back
Token ID736
Feature activation+1.04e+00

Pos logit contributions
a+0.167
ah+0.149
mer+0.130
be+0.129
ch+0.128
Neg logit contributions
 Mickey-0.182
 Bruce-0.180
ados-0.175
 disl-0.173
 herself-0.172
Token soon
Token ID2582
Feature activation+1.86e+00

Pos logit contributions
a+0.052
ah+0.045
be+0.044
ch+0.041
-+0.039
Neg logit contributions
 disl-0.074
ados-0.074
 Mickey-0.073
 court-0.072
 Bruce-0.072
Token.
Token ID13
Feature activation+3.69e-01

Pos logit contributions
a+0.096
ah+0.078
be+0.075
-+0.073
ch+0.072
Neg logit contributions
 disl-0.137
ados-0.136
 vitamins-0.132
array-0.131
 avocado-0.130
Token<|endoftext|>
Token ID50256
Feature activation+1.54e+00

Pos logit contributions
a+0.016
ah+0.014
-+0.014
 of+0.013
ch+0.013
Neg logit contributions
 disl-0.029
 vitamins-0.029
ados-0.028
array-0.028
 avocado-0.027
Token shapes
Token ID15268
Feature activation-1.31e+00

Pos logit contributions
a+0.017
-+0.015
be+0.014
ah+0.014
ch+0.013
Neg logit contributions
 disl-0.020
ados-0.019
array-0.019
 vitamins-0.018
 Mickey-0.018
Token.
Token ID13
Feature activation+3.41e-01

Pos logit contributions
 avocado+0.090
ados+0.088
 vitamins+0.087
 disl+0.087
 av+0.084
Neg logit contributions
a-0.071
ah-0.060
be-0.057
ch-0.056
--0.054
Token After
Token ID2293
Feature activation-3.18e+00

Pos logit contributions
a+0.018
-+0.017
be+0.016
 of+0.016
ah+0.015
Neg logit contributions
 disl-0.024
ados-0.021
array-0.020
 vitamins-0.020
 Mickey-0.019
Token a
Token ID257
Feature activation+6.91e-01

Pos logit contributions
 disl+0.231
ados+0.225
 vitamins+0.217
array+0.216
 Mickey+0.214
Neg logit contributions
a-0.176
--0.150
ah-0.144
be-0.144
ch-0.131
Token few
Token ID1178
Feature activation+2.65e+00

Pos logit contributions
a+0.036
as+0.030
web+0.029
ac+0.029
be+0.029
Neg logit contributions
 Mickey-0.046
 disl-0.045
 Bruce-0.044
 avocado-0.044
 Freddy-0.044
Token minutes
Token ID2431
Feature activation+5.21e+00

Pos logit contributions
a+0.146
be+0.120
ah+0.118
fly+0.115
ba+0.113
Neg logit contributions
 vitamins-0.187
 disl-0.187
ados-0.185
array-0.181
 avocado-0.178
Token,
Token ID11
Feature activation-2.96e-01

Pos logit contributions
a+0.250
ah+0.191
be+0.191
-+0.189
fly+0.177
Neg logit contributions
ados-0.405
 disl-0.400
 Mickey-0.390
 avocado-0.389
array-0.389
Token he
Token ID339
Feature activation-1.49e-01

Pos logit contributions
 disl+0.017
ados+0.016
 vitamins+0.016
array+0.015
 Mickey+0.015
Neg logit contributions
a-0.021
--0.019
ah-0.018
be-0.018
ch-0.017
Token saw
Token ID2497
Feature activation+9.69e-01

Pos logit contributions
 disl+0.009
array+0.009
 Mickey+0.009
 avocado+0.009
ados+0.009
Neg logit contributions
a-0.009
ah-0.008
--0.008
be-0.008
ch-0.007
Token a
Token ID257
Feature activation+7.13e-01

Pos logit contributions
a+0.054
-+0.047
ah+0.044
be+0.044
ch+0.040
Neg logit contributions
 disl-0.070
ados-0.068
array-0.066
 vitamins-0.066
 Mickey-0.064
Token bird
Token ID6512
Feature activation+1.33e+00

Pos logit contributions
a+0.043
ah+0.038
be+0.037
-+0.037
iest+0.036
Neg logit contributions
 avocado-0.044
 av-0.042
 Mickey-0.041
 disl-0.041
 court-0.041
Token up
Token ID510
Feature activation-3.18e+00

Pos logit contributions
a+0.239
ah+0.213
be+0.212
ch+0.204
iest+0.197
Neg logit contributions
 disl-0.178
ados-0.174
 Mickey-0.166
 Bruce-0.164
array-0.163
Token the
Token ID262
Feature activation-4.19e-02

Pos logit contributions
 disl+0.232
ados+0.223
array+0.216
 Mickey+0.214
 vitamins+0.213
Neg logit contributions
a-0.175
--0.144
be-0.144
ah-0.144
ch-0.132
Token adventure
Token ID8855
Feature activation-6.48e-01

Pos logit contributions
 disl+0.002
ados+0.002
array+0.002
 vitamins+0.002
 avocado+0.002
Neg logit contributions
a-0.003
--0.003
ah-0.003
be-0.002
fly-0.002
Token with
Token ID351
Feature activation-1.78e+00

Pos logit contributions
 court+0.044
ados+0.042
 disl+0.042
 Mickey+0.042
 Bruce+0.041
Neg logit contributions
a-0.034
ah-0.029
fly-0.027
be-0.027
ba-0.025
Token one
Token ID530
Feature activation+1.39e+00

Pos logit contributions
 disl+0.120
ados+0.117
 vitamins+0.112
array+0.112
 Mickey+0.110
Neg logit contributions
a-0.107
--0.093
ah-0.090
be-0.089
ch-0.082
Token final
Token ID2457
Feature activation+3.94e+00

Pos logit contributions
a+0.072
ba+0.068
be+0.066
ilot+0.060
ah+0.060
Neg logit contributions
 avocado-0.089
 court-0.084
 av-0.078
 oranges-0.078
handed-0.076
Token zoom
Token ID19792
Feature activation+1.68e+00

Pos logit contributions
a+0.247
ba+0.218
fly+0.208
web+0.198
as+0.197
Neg logit contributions
 disl-0.239
 courtroom-0.212
 court-0.212
array-0.211
 mischief-0.210
Token!
Token ID0
Feature activation-2.14e-01

Pos logit contributions
a+0.078
 spe+0.064
be+0.064
fly+0.062
ah+0.060
Neg logit contributions
ados-0.111
 court-0.106
 disl-0.106
 Everyone-0.099
 Bruce-0.098
Token<|endoftext|>
Token ID50256
Feature activation+1.65e+00

Pos logit contributions
 vitamins+0.012
ados+0.012
 disl+0.012
array+0.011
 av+0.011
Neg logit contributions
a-0.014
 of-0.013
--0.013
ch-0.013
be-0.013
TokenOnce
Token ID7454
Feature activation+5.87e-01

Pos logit contributions
a+0.120
-+0.106
ah+0.104
be+0.104
ch+0.096
Neg logit contributions
 disl-0.086
ados-0.085
 Mickey-0.082
array-0.081
 vitamins-0.081
Token upon
Token ID2402
Feature activation+1.51e+00

Pos logit contributions
a+0.023
be+0.018
-+0.018
ah+0.018
ch+0.016
Neg logit contributions
 disl-0.050
ados-0.049
 Mickey-0.048
 vitamins-0.047
 avocado-0.047
Token gone
Token ID3750
Feature activation+2.05e+00

Pos logit contributions
a+0.020
-+0.018
ah+0.017
be+0.017
fly+0.017
Neg logit contributions
 vitamins-0.018
 disl-0.018
 Mickey-0.017
array-0.017
 Bruce-0.017
Token on
Token ID319
Feature activation+5.57e-01

Pos logit contributions
a+0.115
ah+0.105
be+0.103
ch+0.096
fly+0.090
Neg logit contributions
 Bruce-0.132
 Mickey-0.131
ados-0.131
 disl-0.130
 court-0.128
Token an
Token ID281
Feature activation-2.41e-01

Pos logit contributions
a+0.035
be+0.030
ah+0.030
-+0.029
ch+0.027
Neg logit contributions
 disl-0.037
ados-0.035
 vitamins-0.035
 Mickey-0.034
array-0.034
Token adventure
Token ID8855
Feature activation-6.65e-01

Pos logit contributions
 disl+0.013
 vitamins+0.013
ados+0.012
array+0.012
 avocado+0.012
Neg logit contributions
a-0.017
--0.015
be-0.015
ah-0.015
fly-0.014
Token and
Token ID290
Feature activation+3.74e-01

Pos logit contributions
 court+0.043
 Bruce+0.042
 Mickey+0.042
ados+0.041
 Jack+0.041
Neg logit contributions
a-0.036
be-0.031
ah-0.030
ch-0.029
ba-0.029
Token rocked
Token ID36872
Feature activation+1.46e+00

Pos logit contributions
a+0.022
-+0.019
ah+0.019
be+0.019
ch+0.017
Neg logit contributions
 disl-0.026
ados-0.024
 vitamins-0.024
 Mickey-0.024
array-0.023
Token on
Token ID319
Feature activation+5.63e-01

Pos logit contributions
a+0.089
be+0.078
ah+0.074
fly+0.068
ch+0.066
Neg logit contributions
ados-0.091
 Mickey-0.089
 Bruce-0.089
 Jerry-0.085
 disl-0.085
Token the
Token ID262
Feature activation-7.55e-02

Pos logit contributions
a+0.037
be+0.032
ah+0.031
-+0.030
ch+0.028
Neg logit contributions
 disl-0.035
ados-0.035
 Mickey-0.033
 vitamins-0.033
 avocado-0.033
Token big
Token ID1263
Feature activation-5.84e-01

Pos logit contributions
 disl+0.004
 vitamins+0.004
ados+0.004
array+0.004
 Mickey+0.004
Neg logit contributions
a-0.005
ah-0.004
--0.004
be-0.004
fly-0.004
Token white
Token ID2330
Feature activation-8.52e-01

Pos logit contributions
 disl+0.037
ados+0.036
 vitamins+0.035
 avocado+0.035
 Mickey+0.035
Neg logit contributions
a-0.039
ah-0.031
be-0.031
--0.030
as-0.029
Token sail
Token ID14936
Feature activation+1.04e-01

Pos logit contributions
 disl+0.045
ados+0.043
 vitamins+0.043
 Bruce+0.043
 avocado+0.042
Neg logit contributions
a-0.064
ah-0.054
be-0.052
--0.050
fly-0.050
Tokenily
Token ID813
Feature activation+1.36e+00

Pos logit contributions
 disl+0.033
ados+0.032
 vitamins+0.031
array+0.030
 Mickey+0.030
Neg logit contributions
a-0.044
--0.039
ah-0.038
be-0.038
ch-0.036
Token smiled
Token ID13541
Feature activation+6.96e-01

Pos logit contributions
a+0.077
-+0.066
ah+0.064
be+0.064
ch+0.060
Neg logit contributions
 disl-0.094
ados-0.092
 vitamins-0.088
array-0.088
 Mickey-0.088
Token and
Token ID290
Feature activation+2.85e-01

Pos logit contributions
a+0.039
ah+0.035
ch+0.032
be+0.032
iest+0.031
Neg logit contributions
ados-0.047
 avocado-0.046
 Mickey-0.045
 From-0.044
 av-0.044
Token said
Token ID531
Feature activation+2.27e-02

Pos logit contributions
a+0.017
-+0.015
be+0.014
ah+0.014
ch+0.013
Neg logit contributions
 disl-0.020
ados-0.019
array-0.019
 vitamins-0.019
 avocado-0.018
Token,
Token ID11
Feature activation-3.73e-01

Pos logit contributions
a+0.001
ah+0.001
be+0.001
-+0.001
ch+0.001
Neg logit contributions
ados-0.002
 disl-0.002
 avocado-0.002
 vitamins-0.002
 Mickey-0.002
Token "
Token ID366
Feature activation+2.52e+00

Pos logit contributions
 disl+0.023
ados+0.022
 vitamins+0.021
 Mickey+0.021
array+0.021
Neg logit contributions
a-0.025
--0.022
ah-0.021
be-0.021
ch-0.019
TokenChe
Token ID7376
Feature activation+1.28e+00

Pos logit contributions
a+0.177
-+0.157
ah+0.152
be+0.151
ch+0.141
Neg logit contributions
 disl-0.147
ados-0.141
 vitamins-0.136
array-0.134
 Mickey-0.133
Tokenese
Token ID2771
Feature activation+1.47e+00

Pos logit contributions
a+0.063
 closer+0.057
fly+0.056
be+0.056
ch+0.055
Neg logit contributions
ados-0.092
 disl-0.083
 vitamins-0.082
 avocado-0.080
 av-0.078
Token!"
Token ID2474
Feature activation-2.38e+00

Pos logit contributions
a+0.078
be+0.068
-+0.067
ah+0.065
less+0.062
Neg logit contributions
 disl-0.100
ados-0.098
 vitamins-0.095
 avocado-0.093
 Mickey-0.092
Token<|endoftext|>
Token ID50256
Feature activation+1.54e+00

Pos logit contributions
 disl+0.199
array+0.186
 vitamins+0.184
ados+0.178
 courtroom+0.173
Neg logit contributions
a-0.108
--0.104
 of-0.102
 and-0.088
 on-0.087
TokenS
Token ID50
Feature activation-3.68e-01

Pos logit contributions
a+0.103
-+0.091
ah+0.088
be+0.088
ch+0.082
Neg logit contributions
 disl-0.094
ados-0.090
 vitamins-0.086
array-0.086
 Mickey-0.084
Token hands
Token ID2832
Feature activation-1.71e+00

Pos logit contributions
a+0.093
-+0.087
be+0.081
ah+0.076
ch+0.074
Neg logit contributions
 disl-0.085
ados-0.082
 Mickey-0.080
 Bruce-0.078
 vitamins-0.077
Token,
Token ID11
Feature activation-3.25e-01

Pos logit contributions
ados+0.117
 Mickey+0.115
 disl+0.115
array+0.111
 avocado+0.110
Neg logit contributions
a-0.091
ah-0.080
be-0.070
fly-0.070
--0.069
Token mom
Token ID1995
Feature activation+2.02e-01

Pos logit contributions
 disl+0.018
ados+0.017
 vitamins+0.017
array+0.016
 Mickey+0.016
Neg logit contributions
a-0.024
--0.021
be-0.021
ah-0.020
ch-0.019
Tokenmy
Token ID1820
Feature activation-2.25e-01

Pos logit contributions
a+0.016
mer+0.014
ah+0.014
 souven+0.014
fly+0.014
Neg logit contributions
 Mickey-0.008
array-0.008
ados-0.008
 avocado-0.008
 av-0.007
Token tried
Token ID3088
Feature activation-7.32e-01

Pos logit contributions
 Mickey+0.013
 disl+0.012
ados+0.012
array+0.012
 avocado+0.012
Neg logit contributions
a-0.014
ah-0.013
be-0.012
--0.012
fly-0.012
Token one
Token ID530
Feature activation+1.39e+00

Pos logit contributions
 disl+0.063
ados+0.061
 vitamins+0.059
array+0.058
 Mickey+0.058
Neg logit contributions
a-0.032
--0.027
be-0.024
ah-0.024
ch-0.021
Token more
Token ID517
Feature activation+2.09e-02

Pos logit contributions
a+0.074
ilot+0.072
fly+0.071
be+0.069
ba+0.068
Neg logit contributions
 avocado-0.089
 oranges-0.081
 broccoli-0.080
 squash-0.078
 Mickey-0.078
Token time
Token ID640
Feature activation+1.43e+00

Pos logit contributions
a+0.001
be+0.001
ah+0.001
-+0.001
fly+0.001
Neg logit contributions
 disl-0.002
ados-0.002
 vitamins-0.002
array-0.001
 avocado-0.001
Token and
Token ID290
Feature activation+3.86e-01

Pos logit contributions
a+0.070
ah+0.064
fly+0.057
ch+0.056
be+0.055
Neg logit contributions
 disl-0.106
ados-0.102
 vitamins-0.101
array-0.100
 court-0.098
Token the
Token ID262
Feature activation-1.29e-01

Pos logit contributions
a+0.028
ah+0.025
-+0.024
be+0.024
fly+0.023
Neg logit contributions
 disl-0.021
 Mickey-0.020
ados-0.020
array-0.019
 avocado-0.019
Token door
Token ID3420
Feature activation+5.75e-01

Pos logit contributions
 disl+0.007
array+0.006
 vitamins+0.006
ados+0.006
 avocado+0.006
Neg logit contributions
a-0.010
ah-0.009
--0.009
fly-0.008
be-0.008
Token One
Token ID1881
Feature activation-7.81e-01

Pos logit contributions
ah+0.014
-+0.013
 of+0.013
 passenger+0.013
 too+0.012
Neg logit contributions
 disl-0.013
ados-0.012
 vitamins-0.012
affles-0.011
 av-0.011
Token day
Token ID1110
Feature activation+9.92e-01

Pos logit contributions
 avocado+0.041
 disl+0.037
 Mickey+0.036
 court+0.036
array+0.035
Neg logit contributions
a-0.054
be-0.050
fly-0.048
ist-0.047
ah-0.046
Token,
Token ID11
Feature activation-2.46e-01

Pos logit contributions
a+0.039
-+0.034
ah+0.030
be+0.030
ch+0.027
Neg logit contributions
 disl-0.088
ados-0.085
 vitamins-0.084
array-0.082
 avocado-0.080
Token he
Token ID339
Feature activation-1.75e-02

Pos logit contributions
 disl+0.014
ados+0.013
 vitamins+0.013
array+0.012
 avocado+0.012
Neg logit contributions
a-0.018
--0.016
ah-0.015
be-0.015
ch-0.015
Token stumbled
Token ID24241
Feature activation-1.34e+00

Pos logit contributions
 disl+0.001
ados+0.001
 vitamins+0.001
array+0.001
 Mickey+0.001
Neg logit contributions
a-0.001
--0.001
be-0.001
ah-0.001
ch-0.001
Token across
Token ID1973
Feature activation+1.53e+00

Pos logit contributions
 avocado+0.091
ados+0.091
array+0.090
 court+0.090
 Mickey+0.089
Neg logit contributions
a-0.058
 spe-0.052
ah-0.052
fly-0.052
be-0.050
Token a
Token ID257
Feature activation+6.20e-01

Pos logit contributions
a+0.071
-+0.062
ah+0.056
be+0.056
ch+0.051
Neg logit contributions
 disl-0.124
ados-0.120
 vitamins-0.116
array-0.115
 Mickey-0.113
Token big
Token ID1263
Feature activation-5.76e-01

Pos logit contributions
a+0.038
ah+0.033
be+0.033
-+0.033
less+0.030
Neg logit contributions
 disl-0.038
 avocado-0.038
 Mickey-0.037
ados-0.037
array-0.037
Token box
Token ID3091
Feature activation+5.79e-01

Pos logit contributions
 disl+0.037
ados+0.036
array+0.035
 Mickey+0.034
 avocado+0.034
Neg logit contributions
a-0.037
--0.031
be-0.031
ah-0.031
ch-0.028
Token in
Token ID287
Feature activation-1.14e-01

Pos logit contributions
a+0.029
ah+0.024
be+0.022
ch+0.022
-+0.021
Neg logit contributions
 avocado-0.042
array-0.041
 court-0.041
 Mickey-0.040
 av-0.039
Token his
Token ID465
Feature activation+5.59e-01

Pos logit contributions
 disl+0.008
ados+0.008
 vitamins+0.008
array+0.008
 Mickey+0.008
Neg logit contributions
a-0.006
--0.005
ah-0.005
be-0.005
ch-0.005
Token bright
Token ID6016
Feature activation+8.17e-01

Pos logit contributions
 disl+0.011
ados+0.011
 avocado+0.011
array+0.010
 vitamins+0.010
Neg logit contributions
a-0.013
ah-0.011
be-0.011
--0.010
ba-0.010
Token pattern
Token ID3912
Feature activation-2.57e-01

Pos logit contributions
a+0.059
be+0.048
ah+0.048
ba+0.047
ber+0.046
Neg logit contributions
 avocado-0.047
ados-0.045
 disl-0.045
array-0.043
 vitamins-0.042
Token in
Token ID287
Feature activation+2.25e-02

Pos logit contributions
ados+0.018
 avocado+0.018
 av+0.017
 disl+0.017
 vitamins+0.017
Neg logit contributions
a-0.012
ah-0.011
be-0.011
 passenger-0.010
fly-0.010
Token the
Token ID262
Feature activation-7.55e-02

Pos logit contributions
a+0.001
-+0.001
ah+0.001
be+0.001
ch+0.001
Neg logit contributions
 disl-0.002
ados-0.002
 vitamins-0.002
array-0.001
 Mickey-0.001
Token milk
Token ID7545
Feature activation-4.47e-01

Pos logit contributions
 disl+0.004
ados+0.004
array+0.004
 avocado+0.004
 vitamins+0.004
Neg logit contributions
a-0.005
--0.005
ah-0.005
be-0.004
fly-0.004
Token.
Token ID13
Feature activation+3.86e-01

Pos logit contributions
ados+0.032
 avocado+0.031
array+0.031
 Mickey+0.030
 disl+0.030
Neg logit contributions
a-0.023
ah-0.019
be-0.019
--0.019
ch-0.018
Token She
Token ID1375
Feature activation-5.00e-01

Pos logit contributions
a+0.022
 of+0.019
-+0.018
be+0.017
less+0.017
Neg logit contributions
ados-0.027
 disl-0.026
array-0.026
 vitamins-0.026
 av-0.025
Token feels
Token ID5300
Feature activation-1.98e+00

Pos logit contributions
 disl+0.033
ados+0.032
 vitamins+0.031
array+0.030
 Mickey+0.030
Neg logit contributions
a-0.031
--0.027
ah-0.026
be-0.026
ch-0.024
Token so
Token ID523
Feature activation-1.34e+00

Pos logit contributions
 disl+0.140
 vitamins+0.130
ados+0.130
 avocado+0.128
 Mickey+0.128
Neg logit contributions
a-0.112
ah-0.101
--0.097
be-0.096
ch-0.089
Token happy
Token ID3772
Feature activation+4.98e-01

Pos logit contributions
ados+0.108
 disl+0.102
array+0.102
 Mickey+0.101
 vitamins+0.100
Neg logit contributions
a-0.068
--0.058
be-0.053
ah-0.047
 closer-0.046
Token and
Token ID290
Feature activation+3.11e-01

Pos logit contributions
a+0.026
ah+0.022
be+0.021
ch+0.019
-+0.019
Neg logit contributions
 disl-0.038
ados-0.037
 avocado-0.035
 vitamins-0.035
array-0.035
Token his
Token ID465
Feature activation+4.14e-01

Pos logit contributions
 disl+0.045
ados+0.044
array+0.042
 vitamins+0.042
 Mickey+0.041
Neg logit contributions
a-0.036
--0.033
ah-0.029
be-0.029
ch-0.027
Token homework
Token ID26131
Feature activation-9.14e-02

Pos logit contributions
a+0.035
-+0.034
ah+0.032
be+0.031
ch+0.029
Neg logit contributions
 disl-0.017
ados-0.017
 Mickey-0.015
array-0.015
 vitamins-0.015
Token.
Token ID13
Feature activation+3.03e-01

Pos logit contributions
 disl+0.007
ados+0.007
 vitamins+0.007
array+0.007
 Mickey+0.007
Neg logit contributions
a-0.004
ah-0.004
--0.004
be-0.004
ch-0.003
Token He
Token ID679
Feature activation-5.42e-01

Pos logit contributions
-+0.015
a+0.014
 too+0.013
be+0.012
 driver+0.012
Neg logit contributions
 disl-0.022
irs-0.021
 vitamins-0.019
ados-0.019
Mic-0.019
Token went
Token ID1816
Feature activation-1.65e+00

Pos logit contributions
 disl+0.034
ados+0.033
 vitamins+0.032
array+0.031
 Mickey+0.031
Neg logit contributions
a-0.036
--0.032
ah-0.031
be-0.030
ch-0.028
Token to
Token ID284
Feature activation-8.83e-02

Pos logit contributions
 court+0.116
 Mickey+0.115
ados+0.114
array+0.113
 disl+0.111
Neg logit contributions
a-0.091
ah-0.077
be-0.076
fly-0.068
iest-0.068
Token his
Token ID465
Feature activation+4.12e-01

Pos logit contributions
ados+0.007
 disl+0.007
 vitamins+0.007
array+0.007
 Eating+0.007
Neg logit contributions
a-0.004
--0.004
 closer-0.003
 of-0.003
 faster-0.003
Token room
Token ID2119
Feature activation+1.31e-01

Pos logit contributions
a+0.026
-+0.023
be+0.021
ah+0.021
ch+0.019
Neg logit contributions
 disl-0.028
ados-0.027
 vitamins-0.026
array-0.025
 Mickey-0.025
Token and
Token ID290
Feature activation+2.27e-01

Pos logit contributions
a+0.006
ah+0.005
be+0.005
ch+0.005
fly+0.004
Neg logit contributions
array-0.010
ados-0.010
 court-0.010
 disl-0.010
 avocado-0.010
Token played
Token ID2826
Feature activation-1.12e+00

Pos logit contributions
a+0.014
-+0.012
be+0.011
ah+0.011
ch+0.010
Neg logit contributions
 disl-0.016
ados-0.015
 vitamins-0.015
array-0.014
 avocado-0.014
Token with
Token ID351
Feature activation-1.87e+00

Pos logit contributions
 disl+0.085
ados+0.084
 vitamins+0.080
 Mickey+0.080
array+0.080
Neg logit contributions
a-0.059
ah-0.049
be-0.048
--0.046
fly-0.043
Token
Token ID198
Feature activation-4.29e-01

Pos logit contributions
 disl+0.029
ados+0.028
array+0.027
 vitamins+0.027
 Mickey+0.026
Neg logit contributions
a-0.028
--0.024
be-0.023
ah-0.023
ch-0.021
TokenThey
Token ID2990
Feature activation+3.05e-01

Pos logit contributions
 disl+0.030
ados+0.029
 vitamins+0.028
array+0.028
 Mickey+0.028
Neg logit contributions
a-0.024
--0.021
ah-0.021
be-0.020
ch-0.019
Token keep
Token ID1394
Feature activation-7.40e-01

Pos logit contributions
a+0.020
-+0.017
ah+0.017
be+0.017
ch+0.015
Neg logit contributions
 disl-0.020
ados-0.019
 vitamins-0.018
array-0.018
 Mickey-0.018
Token playing
Token ID2712
Feature activation-1.16e+00

Pos logit contributions
 disl+0.053
 vitamins+0.049
ados+0.049
array+0.048
 Bruce+0.047
Neg logit contributions
a-0.041
--0.038
be-0.035
ah-0.033
 closer-0.032
Token with
Token ID351
Feature activation-1.74e+00

Pos logit contributions
ados+0.089
 disl+0.088
 avocado+0.088
 court+0.086
 av+0.084
Neg logit contributions
a-0.059
ah-0.052
be-0.047
ch-0.044
fly-0.043
Token clay
Token ID21558
Feature activation-1.18e+00

Pos logit contributions
 disl+0.122
ados+0.119
 vitamins+0.115
array+0.114
 Mickey+0.113
Neg logit contributions
a-0.100
--0.086
ah-0.084
be-0.083
ch-0.076
Token and
Token ID290
Feature activation+2.78e-01

Pos logit contributions
ados+0.095
 disl+0.091
 avocado+0.090
 vitamins+0.090
 court+0.088
Neg logit contributions
a-0.056
ah-0.049
be-0.044
ch-0.044
--0.041
Token making
Token ID1642
Feature activation+7.10e-01

Pos logit contributions
a+0.018
-+0.016
ah+0.016
be+0.016
ch+0.015
Neg logit contributions
 disl-0.017
ados-0.017
 vitamins-0.016
array-0.016
 Mickey-0.016
Token different
Token ID1180
Feature activation+1.23e+00

Pos logit contributions
a+0.040
-+0.035
be+0.032
ah+0.032
ch+0.030
Neg logit contributions
 disl-0.050
ados-0.049
array-0.048
 vitamins-0.047
 Mickey-0.047
Token things
Token ID1243
Feature activation-2.45e+00

Pos logit contributions
a+0.079
-+0.072
be+0.066
ah+0.066
y+0.062
Neg logit contributions
 disl-0.077
ados-0.074
array-0.072
 Mickey-0.072
 vitamins-0.071
Token.
Token ID13
Feature activation+2.73e-01

Pos logit contributions
 disl+0.172
ados+0.166
 avocado+0.164
 vitamins+0.161
 Mickey+0.158
Neg logit contributions
a-0.137
ah-0.126
be-0.112
ch-0.105
--0.104
Token,
Token ID11
Feature activation-2.65e-01

Pos logit contributions
a+0.070
be+0.060
ah+0.058
-+0.057
ch+0.053
Neg logit contributions
 disl-0.111
ados-0.108
 Mickey-0.106
 avocado-0.103
 Bruce-0.103
Token there
Token ID612
Feature activation+4.71e-01

Pos logit contributions
 Mickey+0.019
 avocado+0.018
 Freddy+0.018
 Bruce+0.018
 disl+0.018
Neg logit contributions
a-0.012
be-0.012
ah-0.012
--0.011
ch-0.010
Token were
Token ID547
Feature activation-4.14e-02

Pos logit contributions
a+0.020
-+0.016
be+0.016
ah+0.016
ch+0.014
Neg logit contributions
 disl-0.040
ados-0.039
 vitamins-0.038
array-0.038
 Mickey-0.037
Token two
Token ID734
Feature activation-5.05e-01

Pos logit contributions
 disl+0.003
ados+0.003
array+0.003
 vitamins+0.003
 courtroom+0.003
Neg logit contributions
a-0.002
be-0.002
--0.002
ch-0.002
ah-0.002
Token friends
Token ID2460
Feature activation-2.37e+00

Pos logit contributions
ados+0.030
 disl+0.030
 Mickey+0.029
 vitamins+0.029
array+0.029
Neg logit contributions
a-0.033
ah-0.028
--0.028
be-0.028
ch-0.026
Token.
Token ID13
Feature activation+4.56e-01

Pos logit contributions
 Mickey+0.144
ados+0.136
 disl+0.136
array+0.132
 court+0.131
Neg logit contributions
a-0.149
ah-0.130
ch-0.125
be-0.125
iest-0.123
Token One
Token ID1881
Feature activation-7.25e-01

Pos logit contributions
a+0.033
ah+0.030
-+0.029
y+0.029
be+0.029
Neg logit contributions
 disl-0.024
ados-0.024
 vitamins-0.022
array-0.021
 av-0.020
Token day
Token ID1110
Feature activation+8.00e-01

Pos logit contributions
 disl+0.038
 avocado+0.037
 Freddy+0.036
 Mickey+0.035
 Her+0.034
Neg logit contributions
a-0.043
be-0.041
cher-0.040
ba-0.040
ah-0.039
Token,
Token ID11
Feature activation-2.77e-01

Pos logit contributions
a+0.040
ah+0.033
be+0.032
-+0.030
fly+0.029
Neg logit contributions
ados-0.061
 disl-0.060
 Mickey-0.058
 avocado-0.057
 vitamins-0.057
Token they
Token ID484
Feature activation+6.46e-01

Pos logit contributions
 Mickey+0.013
ados+0.013
 disl+0.013
 Freddy+0.012
 avocado+0.012
Neg logit contributions
a-0.022
be-0.020
ah-0.019
--0.019
ist-0.018
Token decided
Token ID3066
Feature activation-2.12e+00

Pos logit contributions
a+0.035
-+0.029
be+0.028
ah+0.027
y+0.026
Neg logit contributions
 disl-0.051
ados-0.049
 vitamins-0.047
array-0.047
 avocado-0.045
Token,
Token ID11
Feature activation-4.38e-01

Pos logit contributions
a+0.067
ah+0.067
iest+0.065
ch+0.065
ilot+0.064
Neg logit contributions
 avocado-0.064
 Mickey-0.063
 court-0.062
 disl-0.061
ados-0.060
Token always
Token ID1464
Feature activation+2.44e+00

Pos logit contributions
 disl+0.035
ados+0.034
 Mickey+0.034
 avocado+0.034
 vitamins+0.033
Neg logit contributions
a-0.020
be-0.016
--0.016
ah-0.015
ch-0.014
Token running
Token ID2491
Feature activation+5.50e-01

Pos logit contributions
a+0.168
ah+0.153
-+0.145
be+0.144
ch+0.140
Neg logit contributions
 disl-0.142
array-0.128
ados-0.128
 vitamins-0.127
 Mickey-0.125
Token and
Token ID290
Feature activation+2.15e-01

Pos logit contributions
a+0.034
ah+0.031
be+0.030
fly+0.029
iest+0.027
Neg logit contributions
ados-0.033
 disl-0.033
 court-0.031
 Mickey-0.031
array-0.031
Token jumping
Token ID14284
Feature activation+9.18e-01

Pos logit contributions
a+0.014
-+0.013
be+0.012
ah+0.012
ch+0.011
Neg logit contributions
 disl-0.013
ados-0.013
 vitamins-0.012
array-0.012
 Mickey-0.012
Token around
Token ID1088
Feature activation-3.46e-01

Pos logit contributions
a+0.048
be+0.041
ah+0.041
fly+0.036
-+0.036
Neg logit contributions
ados-0.066
 disl-0.063
 avocado-0.062
 Mickey-0.061
array-0.061
Token.
Token ID13
Feature activation+2.86e-01

Pos logit contributions
ados+0.026
 disl+0.026
 Mickey+0.025
 avocado+0.025
array+0.025
Neg logit contributions
a-0.018
ah-0.015
be-0.014
--0.014
ch-0.013
Token
Token ID198
Feature activation-3.78e-01

Pos logit contributions
a+0.013
-+0.011
 of+0.011
ah+0.010
ch+0.010
Neg logit contributions
 disl-0.024
ados-0.023
array-0.023
 vitamins-0.022
 av-0.021
Token
Token ID198
Feature activation-3.75e-01

Pos logit contributions
 disl+0.021
ados+0.020
 vitamins+0.019
 Mickey+0.019
array+0.019
Neg logit contributions
a-0.027
--0.024
ah-0.023
be-0.023
ch-0.022
TokenOne
Token ID3198
Feature activation+5.97e-01

Pos logit contributions
 disl+0.023
ados+0.022
 vitamins+0.021
array+0.021
 Mickey+0.021
Neg logit contributions
a-0.025
--0.022
ah-0.021
be-0.021
fly-0.020
Token day
Token ID1110
Feature activation+7.76e-01

Pos logit contributions
fly+0.044
be+0.043
a+0.043
ist+0.042
cher+0.042
Neg logit contributions
 avocado-0.024
 disl-0.023
 broccoli-0.020
 court-0.020
 Mickey-0.019
Token "
Token ID366
Feature activation+2.59e+00

Pos logit contributions
 Mickey+0.015
 disl+0.015
ados+0.015
 Bruce+0.014
array+0.014
Neg logit contributions
a-0.021
ah-0.018
--0.018
be-0.018
iest-0.017
TokenLet
Token ID5756
Feature activation+4.60e-01

Pos logit contributions
a+0.183
-+0.170
ah+0.155
be+0.153
less+0.145
Neg logit contributions
 disl-0.144
ados-0.133
 vitamins-0.130
array-0.130
 Mickey-0.128
Token's
Token ID338
Feature activation-7.55e-01

Pos logit contributions
a+0.026
-+0.023
be+0.022
ah+0.022
ch+0.020
Neg logit contributions
 disl-0.033
ados-0.033
 vitamins-0.032
array-0.031
 avocado-0.031
Token take
Token ID1011
Feature activation-1.18e+00

Pos logit contributions
 vitamins+0.059
ados+0.058
 disl+0.057
array+0.055
 av+0.051
Neg logit contributions
a-0.037
--0.032
 closer-0.030
be-0.029
 of-0.029
Token it
Token ID340
Feature activation-6.32e-01

Pos logit contributions
 disl+0.087
ados+0.083
array+0.082
 vitamins+0.081
 Mickey+0.079
Neg logit contributions
a-0.066
--0.058
be-0.054
ah-0.053
ch-0.050
Token home
Token ID1363
Feature activation-2.47e+00

Pos logit contributions
ados+0.041
 Mickey+0.040
 disl+0.039
 avocado+0.039
array+0.039
Neg logit contributions
a-0.037
ah-0.032
be-0.032
--0.030
fly-0.029
Token and
Token ID290
Feature activation+3.39e-01

Pos logit contributions
ados+0.161
 court+0.160
 disl+0.159
 Mickey+0.158
 avocado+0.157
Neg logit contributions
a-0.126
ah-0.122
ch-0.116
be-0.112
fly-0.106
Token show
Token ID905
Feature activation+1.06e+00

Pos logit contributions
a+0.018
-+0.016
 closer+0.016
be+0.015
 of+0.015
Neg logit contributions
ados-0.024
 disl-0.023
 vitamins-0.023
array-0.023
iveness-0.021
Token it
Token ID340
Feature activation-6.35e-01

Pos logit contributions
a+0.062
-+0.055
be+0.050
ah+0.049
ch+0.046
Neg logit contributions
 disl-0.077
ados-0.073
array-0.073
 vitamins-0.071
 avocado-0.069
Token to
Token ID284
Feature activation+5.79e-02

Pos logit contributions
 disl+0.050
ados+0.048
 vitamins+0.047
 Mickey+0.046
 avocado+0.045
Neg logit contributions
a-0.030
ah-0.026
be-0.025
--0.025
ch-0.022
Token mom
Token ID1995
Feature activation+1.70e-01

Pos logit contributions
a+0.003
-+0.003
be+0.003
ch+0.003
ah+0.003
Neg logit contributions
array-0.004
 disl-0.004
ados-0.004
 vitamins-0.004
 av-0.004
Tokenopl
Token ID20106
Feature activation-1.51e+00

Pos logit contributions
a+0.032
-+0.030
ah+0.029
be+0.029
ch+0.028
Neg logit contributions
 disl-0.009
ados-0.009
 vitamins-0.008
 Mickey-0.008
array-0.008
Tokenane
Token ID1531
Feature activation+1.76e+00

Pos logit contributions
ados+0.100
 disl+0.099
array+0.090
 avocado+0.090
iveness+0.089
Neg logit contributions
a-0.088
ah-0.074
--0.072
be-0.070
 closer-0.069
Token crashed
Token ID14997
Feature activation+2.26e+00

Pos logit contributions
a+0.125
less+0.118
ah+0.105
iest+0.103
ac+0.101
Neg logit contributions
 disl-0.075
 cries-0.074
ados-0.070
 avocado-0.067
 Mickey-0.067
Token on
Token ID319
Feature activation+5.18e-01

Pos logit contributions
a+0.131
ah+0.118
be+0.110
 passenger+0.104
iest+0.103
Neg logit contributions
ados-0.147
array-0.131
 Mickey-0.128
 av-0.127
 avocado-0.125
Token the
Token ID262
Feature activation-1.72e-01

Pos logit contributions
a+0.029
-+0.025
ah+0.024
be+0.024
ch+0.022
Neg logit contributions
 disl-0.037
ados-0.036
 vitamins-0.035
array-0.035
 Mickey-0.034
Token floor
Token ID4314
Feature activation-3.48e+00

Pos logit contributions
 disl+0.006
ados+0.006
 avocado+0.006
array+0.006
 vitamins+0.006
Neg logit contributions
a-0.015
ah-0.014
--0.014
be-0.013
less-0.013
Token.
Token ID13
Feature activation+1.83e-01

Pos logit contributions
ados+0.210
 disl+0.209
array+0.206
 court+0.206
 vitamins+0.200
Neg logit contributions
a-0.205
ah-0.183
ch-0.168
be-0.168
--0.161
Token It
Token ID632
Feature activation+5.49e-01

Pos logit contributions
a+0.010
 of+0.009
ch+0.009
-+0.008
 on+0.008
Neg logit contributions
 disl-0.012
array-0.012
ados-0.011
 av-0.011
 vitamins-0.011
Token broke
Token ID6265
Feature activation+3.02e-01

Pos logit contributions
a+0.036
less+0.032
-+0.031
be+0.031
ah+0.031
Neg logit contributions
 disl-0.029
ados-0.027
 Mickey-0.027
 avocado-0.027
 vitamins-0.027
Token into
Token ID656
Feature activation-2.60e+00

Pos logit contributions
a+0.016
ah+0.014
be+0.013
ch+0.012
-+0.012
Neg logit contributions
ados-0.022
array-0.020
 Mickey-0.020
 avocado-0.020
 disl-0.020
Token pieces
Token ID5207
Feature activation-3.39e+00

Pos logit contributions
 disl+0.169
ados+0.163
 vitamins+0.157
array+0.156
 Mickey+0.154
Neg logit contributions
a-0.164
--0.144
be-0.138
ah-0.138
ch-0.128
Token They
Token ID1119
Feature activation-1.13e+00

Pos logit contributions
 disl+0.019
 vitamins+0.018
array+0.018
 court+0.018
ados+0.018
Neg logit contributions
a-0.017
ah-0.015
--0.014
be-0.013
fly-0.013
Token are
Token ID389
Feature activation+8.58e-01

Pos logit contributions
 disl+0.076
ados+0.072
 vitamins+0.070
array+0.069
 Mickey+0.069
Neg logit contributions
a-0.067
--0.060
ah-0.057
be-0.057
ch-0.053
Token fragile
Token ID21049
Feature activation-2.27e+00

Pos logit contributions
a+0.051
-+0.044
ah+0.044
be+0.043
ch+0.040
Neg logit contributions
 disl-0.058
ados-0.056
 vitamins-0.055
 Mickey-0.054
array-0.054
Token and
Token ID290
Feature activation-5.18e-01

Pos logit contributions
ados+0.182
 disl+0.180
 vitamins+0.172
 avocado+0.170
array+0.169
Neg logit contributions
a-0.110
ah-0.091
be-0.084
--0.081
ch-0.079
Token the
Token ID262
Feature activation-4.64e-01

Pos logit contributions
 disl+0.033
ados+0.031
 vitamins+0.031
 Mickey+0.030
 avocado+0.029
Neg logit contributions
a-0.034
ah-0.030
--0.030
be-0.029
ch-0.026
Token ground
Token ID2323
Feature activation-3.23e+00

Pos logit contributions
 disl+0.029
ados+0.028
 vitamins+0.028
 avocado+0.027
 Mickey+0.027
Neg logit contributions
a-0.030
--0.026
ah-0.025
be-0.025
ch-0.023
Token is
Token ID318
Feature activation+1.62e-01

Pos logit contributions
 disl+0.230
ados+0.218
 vitamins+0.215
array+0.215
 avocado+0.212
Neg logit contributions
a-0.166
ah-0.148
be-0.136
--0.132
ch-0.124
Token hard
Token ID1327
Feature activation-7.09e-01

Pos logit contributions
a+0.011
ah+0.010
-+0.009
be+0.009
iest+0.009
Neg logit contributions
 vitamins-0.010
 disl-0.009
 Mickey-0.009
 avocado-0.009
ados-0.009
Token!"
Token ID2474
Feature activation-2.85e+00

Pos logit contributions
 disl+0.058
ados+0.057
 vitamins+0.056
array+0.056
 Mickey+0.054
Neg logit contributions
a-0.032
ah-0.026
--0.024
be-0.024
ch-0.022
Token
Token ID198
Feature activation-6.84e-01

Pos logit contributions
 disl+0.186
ados+0.184
 vitamins+0.181
array+0.178
 avocado+0.170
Neg logit contributions
a-0.180
--0.155
be-0.148
ah-0.145
 of-0.138
Token
Token ID198
Feature activation-6.15e-01

Pos logit contributions
ados+0.051
 disl+0.048
 vitamins+0.048
array+0.047
 avocado+0.046
Neg logit contributions
a-0.040
--0.034
be-0.031
ah-0.030
ch-0.030
Token pull
Token ID2834
Feature activation-1.89e-01

Pos logit contributions
a+0.001
 of+0.001
-+0.001
be+0.001
ah+0.001
Neg logit contributions
ados-0.002
 vitamins-0.002
 disl-0.002
array-0.002
 courtroom-0.002
Token it
Token ID340
Feature activation-6.54e-01

Pos logit contributions
 disl+0.016
array+0.015
 vitamins+0.014
ados+0.014
 Mickey+0.014
Neg logit contributions
a-0.009
--0.008
ah-0.007
be-0.007
 closer-0.007
Token out
Token ID503
Feature activation+9.53e-01

Pos logit contributions
ados+0.047
 disl+0.046
 Mickey+0.046
 avocado+0.045
array+0.045
Neg logit contributions
a-0.035
be-0.029
ah-0.029
--0.028
ch-0.025
Token of
Token ID286
Feature activation+1.82e+00

Pos logit contributions
a+0.047
ah+0.040
be+0.038
rot+0.036
fly+0.036
Neg logit contributions
ados-0.067
 avocado-0.065
 Mickey-0.065
 av-0.063
 vitamins-0.063
Token the
Token ID262
Feature activation-1.88e-01

Pos logit contributions
a+0.082
-+0.076
ah+0.070
 closer+0.066
ch+0.064
Neg logit contributions
 disl-0.144
ados-0.138
 vitamins-0.135
array-0.133
iveness-0.125
Token ground
Token ID2323
Feature activation-3.73e+00

Pos logit contributions
 disl+0.013
 vitamins+0.010
array+0.010
ados+0.010
quit+0.010
Neg logit contributions
a-0.012
--0.011
 closer-0.011
y-0.010
be-0.010
Token and
Token ID290
Feature activation+3.53e-01

Pos logit contributions
ados+0.275
 disl+0.271
array+0.268
 avocado+0.266
 Mickey+0.265
Neg logit contributions
a-0.182
ah-0.153
be-0.150
--0.143
ch-0.141
Token take
Token ID1011
Feature activation-1.17e+00

Pos logit contributions
a+0.019
-+0.017
 closer+0.016
be+0.015
ah+0.015
Neg logit contributions
ados-0.025
 vitamins-0.025
 disl-0.025
array-0.024
iveness-0.023
Token it
Token ID340
Feature activation-6.62e-01

Pos logit contributions
 disl+0.096
array+0.090
ados+0.090
 vitamins+0.088
 Mickey+0.084
Neg logit contributions
a-0.056
--0.053
be-0.045
ah-0.045
ch-0.045
Token home
Token ID1363
Feature activation-2.51e+00

Pos logit contributions
 disl+0.054
ados+0.053
 vitamins+0.051
array+0.051
 Mickey+0.051
Neg logit contributions
a-0.030
--0.024
ah-0.024
be-0.024
ch-0.021
Token.
Token ID13
Feature activation+4.07e-01

Pos logit contributions
 disl+0.191
ados+0.190
 avocado+0.184
 Mickey+0.183
array+0.181
Neg logit contributions
a-0.123
ah-0.107
be-0.101
ch-0.097
--0.096
Token zoom
Token ID19792
Feature activation+1.66e+00

Pos logit contributions
 disl+0.013
ados+0.012
 vitamins+0.012
array+0.012
 Mickey+0.012
Neg logit contributions
a-0.012
--0.011
ah-0.010
be-0.010
ch-0.010
Token and
Token ID290
Feature activation+3.00e-01

Pos logit contributions
a+0.092
be+0.079
ah+0.076
fly+0.075
less+0.072
Neg logit contributions
 disl-0.110
ados-0.108
 Mickey-0.099
 vitamins-0.098
 court-0.098
Token crash
Token ID7014
Feature activation+1.93e+00

Pos logit contributions
a+0.019
-+0.016
ah+0.015
be+0.015
less+0.014
Neg logit contributions
 disl-0.020
ados-0.019
 vitamins-0.019
array-0.018
 Mickey-0.018
Token on
Token ID319
Feature activation+5.00e-01

Pos logit contributions
a+0.093
ah+0.077
be+0.075
-+0.070
fly+0.067
Neg logit contributions
ados-0.149
 disl-0.148
 Mickey-0.141
 vitamins-0.141
array-0.140
Token the
Token ID262
Feature activation-1.39e-01

Pos logit contributions
a+0.029
-+0.025
ah+0.024
be+0.024
ch+0.022
Neg logit contributions
 disl-0.035
ados-0.034
 vitamins-0.033
array-0.033
 Mickey-0.032
Token floor
Token ID4314
Feature activation-3.54e+00

Pos logit contributions
 disl+0.005
ados+0.005
 vitamins+0.005
array+0.005
 avocado+0.005
Neg logit contributions
a-0.013
--0.011
ah-0.011
be-0.011
fly-0.011
Token.
Token ID13
Feature activation+3.68e-01

Pos logit contributions
 disl+0.227
ados+0.226
 vitamins+0.225
 court+0.222
 avocado+0.220
Neg logit contributions
a-0.193
ah-0.171
be-0.162
ch-0.160
--0.158
Token He
Token ID679
Feature activation-4.03e-01

Pos logit contributions
ah+0.025
ch+0.023
 of+0.022
a+0.022
-+0.022
Neg logit contributions
ados-0.021
 disl-0.021
array-0.020
 vitamins-0.019
handed-0.019
Token also
Token ID635
Feature activation+1.13e+00

Pos logit contributions
 disl+0.025
 vitamins+0.024
array+0.023
 avocado+0.023
 Mickey+0.023
Neg logit contributions
a-0.022
less-0.021
--0.020
ch-0.019
be-0.019
Token had
Token ID550
Feature activation+2.79e-01

Pos logit contributions
a+0.062
-+0.055
ah+0.051
be+0.050
less+0.048
Neg logit contributions
 disl-0.082
 vitamins-0.076
array-0.075
ados-0.074
 Mickey-0.073
Token a
Token ID257
Feature activation+7.03e-01

Pos logit contributions
a+0.016
-+0.014
ah+0.014
be+0.013
fly+0.013
Neg logit contributions
 disl-0.019
ados-0.018
 vitamins-0.018
array-0.018
 Mickey-0.018