TOP ACTIVATIONS
MAX = 0.140

play outside and pick l imes from the tree in her
to swinging and eating l imes with Andy tomorrow . <|endoftext|>
Tim loved to eat l imes . He thought l imes
, she was picking l imes when it started to rain
She loved to eat l imes because they were so tasty
little girl stopped picking l imes and watched the sky shine
pond . She always brought bread and seeds for them .
likes to play with l imes . She likes how they
They take some chips and salsa . They put them in
oppy accidentally bumped into Ho pper 's ear . Ho pper
. Is wine made from grape ? â
bite of the carrot with salsa . They felt a hot
both laughed and threw more bread to the fish .
They put cheese and pepper oni on top . They bake
and one is full of salsa . " H
every day Tim would eat pineapple again . He enjoyed eating
jar . He tried to trap it inside . The mosquito
So she brought bread and leaves to the park
with lots of other l imes . The lime was so
walked and he ate only bread and apples .

MIN ACTIVATIONS
MIN = -0.166

probably celebrating their own birth days . Just when he was
time to celebrate their birth days . Max had a lot
And that 's why Tues days are so important . <|endoftext|>
liked to celebrate their birth days . Tim 's birthday was
she bowed , the town spe ople stopped to admire her
heard before was the door bell . From then on ,
year , on their birth days , they would celebrate together
. It is the door bell . Mom my is home
ones are yellow and the un ri pe ones are green
to celebrate all her birth days together . <|endoftext|> Once upon
Jane celebrated both their birth days together . They played games
so special about Wed nes days ?" Max laughed
the village back to its former glory !"
pond and it was the tid iest water she had ever
She thought it was the tid iest thing ever and knew
you ? This is my wardrobe . Go away !"
. She learned that birth days are not about cakes and
! The town spe ople were sad and scared
with the things the driver unp acked .
back the village to its former state . With the help

INTERVAL 0.064 - 0.140
CONTAINS 0.514%

it on a nearby tree branch . The squirrel happily chat
lake and catch lots of fish . Sometimes the fish were
of y ummy treats . Strip was a very clever k
pretended to sip and nib ble and chat .
Sit ." The children did as they were told and sat

INTERVAL -0.013 - 0.064
CONTAINS 76.112%

to play outside in her backyard . One day , she
the bed . She put her dolls and her
be careful with the tickets because they both wanted to celebrate
very charming and friendly . " Yes , please
was so tidy ! Inside , there lived a kind princess

INTERVAL -0.089 - -0.013
CONTAINS 23.305%

through nature . He was excited to explore the world and
her Mum the hook . Her Mum said that it was
. The next day , Fin and his friends
her mom my . Her mom my saw her and said
big hole on top called a volcano . The volcano was

INTERVAL -0.166 - -0.089
CONTAINS 0.069%

had gone from the hum bl est sack in the world
it to you for your birthday ." Anna says
help but they were both asleep . In the end ,
needle and a cold st eth oscope . The doctor made
. " A hotel is a big house with
Token play
Token ID711
Feature activation-2.21e-02

Pos logit contributions
bell+0.010
spe+0.009
 Mechan+0.009
days+0.009
lights+0.009
Neg logit contributions
 Remy-0.008
isi-0.008
imes-0.007
aw-0.007
Le-0.007
Token outside
Token ID2354
Feature activation-2.50e-02

Pos logit contributions
bell+0.038
days+0.036
 Mechan+0.033
 t+0.032
 stuffed+0.032
Neg logit contributions
aw-0.044
 Remy-0.040
Le-0.040
una-0.038
imes-0.038
Token and
Token ID290
Feature activation+6.77e-03

Pos logit contributions
bell+0.057
 Mechan+0.056
days+0.052
 spoiler+0.051
 stuffed+0.048
Neg logit contributions
aw-0.034
Le-0.029
 Remy-0.028
imes-0.026
P-0.026
Token pick
Token ID2298
Feature activation+5.00e-02

Pos logit contributions
aw+0.014
Le+0.013
 Remy+0.013
imes+0.013
isi+0.013
Neg logit contributions
bell-0.010
days-0.010
 Mechan-0.009
 t-0.009
 stuffed-0.009
Token l
Token ID300
Feature activation+9.40e-02

Pos logit contributions
Le+0.091
isi+0.090
live+0.087
emy+0.085
iles+0.084
Neg logit contributions
 t-0.087
 stuffed-0.079
bell-0.075
 Gr-0.073
 py-0.073
Tokenimes
Token ID999
Feature activation+1.40e-01

Pos logit contributions
 hawk+0.110
Le+0.108
 Remy+0.104
 Duke+0.103
 Stan+0.103
Neg logit contributions
bell-0.200
days-0.189
 unp-0.189
 decor-0.185
 t-0.185
Token from
Token ID422
Feature activation-8.53e-03

Pos logit contributions
emy+0.371
aw+0.371
Le+0.366
iles+0.352
 hawk+0.347
Neg logit contributions
 t-0.120
bell-0.111
 unp-0.096
days-0.093
 decor-0.089
Token the
Token ID262
Feature activation+1.58e-02

Pos logit contributions
 t+0.013
bell+0.012
 stuffed+0.012
 Gr+0.011
 decor+0.011
Neg logit contributions
aw-0.019
Le-0.018
arling-0.017
isi-0.017
imes-0.017
Token tree
Token ID5509
Feature activation+2.02e-02

Pos logit contributions
aw+0.030
emy+0.027
iles+0.027
isi+0.027
imes+0.027
Neg logit contributions
 t-0.029
 stuffed-0.027
bell-0.025
 py-0.025
 Gr-0.025
Token in
Token ID287
Feature activation-9.38e-03

Pos logit contributions
aw+0.046
Le+0.044
isi+0.044
 Remy+0.043
imes+0.043
Neg logit contributions
bell-0.028
days-0.026
 t-0.025
 stuffed-0.023
 unp-0.023
Token her
Token ID607
Feature activation-7.24e-03

Pos logit contributions
bell+0.018
days+0.017
 Mechan+0.016
 stuffed+0.016
 t+0.016
Neg logit contributions
aw-0.016
Le-0.015
 Remy-0.014
isi-0.014
imes-0.014
Token to
Token ID284
Feature activation+4.02e-04

Pos logit contributions
bell+0.008
days+0.008
 Mechan+0.008
 stuffed+0.008
 t+0.007
Neg logit contributions
aw-0.006
 Remy-0.005
Le-0.005
 Sasha-0.005
imes-0.005
Token swinging
Token ID25635
Feature activation+2.92e-02

Pos logit contributions
aw+0.001
 Remy+0.001
Le+0.001
imes+0.001
isi+0.001
Neg logit contributions
bell-0.001
days-0.001
 t-0.001
 Mechan-0.001
 stuffed-0.001
Token and
Token ID290
Feature activation+1.16e-02

Pos logit contributions
aw+0.060
Le+0.055
 Remy+0.054
imes+0.054
isi+0.053
Neg logit contributions
bell-0.047
days-0.045
 t-0.042
 stuffed-0.042
 Mechan-0.041
Token eating
Token ID6600
Feature activation+5.97e-02

Pos logit contributions
aw+0.023
 Remy+0.021
Le+0.021
imes+0.020
isi+0.020
Neg logit contributions
bell-0.019
days-0.018
 Mechan-0.017
 t-0.017
 stuffed-0.017
Token l
Token ID300
Feature activation+9.40e-02

Pos logit contributions
aw+0.115
Le+0.108
isi+0.106
imes+0.104
 Remy+0.104
Neg logit contributions
bell-0.097
 t-0.095
days-0.093
 stuffed-0.091
 unp-0.087
Tokenimes
Token ID999
Feature activation+1.31e-01

Pos logit contributions
 hawk+0.100
 Remy+0.097
Le+0.096
 ram+0.095
 strangers+0.094
Neg logit contributions
days-0.195
bell-0.194
 unp-0.192
 decor-0.184
 t-0.179
Token with
Token ID351
Feature activation+1.12e-02

Pos logit contributions
aw+0.281
Le+0.259
imes+0.257
 Remy+0.256
isi+0.254
Neg logit contributions
bell-0.198
days-0.188
 t-0.178
 stuffed-0.173
 Mechan-0.169
Token Andy
Token ID12382
Feature activation+9.73e-03

Pos logit contributions
aw+0.022
arling+0.021
opard+0.021
Le+0.021
imes+0.021
Neg logit contributions
 t-0.017
bell-0.017
 stuffed-0.016
days-0.015
 unp-0.015
Token tomorrow
Token ID9439
Feature activation-5.43e-02

Pos logit contributions
aw+0.019
 Remy+0.018
Le+0.017
imes+0.017
isi+0.017
Neg logit contributions
bell-0.017
days-0.016
 Mechan-0.015
 t-0.014
 stuffed-0.014
Token.
Token ID13
Feature activation+1.79e-03

Pos logit contributions
bell+0.086
days+0.082
 t+0.078
 stuffed+0.076
 Mechan+0.074
Neg logit contributions
aw-0.113
Le-0.103
 Remy-0.102
imes-0.101
isi-0.101
Token<|endoftext|>
Token ID50256
Feature activation+1.42e-02

Pos logit contributions
aw+0.004
iles+0.004
Le+0.004
imes+0.004
una+0.004
Neg logit contributions
bell-0.003
days-0.002
 t-0.002
 unp-0.002
 Sus-0.002
Token Tim
Token ID5045
Feature activation-2.91e-04

Pos logit contributions
aw+0.001
 Remy+0.001
Le+0.001
imes+0.001
isi+0.001
Neg logit contributions
bell-0.001
days-0.001
 stuffed-0.001
 t-0.001
 py-0.001
Token loved
Token ID6151
Feature activation-2.52e-02

Pos logit contributions
bell+0.001
days+0.000
 stuffed+0.000
 Mechan+0.000
 t+0.000
Neg logit contributions
aw-0.001
Le-0.001
 Remy-0.001
una-0.000
isi-0.000
Token to
Token ID284
Feature activation-7.01e-03

Pos logit contributions
bell+0.043
 t+0.041
days+0.040
 stuffed+0.039
 unp+0.038
Neg logit contributions
aw-0.049
Le-0.045
imes-0.044
isi-0.044
 Remy-0.044
Token eat
Token ID4483
Feature activation+5.52e-02

Pos logit contributions
bell+0.012
days+0.012
spe+0.011
 Mechan+0.011
ksh+0.011
Neg logit contributions
 Remy-0.011
isi-0.011
Le-0.010
aw-0.010
imes-0.010
Token l
Token ID300
Feature activation+8.44e-02

Pos logit contributions
aw+0.101
Le+0.099
isi+0.099
arling+0.096
imes+0.093
Neg logit contributions
 t-0.095
 stuffed-0.090
bell-0.089
 unp-0.087
 py-0.084
Tokenimes
Token ID999
Feature activation+1.28e-01

Pos logit contributions
 hawk+0.118
 Duke+0.115
Fin+0.113
Le+0.110
 Remy+0.110
Neg logit contributions
bell-0.157
 decor-0.155
 t-0.152
 unp-0.151
days-0.148
Token.
Token ID13
Feature activation-2.00e-03

Pos logit contributions
aw+0.324
Le+0.319
emy+0.317
opard+0.305
crow+0.304
Neg logit contributions
 t-0.121
days-0.108
bell-0.104
 unp-0.100
 decor-0.098
Token He
Token ID679
Feature activation+3.44e-03

Pos logit contributions
bell+0.003
days+0.003
 stuffed+0.003
 t+0.003
 unp+0.003
Neg logit contributions
 Remy-0.004
aw-0.004
imes-0.004
Le-0.003
una-0.003
Token thought
Token ID1807
Feature activation-5.36e-03

Pos logit contributions
aw+0.008
Le+0.007
imes+0.007
isi+0.007
 Remy+0.007
Neg logit contributions
bell-0.005
 t-0.004
days-0.004
 stuffed-0.004
 unp-0.004
Token l
Token ID300
Feature activation+6.91e-02

Pos logit contributions
bell+0.010
days+0.009
 t+0.009
 stuffed+0.009
 unp+0.008
Neg logit contributions
aw-0.010
Le-0.009
imes-0.009
 Remy-0.009
isi-0.009
Tokenimes
Token ID999
Feature activation+1.09e-01

Pos logit contributions
aw+0.057
 unnecessary+0.053
 hawk+0.052
Le+0.052
 Duke+0.052
Neg logit contributions
bell-0.162
days-0.159
 t-0.158
 stuffed-0.152
 decor-0.151
Token,
Token ID11
Feature activation+1.52e-02

Pos logit contributions
aw+0.033
 Remy+0.030
Le+0.030
imes+0.029
 Sasha+0.029
Neg logit contributions
bell-0.030
days-0.029
 Mechan-0.027
 t-0.026
 stuffed-0.026
Token she
Token ID673
Feature activation-2.85e-02

Pos logit contributions
aw+0.028
 Remy+0.027
Le+0.026
 Sasha+0.026
imes+0.025
Neg logit contributions
bell-0.028
days-0.026
 Mechan-0.024
 t-0.023
 stuffed-0.023
Token was
Token ID373
Feature activation-1.16e-02

Pos logit contributions
bell+0.052
days+0.051
 Mechan+0.051
 stuffed+0.046
 spoiler+0.046
Neg logit contributions
aw-0.052
Le-0.043
 Remy-0.043
 Sasha-0.042
imes-0.041
Token picking
Token ID10868
Feature activation+2.28e-02

Pos logit contributions
bell+0.020
days+0.019
 t+0.018
 stuffed+0.017
 Mechan+0.017
Neg logit contributions
aw-0.023
Le-0.020
 Remy-0.020
imes-0.020
isi-0.020
Token l
Token ID300
Feature activation+8.17e-02

Pos logit contributions
Le+0.044
aw+0.043
isi+0.043
emy+0.042
 Remy+0.042
Neg logit contributions
 t-0.035
bell-0.034
 stuffed-0.032
 unp-0.031
days-0.031
Tokenimes
Token ID999
Feature activation+1.27e-01

Pos logit contributions
 Remy+0.082
 hawk+0.076
 Duke+0.075
emy+0.073
Le+0.072
Neg logit contributions
bell-0.183
days-0.176
 unp-0.168
 ti-0.165
 t-0.163
Token when
Token ID618
Feature activation+3.63e-02

Pos logit contributions
aw+0.280
Le+0.276
emy+0.276
iles+0.265
isi+0.261
Neg logit contributions
bell-0.165
 t-0.158
days-0.149
 unp-0.144
 stuffed-0.140
Token it
Token ID340
Feature activation+5.87e-03

Pos logit contributions
aw+0.064
Le+0.058
 Remy+0.057
imes+0.057
isi+0.056
Neg logit contributions
bell-0.068
days-0.066
 t-0.063
 stuffed-0.061
 Mechan-0.060
Token started
Token ID2067
Feature activation+2.40e-02

Pos logit contributions
aw+0.013
Le+0.012
imes+0.012
 Remy+0.012
isi+0.012
Neg logit contributions
bell-0.008
days-0.008
 t-0.008
 stuffed-0.007
 unp-0.007
Token to
Token ID284
Feature activation-5.86e-03

Pos logit contributions
aw+0.048
Le+0.045
isi+0.044
 Remy+0.044
una+0.043
Neg logit contributions
bell-0.040
 t-0.037
days-0.037
 stuffed-0.035
 unp-0.035
Token rain
Token ID6290
Feature activation-2.53e-02

Pos logit contributions
bell+0.010
days+0.010
 Mechan+0.009
 stuffed+0.009
 unp+0.008
Neg logit contributions
aw-0.010
 Remy-0.010
 Sasha-0.010
Le-0.010
isi-0.010
Token She
Token ID1375
Feature activation-8.37e-03

Pos logit contributions
aw+0.005
 Remy+0.004
imes+0.004
Le+0.004
isi+0.004
Neg logit contributions
bell-0.007
days-0.006
 Mechan-0.006
 stuffed-0.006
 t-0.006
Token loved
Token ID6151
Feature activation-2.67e-02

Pos logit contributions
bell+0.013
days+0.013
 t+0.012
 stuffed+0.011
 Mechan+0.011
Neg logit contributions
aw-0.017
Le-0.016
 Remy-0.016
una-0.016
imes-0.016
Token to
Token ID284
Feature activation-4.43e-03

Pos logit contributions
bell+0.047
days+0.045
 t+0.044
 stuffed+0.042
 unp+0.041
Neg logit contributions
aw-0.051
Le-0.046
imes-0.046
 Remy-0.045
isi-0.045
Token eat
Token ID4483
Feature activation+5.35e-02

Pos logit contributions
bell+0.008
spe+0.008
days+0.008
 Mechan+0.007
lights+0.007
Neg logit contributions
 Remy-0.007
isi-0.007
imes-0.006
aw-0.006
Le-0.006
Token l
Token ID300
Feature activation+8.50e-02

Pos logit contributions
aw+0.097
Le+0.093
isi+0.091
arling+0.088
imes+0.087
Neg logit contributions
 t-0.094
bell-0.091
 stuffed-0.089
 unp-0.086
days-0.085
Tokenimes
Token ID999
Feature activation+1.26e-01

Pos logit contributions
 hawk+0.108
Fin+0.104
Le+0.103
 Duke+0.102
 Remy+0.100
Neg logit contributions
bell-0.173
 t-0.166
days-0.166
 unp-0.165
 decor-0.165
Token because
Token ID780
Feature activation+4.55e-03

Pos logit contributions
aw+0.301
Le+0.295
emy+0.291
iles+0.277
opard+0.276
Neg logit contributions
 t-0.139
days-0.131
bell-0.131
 unp-0.122
 stuffed-0.119
Token they
Token ID484
Feature activation-2.95e-02

Pos logit contributions
aw+0.009
Le+0.008
 Remy+0.008
isi+0.008
imes+0.008
Neg logit contributions
bell-0.007
days-0.007
 t-0.007
 stuffed-0.007
 unp-0.006
Token were
Token ID547
Feature activation-1.82e-02

Pos logit contributions
bell+0.042
days+0.039
 t+0.037
 stuffed+0.035
 Mechan+0.035
Neg logit contributions
aw-0.065
Le-0.061
imes-0.060
 Remy-0.060
isi-0.060
Token so
Token ID523
Feature activation+2.72e-03

Pos logit contributions
 t+0.026
 stuffed+0.025
bell+0.024
 unp+0.024
 decor+0.023
Neg logit contributions
aw-0.040
arling-0.037
Le-0.037
crow-0.036
opard-0.035
Token tasty
Token ID25103
Feature activation+6.66e-02

Pos logit contributions
aw+0.006
Le+0.005
 Remy+0.005
isi+0.005
imes+0.005
Neg logit contributions
bell-0.004
days-0.004
 t-0.004
 stuffed-0.004
 unp-0.004
Token little
Token ID1310
Feature activation-1.74e-02

Pos logit contributions
bell+0.016
days+0.016
 Mechan+0.015
 t+0.014
 unp+0.014
Neg logit contributions
aw-0.015
Le-0.013
 Remy-0.013
imes-0.013
isi-0.013
Token girl
Token ID2576
Feature activation-2.36e-02

Pos logit contributions
bell+0.033
days+0.032
 Mechan+0.030
 unp+0.028
 t+0.028
Neg logit contributions
aw-0.032
 Remy-0.028
Le-0.028
imes-0.027
 Sasha-0.027
Token stopped
Token ID5025
Feature activation+6.09e-03

Pos logit contributions
days+0.038
 Mechan+0.038
bell+0.038
 t+0.033
 stuffed+0.033
Neg logit contributions
aw-0.048
Le-0.041
 Remy-0.039
 Sasha-0.039
imes-0.038
Token picking
Token ID10868
Feature activation+2.19e-02

Pos logit contributions
aw+0.013
Le+0.012
imes+0.012
 Remy+0.012
isi+0.012
Neg logit contributions
bell-0.009
days-0.009
 t-0.008
 stuffed-0.008
 unp-0.008
Token l
Token ID300
Feature activation+8.54e-02

Pos logit contributions
aw+0.043
Le+0.040
isi+0.039
 Remy+0.039
imes+0.039
Neg logit contributions
bell-0.036
 t-0.034
days-0.034
 stuffed-0.033
 unp-0.031
Tokenimes
Token ID999
Feature activation+1.26e-01

Pos logit contributions
 Remy+0.073
emy+0.072
 unnecessary+0.069
 Duke+0.067
 hawk+0.067
Neg logit contributions
bell-0.202
days-0.191
 unp-0.186
 t-0.184
 stuffed-0.178
Token and
Token ID290
Feature activation+3.23e-03

Pos logit contributions
aw+0.292
Le+0.275
 Remy+0.269
imes+0.269
isi+0.268
Neg logit contributions
bell-0.167
days-0.156
 t-0.150
 stuffed-0.142
 unp-0.139
Token watched
Token ID7342
Feature activation-3.91e-02

Pos logit contributions
aw+0.006
 Remy+0.006
Le+0.006
 Sasha+0.006
imes+0.005
Neg logit contributions
bell-0.005
days-0.005
 Mechan-0.005
 t-0.005
 stuffed-0.005
Token the
Token ID262
Feature activation+2.03e-02

Pos logit contributions
days+0.073
bell+0.072
 Mechan+0.069
 t+0.063
 stuffed+0.062
Neg logit contributions
aw-0.070
 Remy-0.064
imes-0.063
Le-0.061
 Sasha-0.061
Token sky
Token ID6766
Feature activation-1.58e-02

Pos logit contributions
aw+0.035
Le+0.032
 Remy+0.031
imes+0.031
isi+0.031
Neg logit contributions
bell-0.039
days-0.037
 t-0.037
 stuffed-0.036
 unp-0.035
Token shine
Token ID18340
Feature activation-5.32e-02

Pos logit contributions
 Mechan+0.025
days+0.025
bell+0.023
 py+0.022
 stuffed+0.022
Neg logit contributions
aw-0.030
 Sasha-0.026
 Remy-0.025
isi-0.025
Le-0.025
Token pond
Token ID16723
Feature activation+4.75e-02

Pos logit contributions
aw+0.039
imes+0.038
isi+0.037
Le+0.037
emy+0.036
Neg logit contributions
bell-0.043
 t-0.042
 stuffed-0.039
days-0.039
 Gr-0.037
Token.
Token ID13
Feature activation-2.18e-03

Pos logit contributions
aw+0.094
imes+0.085
Le+0.084
 Remy+0.084
una+0.082
Neg logit contributions
bell-0.080
days-0.074
 t-0.072
 Mechan-0.072
 stuffed-0.071
Token She
Token ID1375
Feature activation-6.14e-03

Pos logit contributions
days+0.004
bell+0.004
 stuffed+0.004
 t+0.004
 Mechan+0.004
Neg logit contributions
aw-0.004
 Remy-0.004
 Sasha-0.003
imes-0.003
Le-0.003
Token always
Token ID1464
Feature activation-8.45e-03

Pos logit contributions
bell+0.011
days+0.011
 Mechan+0.010
 spoiler+0.009
 Jos+0.009
Neg logit contributions
aw-0.011
 Remy-0.011
Le-0.011
una-0.010
emy-0.010
Token brought
Token ID3181
Feature activation-1.28e-02

Pos logit contributions
bell+0.015
days+0.014
 Mechan+0.013
 t+0.012
 stuffed+0.012
Neg logit contributions
aw-0.016
 Remy-0.015
 Sasha-0.014
Le-0.014
emy-0.014
Token bread
Token ID8509
Feature activation+1.25e-01

Pos logit contributions
 t+0.021
 stuffed+0.020
bell+0.019
 decor+0.019
 unp+0.019
Neg logit contributions
aw-0.024
isi-0.023
arling-0.023
Le-0.023
opard-0.023
Token and
Token ID290
Feature activation+5.87e-03

Pos logit contributions
aw+0.250
Le+0.231
isi+0.230
arling+0.228
 unnecessary+0.221
Neg logit contributions
 t-0.200
 stuffed-0.195
days-0.185
bell-0.181
 decor-0.175
Token seeds
Token ID11904
Feature activation+6.18e-02

Pos logit contributions
aw+0.010
Le+0.009
isi+0.009
imes+0.009
 Remy+0.008
Neg logit contributions
bell-0.011
days-0.011
 t-0.011
 stuffed-0.011
 unp-0.010
Token for
Token ID329
Feature activation+5.34e-02

Pos logit contributions
aw+0.129
Le+0.122
isi+0.117
imes+0.116
 Remy+0.116
Neg logit contributions
bell-0.095
days-0.090
 t-0.089
 stuffed-0.085
 unp-0.082
Token them
Token ID606
Feature activation+5.77e-03

Pos logit contributions
aw+0.100
arling+0.094
isi+0.090
Le+0.090
opard+0.089
Neg logit contributions
 t-0.091
 stuffed-0.086
 decor-0.085
 unp-0.085
bell-0.084
Token.
Token ID13
Feature activation-3.06e-03

Pos logit contributions
aw+0.012
Le+0.011
isi+0.011
imes+0.011
 Remy+0.011
Neg logit contributions
bell-0.009
days-0.009
 t-0.009
 stuffed-0.008
 unp-0.008
Token likes
Token ID7832
Feature activation+1.23e-02

Pos logit contributions
aw+0.055
una+0.047
isi+0.047
 Remy+0.047
Le+0.047
Neg logit contributions
bell-0.044
days-0.042
 Mechan-0.039
 stuffed-0.039
 py-0.037
Token to
Token ID284
Feature activation-1.02e-03

Pos logit contributions
aw+0.024
Le+0.022
imes+0.021
isi+0.021
 Remy+0.021
Neg logit contributions
bell-0.021
days-0.020
 t-0.020
 stuffed-0.019
 unp-0.019
Token play
Token ID711
Feature activation-1.54e-02

Pos logit contributions
bell+0.002
 Mechan+0.002
days+0.002
ksh+0.002
lights+0.002
Neg logit contributions
 Remy-0.002
 Sasha-0.002
aw-0.002
 Sid-0.002
imes-0.002
Token with
Token ID351
Feature activation+2.34e-03

Pos logit contributions
bell+0.029
days+0.027
 Mechan+0.025
 t+0.023
 unp+0.023
Neg logit contributions
aw-0.030
 Remy-0.027
Le-0.026
imes-0.026
una-0.026
Token l
Token ID300
Feature activation+8.43e-02

Pos logit contributions
aw+0.004
Le+0.004
imes+0.004
 Remy+0.004
isi+0.004
Neg logit contributions
bell-0.004
days-0.004
 t-0.004
 stuffed-0.004
 unp-0.004
Tokenimes
Token ID999
Feature activation+1.25e-01

Pos logit contributions
 hawk+0.105
 Remy+0.098
 Duke+0.097
Le+0.097
Fin+0.096
Neg logit contributions
bell-0.182
days-0.180
 unp-0.166
 decor-0.163
 t-0.160
Token.
Token ID13
Feature activation+1.08e-03

Pos logit contributions
Le+0.315
aw+0.313
emy+0.307
iles+0.299
 Sasha+0.299
Neg logit contributions
 t-0.111
bell-0.111
days-0.110
 unp-0.096
 stuffed-0.093
Token She
Token ID1375
Feature activation-5.10e-03

Pos logit contributions
aw+0.002
 Remy+0.002
Le+0.002
imes+0.002
isi+0.002
Neg logit contributions
bell-0.002
days-0.002
 t-0.002
 stuffed-0.002
 Mechan-0.002
Token likes
Token ID7832
Feature activation+5.37e-03

Pos logit contributions
bell+0.008
days+0.008
 Mechan+0.007
 t+0.007
 stuffed+0.007
Neg logit contributions
aw-0.010
Le-0.010
 Remy-0.009
imes-0.009
una-0.009
Token how
Token ID703
Feature activation-1.05e-02

Pos logit contributions
aw+0.012
arling+0.012
Jud+0.011
ile+0.011
Le+0.011
Neg logit contributions
 t-0.008
 stuffed-0.007
 Gr-0.007
 py-0.006
 Sn-0.006
Token they
Token ID484
Feature activation-3.42e-02

Pos logit contributions
bell+0.018
days+0.017
 t+0.017
 stuffed+0.017
 unp+0.016
Neg logit contributions
aw-0.019
Le-0.018
isi-0.017
 Remy-0.017
una-0.017
Token They
Token ID1119
Feature activation+7.97e-03

Pos logit contributions
bell+0.000
days+0.000
 t+0.000
 stuffed+0.000
 unp+0.000
Neg logit contributions
aw-0.000
Le-0.000
 Remy-0.000
imes-0.000
isi-0.000
Token take
Token ID1011
Feature activation+2.14e-02

Pos logit contributions
aw+0.014
imes+0.013
 Remy+0.013
Le+0.013
 Sasha+0.013
Neg logit contributions
bell-0.014
days-0.014
 Mechan-0.013
 py-0.012
 stuffed-0.012
Token some
Token ID617
Feature activation+9.65e-03

Pos logit contributions
aw+0.045
isi+0.042
Le+0.042
 Remy+0.041
imes+0.041
Neg logit contributions
bell-0.031
 t-0.030
days-0.029
 stuffed-0.028
 unp-0.027
Token chips
Token ID12014
Feature activation+8.48e-02

Pos logit contributions
aw+0.020
Le+0.020
isi+0.019
 Remy+0.019
emy+0.018
Neg logit contributions
bell-0.015
 t-0.014
 stuffed-0.014
 unp-0.013
days-0.013
Token and
Token ID290
Feature activation-2.92e-03

Pos logit contributions
aw+0.206
Le+0.198
emy+0.195
isi+0.195
 Remy+0.190
Neg logit contributions
bell-0.095
 t-0.093
days-0.087
 unp-0.085
 stuffed-0.081
Token salsa
Token ID49529
Feature activation+1.25e-01

Pos logit contributions
bell+0.006
days+0.005
 t+0.005
 Mechan+0.005
 stuffed+0.005
Neg logit contributions
aw-0.005
Le-0.005
 Remy-0.005
imes-0.005
isi-0.004
Token.
Token ID13
Feature activation+2.91e-04

Pos logit contributions
isi+0.295
aw+0.293
emy+0.288
Le+0.285
 Remy+0.279
Neg logit contributions
 t-0.138
bell-0.138
days-0.127
 unp-0.125
 stuffed-0.117
Token They
Token ID1119
Feature activation+6.07e-03

Pos logit contributions
aw+0.001
isi+0.001
Le+0.001
una+0.001
imes+0.001
Neg logit contributions
bell-0.000
days-0.000
 t-0.000
 stuffed-0.000
 unp-0.000
Token put
Token ID1234
Feature activation-4.80e-03

Pos logit contributions
aw+0.011
imes+0.011
 Remy+0.011
Le+0.010
isi+0.010
Neg logit contributions
bell-0.011
days-0.010
 Mechan-0.010
 py-0.009
 t-0.009
Token them
Token ID606
Feature activation+1.04e-02

Pos logit contributions
bell+0.008
days+0.008
 t+0.007
 stuffed+0.007
 unp+0.007
Neg logit contributions
aw-0.010
Le-0.009
 Remy-0.009
imes-0.009
isi-0.009
Token in
Token ID287
Feature activation-1.42e-02

Pos logit contributions
aw+0.019
Le+0.017
imes+0.017
 Remy+0.017
isi+0.016
Neg logit contributions
bell-0.019
days-0.018
 t-0.017
 stuffed-0.017
 Mechan-0.017
Tokenoppy
Token ID26696
Feature activation+3.38e-02

Pos logit contributions
aw+0.044
isi+0.042
Le+0.039
crow+0.039
imes+0.039
Neg logit contributions
days-0.047
 t-0.046
 stuffed-0.044
 Gr-0.044
bell-0.044
Token accidentally
Token ID14716
Feature activation+4.16e-02

Pos logit contributions
aw+0.068
 Remy+0.061
Le+0.061
imes+0.059
una+0.058
Neg logit contributions
bell-0.059
days-0.053
 Mechan-0.051
 t-0.047
 stuffed-0.046
Token bumped
Token ID38034
Feature activation-1.10e-03

Pos logit contributions
aw+0.084
Le+0.077
imes+0.076
isi+0.076
 Remy+0.076
Neg logit contributions
bell-0.068
days-0.064
 t-0.063
 stuffed-0.060
 unp-0.059
Token into
Token ID656
Feature activation-4.73e-03

Pos logit contributions
bell+0.002
days+0.002
 t+0.002
 stuffed+0.002
 unp+0.002
Neg logit contributions
aw-0.002
Le-0.002
imes-0.002
 Remy-0.002
isi-0.002
Token Ho
Token ID9544
Feature activation+2.96e-02

Pos logit contributions
bell+0.010
days+0.009
 Mechan+0.008
 unp+0.008
 lit+0.007
Neg logit contributions
aw-0.008
 Remy-0.008
Le-0.007
imes-0.007
una-0.007
Tokenpper
Token ID2848
Feature activation+1.23e-01

Pos logit contributions
aw+0.054
Le+0.048
imes+0.048
isi+0.047
 Remy+0.046
Neg logit contributions
bell-0.051
days-0.050
 t-0.050
 stuffed-0.048
 unp-0.046
Token's
Token ID338
Feature activation+7.06e-04

Pos logit contributions
aw+0.246
 Remy+0.227
Le+0.225
imes+0.223
una+0.219
Neg logit contributions
bell-0.201
days-0.191
 t-0.177
 Mechan-0.174
 stuffed-0.174
Token ear
Token ID1027
Feature activation+1.18e-02

Pos logit contributions
aw+0.001
Le+0.001
 Remy+0.001
imes+0.001
isi+0.001
Neg logit contributions
bell-0.001
days-0.001
 t-0.001
 stuffed-0.001
 unp-0.001
Token.
Token ID13
Feature activation-4.44e-03

Pos logit contributions
aw+0.020
imes+0.018
 Remy+0.017
Le+0.017
una+0.017
Neg logit contributions
 Mechan-0.021
days-0.021
bell-0.020
 unp-0.019
 stuffed-0.019
Token Ho
Token ID9544
Feature activation+9.67e-03

Pos logit contributions
bell+0.008
days+0.007
 t+0.007
 stuffed+0.007
 unp+0.007
Neg logit contributions
aw-0.008
 Remy-0.008
Le-0.008
imes-0.008
isi-0.008
Tokenpper
Token ID2848
Feature activation+9.28e-02

Pos logit contributions
aw+0.017
Le+0.015
imes+0.015
isi+0.015
 Remy+0.014
Neg logit contributions
bell-0.017
days-0.017
 t-0.016
 stuffed-0.016
 Mechan-0.015
Token.
Token ID13
Feature activation-5.51e-03

Pos logit contributions
aw+0.050
imes+0.046
 Remy+0.045
Le+0.045
una+0.044
Neg logit contributions
bell-0.040
days-0.038
 t-0.037
 stuffed-0.036
 Mechan-0.036
Token Is
Token ID1148
Feature activation-3.05e-02

Pos logit contributions
bell+0.010
days+0.009
 stuffed+0.009
 t+0.009
 unp+0.008
Neg logit contributions
aw-0.011
 Remy-0.010
imes-0.010
Le-0.010
 Sasha-0.009
Token wine
Token ID8237
Feature activation+3.97e-02

Pos logit contributions
bell+0.055
 t+0.051
days+0.050
 unp+0.049
 stuffed+0.048
Neg logit contributions
aw-0.053
Le-0.050
 Remy-0.049
isi-0.049
emy-0.048
Token made
Token ID925
Feature activation-3.72e-02

Pos logit contributions
aw+0.077
Le+0.070
imes+0.070
 Remy+0.070
isi+0.069
Neg logit contributions
bell-0.067
days-0.064
 t-0.061
 stuffed-0.059
 Mechan-0.058
Token from
Token ID422
Feature activation-1.54e-02

Pos logit contributions
bell+0.077
days+0.074
 t+0.073
 stuffed+0.070
 unp+0.069
Neg logit contributions
aw-0.057
Le-0.052
imes-0.050
 Remy-0.050
isi-0.050
Token grape
Token ID30777
Feature activation+1.23e-01

Pos logit contributions
bell+0.026
days+0.025
 t+0.025
 stuffed+0.024
 unp+0.023
Neg logit contributions
aw-0.029
Le-0.027
imes-0.026
isi-0.026
 Remy-0.026
Token?
Token ID30
Feature activation-2.24e-02

Pos logit contributions
aw+0.238
Le+0.222
isi+0.216
 Remy+0.215
imes+0.213
Neg logit contributions
bell-0.206
days-0.198
 t-0.190
 stuffed-0.184
 unp-0.180
Tokenâ
Token ID22940
Feature activation-3.80e-02

Pos logit contributions
bell+0.040
days+0.038
 stuffed+0.037
 t+0.037
 unp+0.035
Neg logit contributions
aw-0.042
 Remy-0.039
imes-0.039
Le-0.038
 Sasha-0.037
Token
Token ID26391
Feature activation-2.01e-02

Pos logit contributions
bell+0.073
days+0.069
 t+0.066
 stuffed+0.064
 unp+0.064
Neg logit contributions
aw-0.066
Le-0.060
 Remy-0.059
imes-0.059
isi-0.058
Token
Token ID198
Feature activation-4.04e-03

Pos logit contributions
bell+0.039
 stuffed+0.037
days+0.036
 t+0.036
 Mechan+0.033
Neg logit contributions
aw-0.037
 Remy-0.033
Le-0.032
 Sasha-0.031
imes-0.030
Token
Token ID198
Feature activation+1.87e-04

Pos logit contributions
bell+0.006
days+0.006
 t+0.006
 unp+0.006
 stuffed+0.005
Neg logit contributions
aw-0.008
imes-0.007
isi-0.007
Le-0.007
 Remy-0.007
Token bite
Token ID13197
Feature activation+8.56e-02

Pos logit contributions
aw+0.002
isi+0.002
iles+0.002
imes+0.002
Le+0.002
Neg logit contributions
bell-0.001
 t-0.001
 stuffed-0.001
days-0.001
 unp-0.001
Token of
Token ID286
Feature activation-2.81e-02

Pos logit contributions
aw+0.187
isi+0.183
Le+0.181
 Remy+0.178
emy+0.176
Neg logit contributions
bell-0.118
 t-0.110
days-0.107
 stuffed-0.102
 unp-0.097
Token the
Token ID262
Feature activation+1.40e-02

Pos logit contributions
bell+0.042
 t+0.041
days+0.040
 stuffed+0.039
 unp+0.037
Neg logit contributions
aw-0.059
Le-0.055
isi-0.054
imes-0.054
 Remy-0.053
Token carrot
Token ID40562
Feature activation+4.51e-02

Pos logit contributions
aw+0.026
Le+0.024
isi+0.024
 Remy+0.023
 Sasha+0.023
Neg logit contributions
 t-0.025
 stuffed-0.024
bell-0.024
days-0.023
 unp-0.022
Token with
Token ID351
Feature activation-1.05e-04

Pos logit contributions
aw+0.099
Le+0.092
isi+0.090
imes+0.090
 Remy+0.089
Neg logit contributions
bell-0.066
days-0.062
 t-0.061
 stuffed-0.058
 unp-0.055
Token salsa
Token ID49529
Feature activation+1.23e-01

Pos logit contributions
bell+0.000
 t+0.000
 stuffed+0.000
days+0.000
 unp+0.000
Neg logit contributions
aw-0.000
isi-0.000
Le-0.000
imes-0.000
 Remy-0.000
Token.
Token ID13
Feature activation-3.71e-04

Pos logit contributions
aw+0.275
isi+0.264
Le+0.263
 Remy+0.259
emy+0.257
Neg logit contributions
bell-0.162
 t-0.154
days-0.149
 stuffed-0.142
 unp-0.138
Token They
Token ID1119
Feature activation+4.82e-03

Pos logit contributions
bell+0.001
days+0.001
 t+0.001
 stuffed+0.001
 Mechan+0.000
Neg logit contributions
aw-0.001
 Remy-0.001
Le-0.001
imes-0.001
una-0.001
Token felt
Token ID2936
Feature activation-4.97e-03

Pos logit contributions
aw+0.009
Le+0.009
 Remy+0.008
imes+0.008
una+0.008
Neg logit contributions
bell-0.008
days-0.008
 Mechan-0.008
 t-0.007
 stuffed-0.007
Token a
Token ID257
Feature activation-3.22e-02

Pos logit contributions
 t+0.007
 stuffed+0.007
bell+0.006
 unp+0.006
 lit+0.006
Neg logit contributions
isi-0.011
Le-0.010
aw-0.010
iles-0.010
live-0.010
Token hot
Token ID3024
Feature activation-4.16e-03

Pos logit contributions
bell+0.050
 t+0.047
days+0.046
 stuffed+0.045
 unp+0.043
Neg logit contributions
aw-0.067
imes-0.062
Le-0.062
isi-0.061
 Remy-0.061
Token both
Token ID1111
Feature activation+3.93e-02

Pos logit contributions
aw+0.032
Le+0.029
 Remy+0.028
imes+0.028
isi+0.027
Neg logit contributions
days-0.028
bell-0.027
 Mechan-0.025
 py-0.023
 stuffed-0.023
Token laughed
Token ID13818
Feature activation+1.94e-02

Pos logit contributions
aw+0.083
Le+0.076
 Remy+0.073
imes+0.073
isi+0.072
Neg logit contributions
bell-0.062
days-0.060
 t-0.054
 Mechan-0.054
 stuffed-0.053
Token and
Token ID290
Feature activation-3.27e-03

Pos logit contributions
aw+0.043
 Remy+0.038
Le+0.037
imes+0.037
una+0.037
Neg logit contributions
days-0.030
bell-0.030
 Mechan-0.027
 stuffed-0.025
 unp-0.025
Token threw
Token ID9617
Feature activation+5.93e-02

Pos logit contributions
bell+0.005
days+0.005
 t+0.004
 stuffed+0.004
 unp+0.004
Neg logit contributions
aw-0.007
Le-0.007
imes-0.007
isi-0.006
 Remy-0.006
Token more
Token ID517
Feature activation+6.53e-02

Pos logit contributions
isi+0.128
aw+0.127
live+0.125
emy+0.122
arling+0.122
Neg logit contributions
 t-0.081
 stuffed-0.075
bell-0.073
days-0.069
 unp-0.066
Token bread
Token ID8509
Feature activation+1.22e-01

Pos logit contributions
isi+0.098
live+0.095
arling+0.093
aw+0.091
Phil+0.091
Neg logit contributions
 t-0.134
 stuffed-0.132
bell-0.122
 decor-0.117
 unp-0.117
Token to
Token ID284
Feature activation-8.43e-03

Pos logit contributions
isi+0.295
aw+0.290
live+0.284
Phil+0.272
Le+0.271
Neg logit contributions
 t-0.140
 stuffed-0.124
bell-0.119
days-0.112
 unp-0.107
Token the
Token ID262
Feature activation+1.63e-02

Pos logit contributions
 t+0.012
bell+0.011
 stuffed+0.011
days+0.010
 decor+0.010
Neg logit contributions
aw-0.019
isi-0.018
imes-0.018
arling-0.017
Le-0.017
Token fish
Token ID5916
Feature activation+4.42e-02

Pos logit contributions
aw+0.027
isi+0.026
imes+0.025
Le+0.025
 Remy+0.024
Neg logit contributions
 t-0.031
bell-0.031
 stuffed-0.030
days-0.030
 py-0.028
Token.
Token ID13
Feature activation+1.71e-03

Pos logit contributions
aw+0.099
isi+0.095
Le+0.093
imes+0.092
una+0.090
Neg logit contributions
bell-0.058
days-0.058
 t-0.056
 stuffed-0.053
 unp-0.050
Token
Token ID198
Feature activation+9.11e-03

Pos logit contributions
aw+0.004
Le+0.004
 Remy+0.003
imes+0.003
isi+0.003
Neg logit contributions
bell-0.002
days-0.002
 t-0.002
 stuffed-0.002
 Mechan-0.002
Token They
Token ID1119
Feature activation+2.44e-03

Pos logit contributions
bell+0.005
days+0.005
 t+0.004
 stuffed+0.004
 unp+0.004
Neg logit contributions
aw-0.008
Le-0.007
isi-0.007
imes-0.007
 Remy-0.007
Token put
Token ID1234
Feature activation-5.55e-03

Pos logit contributions
aw+0.004
imes+0.004
Le+0.004
 Remy+0.004
iles+0.004
Neg logit contributions
days-0.004
bell-0.004
 Mechan-0.004
 py-0.004
 Gr-0.003
Token cheese
Token ID9891
Feature activation+9.43e-02

Pos logit contributions
bell+0.010
days+0.009
 t+0.009
 stuffed+0.009
 Mechan+0.008
Neg logit contributions
aw-0.011
Le-0.010
imes-0.010
 Remy-0.010
una-0.009
Token and
Token ID290
Feature activation+2.80e-04

Pos logit contributions
aw+0.204
Le+0.189
isi+0.188
 Remy+0.186
imes+0.185
Neg logit contributions
bell-0.137
days-0.128
 t-0.128
 stuffed-0.122
 unp-0.118
Token pepper
Token ID13385
Feature activation+9.77e-02

Pos logit contributions
aw+0.000
 Remy+0.000
Le+0.000
imes+0.000
una+0.000
Neg logit contributions
bell-0.001
days-0.001
 Mechan-0.000
 t-0.000
 stuffed-0.000
Tokenoni
Token ID14651
Feature activation+1.22e-01

Pos logit contributions
aw+0.197
isi+0.191
Le+0.186
 Remy+0.181
emy+0.180
Neg logit contributions
bell-0.147
 t-0.144
days-0.136
 stuffed-0.134
 unp-0.133
Token on
Token ID319
Feature activation-3.96e-03

Pos logit contributions
aw+0.248
isi+0.232
Le+0.231
 Remy+0.227
imes+0.224
Neg logit contributions
bell-0.188
days-0.180
 t-0.179
 stuffed-0.172
 unp-0.169
Token top
Token ID1353
Feature activation+3.26e-02

Pos logit contributions
bell+0.007
days+0.007
 t+0.006
 Mechan+0.006
 stuffed+0.006
Neg logit contributions
aw-0.007
Le-0.007
 Remy-0.007
imes-0.007
una-0.007
Token.
Token ID13
Feature activation+3.14e-03

Pos logit contributions
aw+0.061
Le+0.055
imes+0.055
 Remy+0.054
una+0.053
Neg logit contributions
bell-0.058
days-0.056
 t-0.054
 stuffed-0.053
 Mechan-0.052
Token They
Token ID1119
Feature activation+6.52e-03

Pos logit contributions
aw+0.007
Le+0.006
 Remy+0.006
imes+0.006
isi+0.006
Neg logit contributions
bell-0.005
days-0.005
 t-0.004
 stuffed-0.004
 unp-0.004
Token bake
Token ID28450
Feature activation-2.22e-02

Pos logit contributions
aw+0.012
imes+0.011
Le+0.011
 Remy+0.011
iles+0.011
Neg logit contributions
days-0.011
bell-0.011
 Mechan-0.010
 py-0.009
 Sus-0.009
Token and
Token ID290
Feature activation-3.85e-04

Pos logit contributions
aw+0.081
Le+0.075
 Remy+0.074
imes+0.074
isi+0.073
Neg logit contributions
bell-0.061
days-0.057
 t-0.055
 stuffed-0.053
 unp-0.052
Token one
Token ID530
Feature activation-8.81e-03

Pos logit contributions
bell+0.001
days+0.001
 Mechan+0.001
 t+0.001
 unp+0.001
Neg logit contributions
aw-0.001
imes-0.001
 Remy-0.001
Le-0.001
una-0.001
Token is
Token ID318
Feature activation-4.58e-03

Pos logit contributions
bell+0.014
 t+0.013
days+0.013
 stuffed+0.013
 unp+0.012
Neg logit contributions
aw-0.018
Le-0.017
isi-0.017
 Remy-0.017
imes-0.016
Token full
Token ID1336
Feature activation-2.51e-02

Pos logit contributions
bell+0.007
 t+0.007
 stuffed+0.006
days+0.006
 unp+0.006
Neg logit contributions
aw-0.010
Le-0.009
isi-0.009
 Remy-0.009
imes-0.009
Token of
Token ID286
Feature activation-2.88e-02

Pos logit contributions
bell+0.043
days+0.041
 t+0.039
 Mechan+0.038
 stuffed+0.038
Neg logit contributions
aw-0.049
imes-0.044
Le-0.044
 Remy-0.043
isi-0.043
Token salsa
Token ID49529
Feature activation+1.22e-01

Pos logit contributions
bell+0.056
days+0.053
 Mechan+0.050
 t+0.049
 stuffed+0.048
Neg logit contributions
aw-0.050
imes-0.045
Le-0.045
 Remy-0.045
una-0.044
Token.
Token ID13
Feature activation-2.38e-03

Pos logit contributions
aw+0.282
isi+0.280
Le+0.279
emy+0.273
 Remy+0.268
Neg logit contributions
bell-0.140
 t-0.139
days-0.132
 unp-0.129
 stuffed-0.126
Token
Token ID198
Feature activation+6.91e-03

Pos logit contributions
bell+0.004
days+0.004
 t+0.004
 stuffed+0.004
 Mechan+0.004
Neg logit contributions
aw-0.005
 Remy-0.004
imes-0.004
Le-0.004
una-0.004
Token
Token ID198
Feature activation+8.98e-03

Pos logit contributions
aw+0.014
isi+0.013
imes+0.013
Le+0.013
 Remy+0.013
Neg logit contributions
bell-0.011
days-0.010
 t-0.010
 unp-0.009
 stuffed-0.009
Token"
Token ID1
Feature activation-6.01e-03

Pos logit contributions
aw+0.016
imes+0.014
isi+0.014
Le+0.014
 Remy+0.014
Neg logit contributions
bell-0.017
days-0.016
 t-0.016
 stuffed-0.015
 unp-0.015
TokenH
Token ID39
Feature activation-2.29e-02

Pos logit contributions
bell+0.011
days+0.010
 t+0.010
 stuffed+0.010
 unp+0.009
Neg logit contributions
aw-0.011
 Remy-0.010
imes-0.010
isi-0.010
arling-0.010
Token every
Token ID790
Feature activation-1.13e-02

Pos logit contributions
aw+0.038
 Remy+0.037
imes+0.034
Le+0.034
 Sasha+0.034
Neg logit contributions
bell-0.037
days-0.033
 stuffed-0.031
 Mechan-0.031
 t-0.031
Token day
Token ID1110
Feature activation+7.08e-05

Pos logit contributions
bell+0.023
days+0.021
 t+0.021
 stuffed+0.021
 Mechan+0.020
Neg logit contributions
aw-0.018
Le-0.017
 Remy-0.017
una-0.016
isi-0.016
Token Tim
Token ID5045
Feature activation+4.27e-03

Pos logit contributions
aw+0.000
Le+0.000
imes+0.000
isi+0.000
una+0.000
Neg logit contributions
bell-0.000
days-0.000
 t-0.000
 unp-0.000
 stuffed-0.000
Token would
Token ID561
Feature activation-1.41e-02

Pos logit contributions
aw+0.009
 Remy+0.008
Le+0.008
imes+0.008
isi+0.008
Neg logit contributions
bell-0.007
days-0.006
 stuffed-0.006
 t-0.006
 Mechan-0.006
Token eat
Token ID4483
Feature activation+5.01e-02

Pos logit contributions
bell+0.024
days+0.023
 Mechan+0.022
 stuffed+0.021
 t+0.020
Neg logit contributions
aw-0.026
 Remy-0.025
isi-0.024
Le-0.024
 Sasha-0.024
Token pineapple
Token ID45540
Feature activation+1.22e-01

Pos logit contributions
aw+0.095
 Remy+0.086
imes+0.085
Le+0.084
una+0.082
Neg logit contributions
bell-0.091
days-0.087
 Mechan-0.080
 t-0.080
 stuffed-0.078
Token again
Token ID757
Feature activation-8.26e-03

Pos logit contributions
aw+0.267
Le+0.252
isi+0.248
 Remy+0.245
imes+0.242
Neg logit contributions
bell-0.167
days-0.160
 t-0.158
 stuffed-0.149
 unp-0.145
Token.
Token ID13
Feature activation-2.19e-03

Pos logit contributions
bell+0.014
days+0.012
 Mechan+0.012
 stuffed+0.012
 t+0.012
Neg logit contributions
aw-0.017
 Remy-0.016
Le-0.015
imes-0.015
una-0.015
Token He
Token ID679
Feature activation+5.15e-03

Pos logit contributions
bell+0.004
days+0.004
 stuffed+0.004
 t+0.004
 unp+0.003
Neg logit contributions
aw-0.004
 Remy-0.004
imes-0.004
Le-0.004
isi-0.004
Token enjoyed
Token ID8359
Feature activation-2.06e-02

Pos logit contributions
aw+0.010
 Remy+0.009
Le+0.009
imes+0.009
una+0.009
Neg logit contributions
bell-0.009
days-0.008
 Mechan-0.008
 t-0.007
 py-0.007
Token eating
Token ID6600
Feature activation+4.89e-02

Pos logit contributions
bell+0.040
days+0.037
 t+0.033
 Mechan+0.033
 stuffed+0.033
Neg logit contributions
aw-0.037
 Remy-0.035
Le-0.034
imes-0.033
una-0.032
Token jar
Token ID17379
Feature activation-1.37e-04

Pos logit contributions
 t+0.019
 stuffed+0.017
bell+0.017
days+0.016
 unp+0.015
Neg logit contributions
aw-0.035
isi-0.032
Le-0.031
imes-0.031
crow-0.030
Token.
Token ID13
Feature activation+5.18e-04

Pos logit contributions
bell+0.000
days+0.000
 Mechan+0.000
 t+0.000
 stuffed+0.000
Neg logit contributions
aw-0.000
imes-0.000
 Remy-0.000
Le-0.000
una-0.000
Token He
Token ID679
Feature activation+4.45e-03

Pos logit contributions
aw+0.001
 Remy+0.001
Le+0.001
imes+0.001
una+0.001
Neg logit contributions
days-0.001
bell-0.001
 stuffed-0.001
 t-0.001
 Mechan-0.001
Token tried
Token ID3088
Feature activation+5.06e-02

Pos logit contributions
aw+0.009
isi+0.008
imes+0.008
Le+0.008
 Remy+0.008
Neg logit contributions
bell-0.007
 t-0.007
days-0.006
 stuffed-0.006
 unp-0.006
Token to
Token ID284
Feature activation+2.68e-02

Pos logit contributions
aw+0.120
isi+0.111
imes+0.108
iles+0.107
opard+0.105
Neg logit contributions
 t-0.068
bell-0.063
 stuffed-0.059
days-0.057
 unp-0.056
Token trap
Token ID12840
Feature activation+1.22e-01

Pos logit contributions
aw+0.058
imes+0.052
isi+0.049
Le+0.049
arling+0.049
Neg logit contributions
 t-0.043
bell-0.042
 stuffed-0.041
days-0.040
 decor-0.037
Token it
Token ID340
Feature activation+1.65e-02

Pos logit contributions
aw+0.256
isi+0.243
Le+0.237
imes+0.233
emy+0.231
Neg logit contributions
bell-0.183
 t-0.181
 stuffed-0.170
days-0.159
 unp-0.158
Token inside
Token ID2641
Feature activation-1.51e-02

Pos logit contributions
aw+0.034
Le+0.031
imes+0.031
 Remy+0.031
isi+0.030
Neg logit contributions
bell-0.026
days-0.025
 t-0.024
 stuffed-0.023
 unp-0.023
Token.
Token ID13
Feature activation+5.41e-03

Pos logit contributions
bell+0.027
days+0.025
 Mechan+0.024
 t+0.023
 stuffed+0.023
Neg logit contributions
aw-0.029
 Remy-0.026
imes-0.026
Le-0.026
una-0.025
Token The
Token ID383
Feature activation-5.80e-03

Pos logit contributions
aw+0.010
 Remy+0.010
Le+0.009
imes+0.009
una+0.008
Neg logit contributions
days-0.010
bell-0.010
 stuffed-0.009
 t-0.009
 Mechan-0.009
Token mosquito
Token ID35446
Feature activation+2.18e-02

Pos logit contributions
 t+0.011
 stuffed+0.010
bell+0.010
days+0.009
 lamp+0.009
Neg logit contributions
aw-0.011
isi-0.010
Phil-0.010
 Remy-0.010
Le-0.009
Token
Token ID198
Feature activation+2.58e-03

Pos logit contributions
aw+0.005
imes+0.005
isi+0.005
Le+0.005
una+0.005
Neg logit contributions
bell-0.003
days-0.003
 t-0.003
 unp-0.002
 stuffed-0.002
Token
Token ID198
Feature activation+5.17e-03

Pos logit contributions
aw+0.006
imes+0.006
iles+0.006
isi+0.006
opard+0.006
Neg logit contributions
bell-0.003
days-0.003
 unp-0.003
 t-0.003
 Gr-0.002
TokenSo
Token ID2396
Feature activation+3.01e-02

Pos logit contributions
aw+0.010
imes+0.010
 Remy+0.009
iles+0.009
isi+0.009
Neg logit contributions
bell-0.009
days-0.008
 t-0.008
 unp-0.008
 stuffed-0.007
Token she
Token ID673
Feature activation-7.18e-03

Pos logit contributions
aw+0.063
Le+0.058
imes+0.057
isi+0.057
 Remy+0.057
Neg logit contributions
bell-0.047
days-0.045
 t-0.043
 stuffed-0.042
 unp-0.041
Token brought
Token ID3181
Feature activation-1.98e-02

Pos logit contributions
days+0.012
bell+0.012
 t+0.011
 Mechan+0.011
 stuffed+0.011
Neg logit contributions
aw-0.014
 Remy-0.013
Le-0.013
isi-0.012
imes-0.012
Token bread
Token ID8509
Feature activation+1.22e-01

Pos logit contributions
 t+0.027
bell+0.025
 stuffed+0.025
 unp+0.023
 decor+0.023
Neg logit contributions
aw-0.045
iles-0.042
opard-0.042
Le-0.042
imes-0.042
Token and
Token ID290
Feature activation+7.54e-03

Pos logit contributions
aw+0.265
isi+0.242
Le+0.239
arling+0.229
iles+0.229
Neg logit contributions
 t-0.177
days-0.169
 stuffed-0.167
bell-0.166
 unp-0.151
Token leaves
Token ID5667
Feature activation+6.44e-02

Pos logit contributions
aw+0.013
Le+0.012
imes+0.012
isi+0.012
 Remy+0.011
Neg logit contributions
bell-0.014
days-0.014
 t-0.014
 stuffed-0.013
 unp-0.013
Token to
Token ID284
Feature activation+1.21e-03

Pos logit contributions
aw+0.120
Le+0.109
imes+0.108
 Remy+0.108
isi+0.106
Neg logit contributions
bell-0.115
days-0.110
 t-0.105
 stuffed-0.102
 Mechan-0.101
Token the
Token ID262
Feature activation+1.38e-02

Pos logit contributions
aw+0.003
imes+0.003
arling+0.003
Le+0.002
isi+0.002
Neg logit contributions
 t-0.002
 stuffed-0.002
bell-0.002
 decor-0.002
days-0.001
Token park
Token ID3952
Feature activation+3.76e-03

Pos logit contributions
imes+0.028
aw+0.027
live+0.027
Le+0.027
una+0.026
Neg logit contributions
 t-0.024
 stuffed-0.021
bell-0.020
 Gr-0.019
 design-0.018
Token with
Token ID351
Feature activation+6.39e-04

Pos logit contributions
bell+0.093
days+0.088
 t+0.083
 stuffed+0.081
 Mechan+0.079
Neg logit contributions
aw-0.127
Le-0.118
 Remy-0.116
imes-0.115
isi-0.113
Token lots
Token ID6041
Feature activation-1.39e-03

Pos logit contributions
aw+0.001
 Remy+0.001
Le+0.001
imes+0.001
una+0.001
Neg logit contributions
bell-0.001
days-0.001
 Mechan-0.001
 t-0.001
 stuffed-0.001
Token of
Token ID286
Feature activation-4.46e-03

Pos logit contributions
bell+0.003
days+0.003
 t+0.003
 Mechan+0.003
 stuffed+0.003
Neg logit contributions
aw-0.002
Le-0.002
imes-0.002
 Remy-0.002
una-0.002
Token other
Token ID584
Feature activation+9.96e-02

Pos logit contributions
bell+0.008
days+0.008
 Mechan+0.007
 t+0.007
 unp+0.007
Neg logit contributions
aw-0.008
 Remy-0.007
Le-0.007
imes-0.007
una-0.007
Token l
Token ID300
Feature activation+8.13e-02

Pos logit contributions
aw+0.142
 Remy+0.121
imes+0.118
Le+0.118
iles+0.115
Neg logit contributions
bell-0.231
days-0.220
 Mechan-0.205
 t-0.202
 stuffed-0.196
Tokenimes
Token ID999
Feature activation+1.22e-01

Pos logit contributions
isi+0.111
 Remy+0.109
Le+0.109
aw+0.107
 Duke+0.102
Neg logit contributions
bell-0.159
days-0.156
 unp-0.153
 t-0.144
 decor-0.141
Token.
Token ID13
Feature activation-8.39e-03

Pos logit contributions
aw+0.259
Le+0.244
isi+0.238
 Remy+0.237
imes+0.235
Neg logit contributions
bell-0.179
days-0.170
 t-0.166
 stuffed-0.158
 unp-0.157
Token The
Token ID383
Feature activation-3.17e-03

Pos logit contributions
bell+0.013
days+0.013
 t+0.012
 stuffed+0.012
 Mechan+0.011
Neg logit contributions
aw-0.018
 Remy-0.017
Le-0.016
imes-0.016
 Sasha-0.016
Token lime
Token ID28738
Feature activation+4.77e-02

Pos logit contributions
bell+0.006
days+0.006
 t+0.005
 stuffed+0.005
 unp+0.005
Neg logit contributions
aw-0.006
Le-0.005
 Remy-0.005
imes-0.005
isi-0.005
Token was
Token ID373
Feature activation-1.28e-02

Pos logit contributions
aw+0.102
Le+0.094
 Remy+0.093
imes+0.093
isi+0.092
Neg logit contributions
bell-0.072
days-0.069
 t-0.064
 stuffed-0.062
 Mechan-0.061
Token so
Token ID523
Feature activation-5.72e-03

Pos logit contributions
bell+0.021
days+0.021
 Mechan+0.019
 t+0.018
 stuffed+0.018
Neg logit contributions
aw-0.026
 Remy-0.023
Le-0.023
imes-0.023
 Sasha-0.023
Token walked
Token ID6807
Feature activation-2.62e-02

Pos logit contributions
days+0.023
bell+0.023
 Mechan+0.021
 spoiler+0.019
 Sus+0.019
Neg logit contributions
aw-0.022
Le-0.020
 Remy-0.020
 Sasha-0.018
una-0.017
Token and
Token ID290
Feature activation+1.45e-02

Pos logit contributions
bell+0.045
days+0.043
 t+0.041
 stuffed+0.040
 unp+0.039
Neg logit contributions
aw-0.051
Le-0.047
imes-0.046
 Remy-0.046
isi-0.046
Token he
Token ID339
Feature activation-6.32e-03

Pos logit contributions
aw+0.028
 Remy+0.026
Le+0.026
 Sasha+0.024
isi+0.024
Neg logit contributions
bell-0.025
days-0.024
 Mechan-0.022
 stuffed-0.021
 t-0.021
Token ate
Token ID15063
Feature activation+4.01e-02

Pos logit contributions
bell+0.012
days+0.012
 Mechan+0.011
 stuffed+0.010
 t+0.010
Neg logit contributions
aw-0.011
Le-0.010
 Remy-0.010
 Sasha-0.009
 Duke-0.009
Token only
Token ID691
Feature activation+4.74e-02

Pos logit contributions
aw+0.079
 Remy+0.071
Le+0.070
imes+0.070
una+0.068
Neg logit contributions
bell-0.071
days-0.068
 Mechan-0.063
 t-0.061
 stuffed-0.061
Token bread
Token ID8509
Feature activation+1.21e-01

Pos logit contributions
aw+0.087
 Remy+0.078
imes+0.078
Le+0.076
 Sasha+0.075
Neg logit contributions
bell-0.088
days-0.082
 Mechan-0.078
 t-0.074
 stuffed-0.073
Token and
Token ID290
Feature activation+9.63e-04

Pos logit contributions
aw+0.273
Le+0.260
isi+0.254
imes+0.250
 Remy+0.248
Neg logit contributions
bell-0.156
 t-0.152
days-0.150
 stuffed-0.144
 unp-0.135
Token apples
Token ID22514
Feature activation+7.42e-02

Pos logit contributions
aw+0.002
Le+0.002
 Remy+0.002
imes+0.002
isi+0.002
Neg logit contributions
bell-0.002
days-0.002
 t-0.001
 Mechan-0.001
 stuffed-0.001
Token.
Token ID13
Feature activation-1.88e-03

Pos logit contributions
aw+0.149
Le+0.135
 Remy+0.134
imes+0.133
isi+0.131
Neg logit contributions
bell-0.123
days-0.118
 t-0.108
 stuffed-0.107
 Mechan-0.107
Token
Token ID198
Feature activation+4.20e-03

Pos logit contributions
bell+0.003
days+0.003
 stuffed+0.003
 t+0.003
 Mechan+0.003
Neg logit contributions
aw-0.004
 Remy-0.004
Le-0.004
imes-0.003
isi-0.003
Token
Token ID198
Feature activation+6.66e-03

Pos logit contributions
aw+0.008
imes+0.008
isi+0.008
iles+0.008
arling+0.008
Neg logit contributions
bell-0.007
days-0.006
 t-0.006
 unp-0.006
 stuffed-0.006
Token probably
Token ID2192
Feature activation+9.63e-03

Pos logit contributions
bell+0.035
days+0.034
 Mechan+0.032
 stuffed+0.030
 t+0.030
Neg logit contributions
aw-0.033
imes-0.028
 Remy-0.027
Le-0.027
 Sasha-0.027
Token celebrating
Token ID17499
Feature activation-4.24e-02

Pos logit contributions
aw+0.018
imes+0.016
 Remy+0.016
Le+0.015
una+0.015
Neg logit contributions
bell-0.017
days-0.016
 Mechan-0.015
 t-0.015
 stuffed-0.014
Token their
Token ID511
Feature activation-1.47e-02

Pos logit contributions
bell+0.082
days+0.076
 Mechan+0.074
 stuffed+0.068
 t+0.067
Neg logit contributions
aw-0.074
 Remy-0.065
una-0.063
Le-0.062
imes-0.062
Token own
Token ID898
Feature activation-3.18e-02

Pos logit contributions
bell+0.028
 Mechan+0.025
days+0.025
 spoiler+0.023
 t+0.023
Neg logit contributions
aw-0.026
Le-0.022
una-0.022
imes-0.022
isi-0.021
Token birth
Token ID4082
Feature activation-1.15e-01

Pos logit contributions
bell+0.059
 Mechan+0.054
days+0.053
 t+0.049
 stuffed+0.049
Neg logit contributions
aw-0.057
una-0.049
imes-0.049
 Sasha-0.047
Le-0.047
Tokendays
Token ID12545
Feature activation-1.66e-01

Pos logit contributions
 stuffed+0.064
 t+0.062
 Mechan+0.060
 py+0.060
bell+0.052
Neg logit contributions
aw-0.315
imes-0.304
isi-0.298
iles-0.295
arling-0.287
Token.
Token ID13
Feature activation-7.38e-03

Pos logit contributions
bell+0.317
 Mechan+0.313
 stuffed+0.309
 py+0.303
days+0.300
Neg logit contributions
aw-0.272
imes-0.213
isi-0.206
una-0.200
 Remy-0.198
Token Just
Token ID2329
Feature activation-8.26e-03

Pos logit contributions
bell+0.013
 stuffed+0.013
days+0.012
 t+0.012
 Mechan+0.011
Neg logit contributions
aw-0.014
 Remy-0.012
Le-0.012
 Sasha-0.012
imes-0.012
Token when
Token ID618
Feature activation+3.31e-02

Pos logit contributions
bell+0.017
 Mechan+0.016
days+0.015
 stuffed+0.014
 t+0.014
Neg logit contributions
aw-0.013
 Remy-0.012
 Sasha-0.012
imes-0.011
una-0.011
Token he
Token ID339
Feature activation-8.92e-03

Pos logit contributions
 Remy+0.047
aw+0.046
 Sasha+0.045
Le+0.043
 Duke+0.043
Neg logit contributions
bell-0.066
days-0.063
 stuffed-0.061
 Mechan-0.060
 py-0.059
Token was
Token ID373
Feature activation-7.71e-04

Pos logit contributions
days+0.014
bell+0.014
 Mechan+0.014
 stuffed+0.013
 spoiler+0.013
Neg logit contributions
aw-0.017
Le-0.015
 Remy-0.015
isi-0.014
una-0.014
Token time
Token ID640
Feature activation+2.42e-02

Pos logit contributions
bell+0.022
days+0.021
 Mechan+0.019
 t+0.019
 stuffed+0.019
Neg logit contributions
aw-0.021
 Remy-0.020
Le-0.019
isi-0.019
una-0.019
Token to
Token ID284
Feature activation-1.16e-03

Pos logit contributions
aw+0.040
imes+0.036
 Remy+0.036
Le+0.036
una+0.035
Neg logit contributions
bell-0.048
days-0.045
 t-0.044
 stuffed-0.043
 Mechan-0.042
Token celebrate
Token ID10648
Feature activation-4.42e-02

Pos logit contributions
bell+0.002
days+0.002
 Mechan+0.002
 stuffed+0.002
 py+0.002
Neg logit contributions
aw-0.002
 Remy-0.002
isi-0.002
una-0.001
 Sasha-0.001
Token their
Token ID511
Feature activation-1.65e-02

Pos logit contributions
bell+0.080
days+0.074
 t+0.070
 Mechan+0.069
 stuffed+0.068
Neg logit contributions
aw-0.084
 Remy-0.076
Le-0.076
una-0.074
imes-0.074
Token birth
Token ID4082
Feature activation-1.06e-01

Pos logit contributions
bell+0.028
 Mechan+0.027
days+0.025
 spoiler+0.024
cel+0.023
Neg logit contributions
aw-0.029
una-0.025
imes-0.025
iles-0.025
 Remy-0.025
Tokendays
Token ID12545
Feature activation-1.61e-01

Pos logit contributions
 t+0.058
 stuffed+0.057
 Mechan+0.054
 py+0.053
 spoiler+0.048
Neg logit contributions
aw-0.289
imes-0.272
isi-0.271
iles-0.263
una-0.261
Token.
Token ID13
Feature activation-7.18e-03

Pos logit contributions
 Mechan+0.354
 stuffed+0.347
 prope+0.344
 py+0.343
bell+0.337
Neg logit contributions
aw-0.210
isi-0.132
imes-0.132
una-0.129
arling-0.126
Token Max
Token ID5436
Feature activation-8.97e-03

Pos logit contributions
bell+0.009
 t+0.009
 stuffed+0.008
days+0.008
 Gr+0.008
Neg logit contributions
aw-0.017
imes-0.016
isi-0.015
Le-0.015
una-0.015
Token had
Token ID550
Feature activation+3.90e-03

Pos logit contributions
bell+0.017
days+0.017
 Mechan+0.016
 spoiler+0.015
 py+0.015
Neg logit contributions
aw-0.015
 Remy-0.015
 Sasha-0.013
Le-0.013
una-0.013
Token a
Token ID257
Feature activation-1.48e-02

Pos logit contributions
aw+0.006
Le+0.005
 Remy+0.005
una+0.005
 Sasha+0.004
Neg logit contributions
bell-0.009
days-0.008
 spoiler-0.007
 Mechan-0.007
lights-0.007
Token lot
Token ID1256
Feature activation+5.95e-02

Pos logit contributions
bell+0.029
days+0.029
 Mechan+0.025
 unp+0.025
 Jos+0.024
Neg logit contributions
aw-0.022
 Remy-0.021
isi-0.021
Le-0.021
una-0.020
Token And
Token ID843
Feature activation+5.95e-03

Pos logit contributions
bell+0.002
days+0.002
 t+0.002
 stuffed+0.002
 unp+0.002
Neg logit contributions
aw-0.002
 Remy-0.002
Le-0.002
imes-0.002
isi-0.002
Token that
Token ID326
Feature activation+1.55e-03

Pos logit contributions
aw+0.011
 Remy+0.010
Le+0.010
imes+0.010
isi+0.010
Neg logit contributions
bell-0.011
days-0.010
 t-0.010
 stuffed-0.009
 Mechan-0.009
Token's
Token ID338
Feature activation-6.81e-03

Pos logit contributions
aw+0.003
 Remy+0.003
Le+0.002
una+0.002
imes+0.002
Neg logit contributions
bell-0.003
days-0.003
 stuffed-0.003
 t-0.002
 Mechan-0.002
Token why
Token ID1521
Feature activation-1.22e-02

Pos logit contributions
bell+0.014
days+0.013
 t+0.013
 stuffed+0.012
 Mechan+0.012
Neg logit contributions
aw-0.011
 Remy-0.010
Le-0.010
imes-0.010
isi-0.010
Token Tues
Token ID48496
Feature activation-1.03e-01

Pos logit contributions
bell+0.025
days+0.023
 Mechan+0.021
 stuffed+0.020
 t+0.020
Neg logit contributions
 Remy-0.020
aw-0.020
imes-0.018
 Sasha-0.018
Le-0.018
Tokendays
Token ID12545
Feature activation-1.58e-01

Pos logit contributions
 stuffed+0.108
bell+0.105
 t+0.098
 matt+0.089
 py+0.087
Neg logit contributions
aw-0.245
imes-0.230
opard-0.230
arling-0.229
live-0.226
Token are
Token ID389
Feature activation-1.49e-02

Pos logit contributions
bell+0.269
 stuffed+0.253
days+0.252
 py+0.249
 Mechan+0.245
Neg logit contributions
aw-0.284
crow-0.229
imes-0.228
iles-0.224
 Remy-0.222
Token so
Token ID523
Feature activation-9.19e-03

Pos logit contributions
bell+0.027
days+0.026
 t+0.024
 stuffed+0.024
 Mechan+0.024
Neg logit contributions
aw-0.027
 Remy-0.024
imes-0.024
Le-0.024
isi-0.024
Token important
Token ID1593
Feature activation+2.64e-02

Pos logit contributions
bell+0.017
days+0.017
 stuffed+0.016
 Mechan+0.016
 t+0.016
Neg logit contributions
aw-0.015
imes-0.013
 Remy-0.013
 Sasha-0.012
Le-0.012
Token.
Token ID13
Feature activation-7.89e-03

Pos logit contributions
aw+0.047
 Remy+0.042
imes+0.041
una+0.040
Le+0.040
Neg logit contributions
bell-0.051
days-0.048
 Mechan-0.044
 t-0.044
 stuffed-0.043
Token<|endoftext|>
Token ID50256
Feature activation+7.53e-03

Pos logit contributions
bell+0.014
days+0.013
 t+0.013
 stuffed+0.013
 unp+0.012
Neg logit contributions
aw-0.015
Le-0.014
 Remy-0.014
imes-0.013
isi-0.013
Token liked
Token ID8288
Feature activation-7.27e-03

Pos logit contributions
aw+0.056
Le+0.050
isi+0.047
 Remy+0.046
imes+0.045
Neg logit contributions
bell-0.058
days-0.053
 Mechan-0.052
etti-0.051
 py-0.051
Token to
Token ID284
Feature activation-2.83e-03

Pos logit contributions
bell+0.016
days+0.016
 Mechan+0.014
 t+0.014
 stuffed+0.014
Neg logit contributions
aw-0.010
 Remy-0.009
Le-0.009
imes-0.008
una-0.008
Token celebrate
Token ID10648
Feature activation-4.13e-02

Pos logit contributions
 asleep+0.006
ksh+0.005
bell+0.005
rily+0.005
 Mechan+0.005
Neg logit contributions
Fin-0.003
 Remy-0.003
 dads-0.003
Le-0.003
aw-0.003
Token their
Token ID511
Feature activation-1.11e-02

Pos logit contributions
bell+0.076
days+0.071
 Mechan+0.067
 t+0.066
 stuffed+0.065
Neg logit contributions
aw-0.078
Le-0.069
 Remy-0.069
una-0.068
imes-0.067
Token birth
Token ID4082
Feature activation-9.84e-02

Pos logit contributions
bell+0.019
days+0.018
 Mechan+0.018
 lit+0.016
 Sus+0.016
Neg logit contributions
aw-0.019
iles-0.017
Le-0.017
emy-0.017
 Remy-0.017
Tokendays
Token ID12545
Feature activation-1.50e-01

Pos logit contributions
 t+0.045
 stuffed+0.042
 py+0.041
bell+0.040
 Mechan+0.037
Neg logit contributions
aw-0.283
imes-0.265
isi-0.264
iles-0.263
Le-0.259
Token.
Token ID13
Feature activation-4.71e-03

Pos logit contributions
 Mechan+0.317
bell+0.297
 stuffed+0.297
 py+0.291
 spoiler+0.290
Neg logit contributions
aw-0.224
una-0.162
imes-0.161
isi-0.150
iles-0.150
Token Tim
Token ID5045
Feature activation-1.54e-03

Pos logit contributions
bell+0.007
days+0.007
 t+0.007
 stuffed+0.006
 unp+0.006
Neg logit contributions
aw-0.010
Le-0.009
imes-0.009
isi-0.009
 Remy-0.009
Token's
Token ID338
Feature activation-2.13e-02

Pos logit contributions
bell+0.003
days+0.003
 Mechan+0.002
 py+0.002
lights+0.002
Neg logit contributions
aw-0.003
Le-0.002
 Remy-0.002
una-0.002
isi-0.002
Token birthday
Token ID10955
Feature activation-7.40e-02

Pos logit contributions
bell+0.037
days+0.036
 Mechan+0.034
 unp+0.032
 lit+0.032
Neg logit contributions
aw-0.038
Le-0.033
 Remy-0.033
una-0.032
imes-0.032
Token was
Token ID373
Feature activation-1.47e-02

Pos logit contributions
bell+0.122
days+0.116
 Mechan+0.108
 stuffed+0.105
 t+0.104
Neg logit contributions
aw-0.145
una-0.126
isi-0.125
 Remy-0.125
Le-0.123
Token she
Token ID673
Feature activation-3.94e-02

Pos logit contributions
bell+0.013
days+0.012
 t+0.011
 stuffed+0.011
 Mechan+0.011
Neg logit contributions
aw-0.013
Le-0.012
 Remy-0.012
imes-0.012
isi-0.011
Token bowed
Token ID35737
Feature activation-2.35e-02

Pos logit contributions
days+0.065
bell+0.064
 Mechan+0.059
 Jos+0.056
 Sus+0.054
Neg logit contributions
aw-0.078
Le-0.068
 Remy-0.067
isi-0.065
imes-0.065
Token,
Token ID11
Feature activation+1.85e-03

Pos logit contributions
days+0.042
bell+0.041
 Mechan+0.040
 unp+0.039
 stuffed+0.038
Neg logit contributions
aw-0.042
 Remy-0.037
Le-0.036
 Sasha-0.035
imes-0.035
Token the
Token ID262
Feature activation+1.46e-03

Pos logit contributions
aw+0.003
 Remy+0.003
Le+0.003
imes+0.003
 Sasha+0.003
Neg logit contributions
bell-0.004
days-0.004
 Mechan-0.003
 t-0.003
 stuffed-0.003
Token town
Token ID3240
Feature activation-6.02e-02

Pos logit contributions
aw+0.003
Le+0.003
 Remy+0.002
imes+0.002
isi+0.002
Neg logit contributions
bell-0.003
days-0.002
 t-0.002
 stuffed-0.002
 unp-0.002
Tokenspe
Token ID4125
Feature activation-1.49e-01

Pos logit contributions
days+0.091
bell+0.089
 Mechan+0.087
 t+0.086
 stuffed+0.086
Neg logit contributions
aw-0.122
crow-0.104
Le-0.101
iles-0.100
isi-0.099
Tokenople
Token ID643
Feature activation-3.50e-02

Pos logit contributions
bell+0.276
 t+0.266
 stuffed+0.265
days+0.264
 py+0.255
Neg logit contributions
aw-0.286
Le-0.225
iles-0.222
crow-0.222
imes-0.219
Token stopped
Token ID5025
Feature activation+9.32e-03

Pos logit contributions
bell+0.059
days+0.056
 Mechan+0.055
 stuffed+0.053
 py+0.053
Neg logit contributions
aw-0.067
Le-0.056
iles-0.056
imes-0.056
isi-0.055
Token to
Token ID284
Feature activation-1.88e-03

Pos logit contributions
aw+0.017
 Remy+0.015
Le+0.015
 Sasha+0.014
iles+0.014
Neg logit contributions
bell-0.017
days-0.017
 stuffed-0.015
 Mechan-0.015
 t-0.015
Token admire
Token ID21099
Feature activation-4.16e-02

Pos logit contributions
days+0.003
bell+0.003
 Mechan+0.003
lights+0.003
 stuffed+0.003
Neg logit contributions
aw-0.003
isi-0.003
 Remy-0.003
Le-0.003
 Sasha-0.003
Token her
Token ID607
Feature activation-9.34e-03

Pos logit contributions
bell+0.082
days+0.081
 Mechan+0.078
 stuffed+0.073
 t+0.073
Neg logit contributions
aw-0.070
 Remy-0.060
Le-0.059
imes-0.058
 Sasha-0.058
Token heard
Token ID2982
Feature activation-5.49e-03

Pos logit contributions
bell+0.007
days+0.007
 Mechan+0.006
 stuffed+0.006
 t+0.006
Neg logit contributions
aw-0.006
Le-0.005
 Remy-0.005
imes-0.005
isi-0.005
Token before
Token ID878
Feature activation+4.30e-02

Pos logit contributions
days+0.011
bell+0.010
 Mechan+0.010
 stuffed+0.010
 t+0.010
Neg logit contributions
aw-0.010
una-0.008
isi-0.008
Le-0.008
imes-0.008
Token was
Token ID373
Feature activation+9.16e-03

Pos logit contributions
aw+0.069
 Remy+0.063
 Sasha+0.062
imes+0.059
Le+0.058
Neg logit contributions
days-0.082
bell-0.080
 Mechan-0.077
 stuffed-0.075
 t-0.072
Token the
Token ID262
Feature activation-1.33e-02

Pos logit contributions
aw+0.017
imes+0.015
Le+0.015
 Remy+0.015
isi+0.015
Neg logit contributions
bell-0.016
days-0.016
 t-0.014
 stuffed-0.014
 Mechan-0.014
Token door
Token ID3420
Feature activation-4.89e-02

Pos logit contributions
days+0.024
bell+0.024
 unp+0.021
 t+0.021
 Mechan+0.021
Neg logit contributions
aw-0.025
Le-0.022
isi-0.022
 Remy-0.021
una-0.021
Tokenbell
Token ID7923
Feature activation-1.49e-01

Pos logit contributions
 Mechan+0.081
days+0.081
 stuffed+0.075
 py+0.074
 t+0.072
Neg logit contributions
aw-0.088
ups-0.067
crow-0.067
arling-0.066
 strangers-0.065
Token.
Token ID13
Feature activation-8.49e-04

Pos logit contributions
days+0.249
 py+0.209
 Mechan+0.207
 stuffed+0.207
 unp+0.201
Neg logit contributions
aw-0.293
crow-0.235
isi-0.224
arling-0.220
 strangers-0.216
Token From
Token ID3574
Feature activation-1.35e-02

Pos logit contributions
bell+0.001
days+0.001
 t+0.001
 stuffed+0.001
 unp+0.001
Neg logit contributions
aw-0.002
Le-0.002
imes-0.002
 Remy-0.002
isi-0.002
Token then
Token ID788
Feature activation+1.48e-02

Pos logit contributions
bell+0.022
 t+0.021
 unp+0.020
 Sus+0.019
 stuffed+0.019
Neg logit contributions
imes-0.026
Le-0.025
aw-0.025
una-0.024
isi-0.024
Token on
Token ID319
Feature activation+2.63e-03

Pos logit contributions
aw+0.027
Le+0.025
isi+0.024
 Remy+0.024
imes+0.024
Neg logit contributions
bell-0.027
days-0.026
 t-0.025
 unp-0.024
 stuffed-0.024
Token,
Token ID11
Feature activation+1.72e-02

Pos logit contributions
aw+0.005
 Remy+0.005
Le+0.005
imes+0.004
 Sasha+0.004
Neg logit contributions
bell-0.005
days-0.005
 Mechan-0.004
 t-0.004
 stuffed-0.004
Token year
Token ID614
Feature activation-4.34e-02

Pos logit contributions
bell+0.024
 Mechan+0.023
days+0.023
 t+0.022
 stuffed+0.022
Neg logit contributions
aw-0.019
una-0.017
 Remy-0.016
Le-0.016
 Sasha-0.016
Token,
Token ID11
Feature activation+9.15e-03

Pos logit contributions
bell+0.078
days+0.076
 t+0.073
 Mechan+0.071
 stuffed+0.071
Neg logit contributions
aw-0.081
Le-0.072
imes-0.071
 Remy-0.071
una-0.070
Token on
Token ID319
Feature activation+9.54e-04

Pos logit contributions
aw+0.018
Le+0.016
imes+0.016
isi+0.016
 Remy+0.016
Neg logit contributions
bell-0.015
days-0.015
 t-0.014
 stuffed-0.014
 unp-0.013
Token their
Token ID511
Feature activation+1.89e-03

Pos logit contributions
aw+0.002
 Remy+0.002
Le+0.002
 Sasha+0.002
una+0.002
Neg logit contributions
bell-0.002
 Mechan-0.002
days-0.002
 t-0.002
 stuffed-0.002
Token birth
Token ID4082
Feature activation-8.41e-02

Pos logit contributions
aw+0.003
Le+0.003
 Remy+0.003
isi+0.003
una+0.003
Neg logit contributions
bell-0.003
days-0.003
 Mechan-0.003
 t-0.003
 unp-0.003
Tokendays
Token ID12545
Feature activation-1.48e-01

Pos logit contributions
 py+0.061
 Mechan+0.057
 stuffed+0.056
 t+0.055
 matt+0.054
Neg logit contributions
aw-0.219
imes-0.204
iles-0.198
isi-0.196
ile-0.194
Token,
Token ID11
Feature activation-5.15e-03

Pos logit contributions
bell+0.247
 Mechan+0.232
days+0.231
 stuffed+0.226
 py+0.226
Neg logit contributions
aw-0.286
crow-0.233
imes-0.229
isi-0.228
Le-0.224
Token they
Token ID484
Feature activation-1.94e-02

Pos logit contributions
bell+0.009
days+0.009
 t+0.008
 Mechan+0.008
 stuffed+0.008
Neg logit contributions
aw-0.010
Le-0.009
 Remy-0.009
imes-0.009
una-0.009
Token would
Token ID561
Feature activation-2.02e-02

Pos logit contributions
bell+0.033
days+0.031
 Mechan+0.030
 py+0.030
 stuffed+0.029
Neg logit contributions
aw-0.036
Le-0.033
isi-0.032
 Remy-0.032
imes-0.032
Token celebrate
Token ID10648
Feature activation-5.02e-02

Pos logit contributions
bell+0.035
 Mechan+0.034
days+0.033
 py+0.031
 matt+0.031
Neg logit contributions
aw-0.034
 Remy-0.032
isi-0.032
Le-0.031
 Sasha-0.031
Token together
Token ID1978
Feature activation-1.77e-02

Pos logit contributions
bell+0.094
 Mechan+0.086
days+0.084
 t+0.080
 stuffed+0.078
Neg logit contributions
aw-0.094
Le-0.083
 Remy-0.082
una-0.082
imes-0.080
Token.
Token ID13
Feature activation-4.16e-04

Pos logit contributions
aw+0.047
Le+0.039
una+0.038
 Remy+0.038
imes+0.038
Neg logit contributions
days-0.060
bell-0.056
 stuffed-0.055
 Mechan-0.055
 py-0.053
Token It
Token ID632
Feature activation+2.28e-03

Pos logit contributions
days+0.001
bell+0.001
 t+0.001
 stuffed+0.001
 Mechan+0.001
Neg logit contributions
aw-0.001
 Remy-0.001
imes-0.001
Le-0.001
una-0.001
Token is
Token ID318
Feature activation-1.11e-03

Pos logit contributions
aw+0.004
Le+0.004
 Remy+0.004
imes+0.004
una+0.004
Neg logit contributions
bell-0.004
days-0.004
 t-0.004
 stuffed-0.004
 Mechan-0.004
Token the
Token ID262
Feature activation-2.17e-02

Pos logit contributions
bell+0.002
 t+0.002
days+0.002
 stuffed+0.002
 unp+0.001
Neg logit contributions
aw-0.002
Le-0.002
isi-0.002
imes-0.002
 Remy-0.002
Token door
Token ID3420
Feature activation-5.46e-02

Pos logit contributions
bell+0.036
 t+0.034
days+0.034
 stuffed+0.033
 unp+0.031
Neg logit contributions
aw-0.043
Le-0.040
 Remy-0.039
imes-0.039
isi-0.039
Tokenbell
Token ID7923
Feature activation-1.44e-01

Pos logit contributions
days+0.100
 Mechan+0.093
 stuffed+0.088
 Gr+0.086
 Sus+0.085
Neg logit contributions
aw-0.100
ups-0.075
arling-0.074
iles-0.074
una-0.071
Token.
Token ID13
Feature activation-3.96e-03

Pos logit contributions
days+0.285
 stuffed+0.253
 Mechan+0.249
 unp+0.245
 py+0.244
Neg logit contributions
aw-0.267
una-0.189
arling-0.189
crow-0.189
isi-0.186
Token Mom
Token ID11254
Feature activation-2.61e-02

Pos logit contributions
days+0.007
bell+0.007
 t+0.006
 stuffed+0.006
 Mechan+0.006
Neg logit contributions
aw-0.008
 Remy-0.007
imes-0.007
Le-0.007
una-0.007
Tokenmy
Token ID1820
Feature activation-2.17e-02

Pos logit contributions
bell+0.042
days+0.040
 t+0.039
 stuffed+0.037
 unp+0.036
Neg logit contributions
aw-0.053
Le-0.049
 Remy-0.048
imes-0.048
isi-0.048
Token is
Token ID318
Feature activation-8.09e-03

Pos logit contributions
bell+0.037
days+0.035
 t+0.034
 stuffed+0.033
 unp+0.032
Neg logit contributions
aw-0.042
Le-0.039
imes-0.038
 Remy-0.038
isi-0.038
Token home
Token ID1363
Feature activation-1.63e-02

Pos logit contributions
bell+0.014
days+0.014
 t+0.013
 stuffed+0.013
 unp+0.013
Neg logit contributions
aw-0.015
Le-0.014
 Remy-0.014
imes-0.014
isi-0.014
Token ones
Token ID3392
Feature activation-9.17e-03

Pos logit contributions
aw+0.055
Le+0.049
imes+0.049
 Remy+0.049
isi+0.048
Neg logit contributions
bell-0.054
days-0.052
 t-0.049
 stuffed-0.048
 Mechan-0.048
Token are
Token ID389
Feature activation-2.52e-02

Pos logit contributions
bell+0.016
days+0.015
 t+0.015
 stuffed+0.014
 unp+0.014
Neg logit contributions
aw-0.017
Le-0.016
 Remy-0.016
isi-0.016
imes-0.016
Token yellow
Token ID7872
Feature activation-6.65e-03

Pos logit contributions
bell+0.039
 t+0.038
 stuffed+0.037
 unp+0.036
days+0.035
Neg logit contributions
aw-0.053
Le-0.049
isi-0.048
arling-0.047
imes-0.046
Token and
Token ID290
Feature activation-3.97e-02

Pos logit contributions
bell+0.010
days+0.010
 Mechan+0.009
 unp+0.009
 stuffed+0.009
Neg logit contributions
aw-0.014
imes-0.013
 Remy-0.012
una-0.012
iles-0.012
Token the
Token ID262
Feature activation-1.94e-02

Pos logit contributions
bell+0.067
days+0.066
 Mechan+0.061
 stuffed+0.056
 t+0.055
Neg logit contributions
aw-0.074
 Remy-0.072
Le-0.069
imes-0.069
 Sasha-0.066
Token un
Token ID555
Feature activation-1.44e-01

Pos logit contributions
bell+0.035
days+0.034
 t+0.033
 stuffed+0.032
 unp+0.031
Neg logit contributions
aw-0.035
Le-0.032
 Remy-0.032
imes-0.032
isi-0.031
Tokenri
Token ID380
Feature activation-1.03e-01

Pos logit contributions
bell+0.245
days+0.240
 t+0.234
 stuffed+0.232
 unp+0.220
Neg logit contributions
aw-0.280
imes-0.247
Le-0.242
opard-0.237
isi-0.236
Tokenpe
Token ID431
Feature activation-5.59e-02

Pos logit contributions
bell+0.189
days+0.183
 t+0.171
 stuffed+0.170
 Mechan+0.169
Neg logit contributions
aw-0.193
imes-0.170
Le-0.168
una-0.166
isi-0.164
Token ones
Token ID3392
Feature activation-1.86e-02

Pos logit contributions
bell+0.100
days+0.095
 t+0.092
 stuffed+0.090
 Mechan+0.088
Neg logit contributions
aw-0.104
Le-0.093
imes-0.093
 Remy-0.092
isi-0.091
Token are
Token ID389
Feature activation-3.06e-02

Pos logit contributions
bell+0.031
days+0.030
 t+0.029
 stuffed+0.028
 unp+0.027
Neg logit contributions
aw-0.036
Le-0.034
 Remy-0.033
isi-0.033
imes-0.033
Token green
Token ID4077
Feature activation-1.04e-02

Pos logit contributions
bell+0.048
 t+0.046
days+0.045
 stuffed+0.044
 unp+0.043
Neg logit contributions
aw-0.063
Le-0.059
isi-0.057
 Remy-0.056
imes-0.056
Token to
Token ID284
Feature activation+7.49e-03

Pos logit contributions
bell+0.042
days+0.042
 stuffed+0.040
 t+0.040
 Mechan+0.040
Neg logit contributions
aw-0.035
isi-0.031
 Remy-0.031
 Sasha-0.031
Le-0.030
Token celebrate
Token ID10648
Feature activation-3.54e-02

Pos logit contributions
aw+0.014
isi+0.013
 Remy+0.013
Le+0.013
 Sasha+0.012
Neg logit contributions
bell-0.013
days-0.012
 Mechan-0.012
 stuffed-0.012
 t-0.011
Token all
Token ID477
Feature activation+6.40e-03

Pos logit contributions
bell+0.067
 Mechan+0.061
days+0.060
 t+0.057
 stuffed+0.056
Neg logit contributions
aw-0.066
 Remy-0.057
Le-0.057
una-0.056
imes-0.056
Token her
Token ID607
Feature activation-2.09e-03

Pos logit contributions
aw+0.012
Le+0.011
 Remy+0.011
imes+0.011
isi+0.011
Neg logit contributions
bell-0.011
days-0.011
 t-0.010
 stuffed-0.010
 unp-0.010
Token birth
Token ID4082
Feature activation-8.40e-02

Pos logit contributions
bell+0.005
 Mechan+0.004
days+0.004
 spoiler+0.004
 t+0.004
Neg logit contributions
aw-0.003
imes-0.003
una-0.003
iles-0.002
Le-0.002
Tokendays
Token ID12545
Feature activation-1.44e-01

Pos logit contributions
 t+0.059
 Mechan+0.057
 stuffed+0.057
 py+0.056
bell+0.056
Neg logit contributions
aw-0.217
imes-0.203
iles-0.197
arling-0.195
isi-0.195
Token together
Token ID1978
Feature activation-1.75e-02

Pos logit contributions
 Mechan+0.297
 spoiler+0.279
 stuffed+0.272
bell+0.265
 py+0.264
Neg logit contributions
aw-0.225
imes-0.159
ups-0.157
arling-0.151
isi-0.149
Token.
Token ID13
Feature activation-4.85e-03

Pos logit contributions
bell+0.035
 Mechan+0.034
days+0.031
 stuffed+0.031
 spoiler+0.030
Neg logit contributions
aw-0.029
imes-0.024
 Sasha-0.023
Le-0.023
una-0.023
Token<|endoftext|>
Token ID50256
Feature activation+1.28e-02

Pos logit contributions
bell+0.008
 t+0.008
 stuffed+0.008
days+0.008
 Mechan+0.007
Neg logit contributions
aw-0.009
 Remy-0.008
Le-0.008
isi-0.008
imes-0.008
TokenOnce
Token ID7454
Feature activation-1.13e-02

Pos logit contributions
aw+0.019
Le+0.017
 Remy+0.016
imes+0.016
isi+0.016
Neg logit contributions
bell-0.028
days-0.027
 t-0.026
 stuffed-0.026
 unp-0.025
Token upon
Token ID2402
Feature activation+1.23e-02

Pos logit contributions
bell+0.016
days+0.015
 t+0.014
 stuffed+0.014
 Mechan+0.013
Neg logit contributions
aw-0.025
Le-0.023
imes-0.023
 Remy-0.023
isi-0.023
Token Jane
Token ID12091
Feature activation-1.49e-02

Pos logit contributions
aw+0.006
Le+0.006
 Remy+0.006
isi+0.006
imes+0.006
Neg logit contributions
bell-0.005
days-0.005
 t-0.004
 stuffed-0.004
 Mechan-0.004
Token celebrated
Token ID13943
Feature activation-2.82e-02

Pos logit contributions
 Mechan+0.024
days+0.024
bell+0.023
 py+0.023
 stuffed+0.022
Neg logit contributions
aw-0.028
Le-0.024
isi-0.024
imes-0.023
 Sasha-0.023
Token both
Token ID1111
Feature activation+5.83e-02

Pos logit contributions
bell+0.051
days+0.046
 Mechan+0.046
 t+0.043
 stuffed+0.043
Neg logit contributions
aw-0.054
 Remy-0.049
imes-0.047
Le-0.047
 Sasha-0.047
Token their
Token ID511
Feature activation+7.56e-03

Pos logit contributions
aw+0.092
 Sasha+0.078
imes+0.077
 Remy+0.076
una+0.076
Neg logit contributions
bell-0.113
 Mechan-0.110
days-0.106
 t-0.104
 py-0.104
Token birth
Token ID4082
Feature activation-8.20e-02

Pos logit contributions
aw+0.014
imes+0.012
una+0.012
Le+0.012
 Remy+0.012
Neg logit contributions
bell-0.012
 Mechan-0.012
days-0.011
 spoiler-0.011
 t-0.010
Tokendays
Token ID12545
Feature activation-1.43e-01

Pos logit contributions
 py+0.059
 spoiler+0.054
 stuffed+0.054
 t+0.053
 prope+0.052
Neg logit contributions
aw-0.208
imes-0.195
arling-0.190
old-0.189
isi-0.188
Token together
Token ID1978
Feature activation-1.39e-02

Pos logit contributions
 Mechan+0.275
bell+0.268
 py+0.263
 stuffed+0.262
days+0.255
Neg logit contributions
aw-0.243
imes-0.176
isi-0.171
arling-0.171
 Sasha-0.166
Token.
Token ID13
Feature activation-2.82e-03

Pos logit contributions
bell+0.025
 Mechan+0.023
days+0.023
 t+0.022
 stuffed+0.021
Neg logit contributions
aw-0.026
 Remy-0.022
imes-0.022
Le-0.022
 Sasha-0.022
Token They
Token ID1119
Feature activation+6.43e-03

Pos logit contributions
bell+0.005
days+0.004
 t+0.004
 stuffed+0.004
 Mechan+0.004
Neg logit contributions
aw-0.006
Le-0.005
 Remy-0.005
imes-0.005
isi-0.005
Token played
Token ID2826
Feature activation-4.28e-02

Pos logit contributions
aw+0.011
isi+0.010
 Remy+0.010
Le+0.010
imes+0.010
Neg logit contributions
bell-0.011
 Mechan-0.011
days-0.011
 py-0.010
 spoiler-0.009
Token games
Token ID1830
Feature activation+9.32e-03

Pos logit contributions
bell+0.092
 Mechan+0.083
days+0.079
bul+0.074
 spoiler+0.072
Neg logit contributions
aw-0.075
 Remy-0.061
una-0.061
Le-0.059
imes-0.056
Token so
Token ID523
Feature activation-2.06e-02

Pos logit contributions
bell+0.034
 t+0.034
 unp+0.032
 stuffed+0.031
days+0.031
Neg logit contributions
aw-0.038
Le-0.036
isi-0.035
imes-0.035
emy-0.034
Token special
Token ID2041
Feature activation+7.36e-04

Pos logit contributions
bell+0.036
days+0.035
 t+0.033
 stuffed+0.032
 Mechan+0.031
Neg logit contributions
aw-0.039
Le-0.036
 Remy-0.036
imes-0.035
isi-0.035
Token about
Token ID546
Feature activation-5.11e-02

Pos logit contributions
aw+0.001
 Remy+0.001
imes+0.001
isi+0.001
una+0.001
Neg logit contributions
bell-0.001
days-0.001
 t-0.001
 stuffed-0.001
 Mechan-0.001
Token Wed
Token ID3300
Feature activation-4.99e-02

Pos logit contributions
bell+0.093
days+0.092
 t+0.081
 Mechan+0.081
 stuffed+0.080
Neg logit contributions
aw-0.093
 Remy-0.088
Le-0.084
una-0.083
imes-0.083
Tokennes
Token ID2516
Feature activation-1.30e-01

Pos logit contributions
bell+0.062
 t+0.061
 stuffed+0.059
days+0.056
 py+0.054
Neg logit contributions
aw-0.116
Le-0.110
imes-0.109
isi-0.108
una-0.105
Tokendays
Token ID12545
Feature activation-1.43e-01

Pos logit contributions
 t+0.193
bell+0.192
 stuffed+0.191
 Mechan+0.190
 py+0.179
Neg logit contributions
aw-0.248
imes-0.244
isi-0.235
una-0.235
iles-0.235
Token?"
Token ID1701
Feature activation-3.24e-02

Pos logit contributions
 stuffed+0.290
 Mechan+0.277
 t+0.277
 py+0.275
 prope+0.274
Neg logit contributions
aw-0.203
imes-0.167
iles-0.164
isi-0.163
una-0.157
Token
Token ID198
Feature activation-1.21e-03

Pos logit contributions
bell+0.064
days+0.062
 stuffed+0.059
 t+0.059
 unp+0.057
Neg logit contributions
aw-0.054
Le-0.049
 Remy-0.049
isi-0.047
imes-0.046
Token
Token ID198
Feature activation+1.94e-03

Pos logit contributions
bell+0.002
days+0.002
 t+0.002
 stuffed+0.002
 unp+0.002
Neg logit contributions
aw-0.002
imes-0.002
Le-0.002
isi-0.002
 Remy-0.002
TokenMax
Token ID11518
Feature activation-5.94e-04

Pos logit contributions
aw+0.003
Le+0.003
imes+0.003
 Remy+0.003
isi+0.003
Neg logit contributions
bell-0.004
days-0.004
 t-0.004
 stuffed-0.003
 unp-0.003
Token laughed
Token ID13818
Feature activation+1.20e-02

Pos logit contributions
days+0.001
bell+0.001
 Mechan+0.001
 stuffed+0.001
 py+0.001
Neg logit contributions
aw-0.001
Le-0.001
 Remy-0.001
isi-0.001
una-0.001
Token the
Token ID262
Feature activation+8.57e-03

Pos logit contributions
bell+0.047
days+0.045
 t+0.043
 stuffed+0.042
 Mechan+0.041
Neg logit contributions
aw-0.053
Le-0.049
 Remy-0.048
imes-0.048
isi-0.047
Token village
Token ID7404
Feature activation-3.20e-02

Pos logit contributions
aw+0.015
Le+0.014
 Remy+0.013
imes+0.013
isi+0.013
Neg logit contributions
bell-0.016
days-0.015
 t-0.015
 stuffed-0.015
 unp-0.014
Token back
Token ID736
Feature activation+1.69e-02

Pos logit contributions
bell+0.056
 Mechan+0.054
 stuffed+0.051
 t+0.051
days+0.051
Neg logit contributions
aw-0.058
imes-0.049
 Remy-0.048
 Sasha-0.048
crow-0.047
Token to
Token ID284
Feature activation-2.67e-02

Pos logit contributions
aw+0.030
 Remy+0.027
imes+0.026
Le+0.026
 Sasha+0.026
Neg logit contributions
bell-0.031
days-0.029
 Mechan-0.029
 t-0.028
 stuffed-0.028
Token its
Token ID663
Feature activation-1.07e-02

Pos logit contributions
bell+0.055
days+0.051
 Mechan+0.048
 stuffed+0.047
 t+0.047
Neg logit contributions
aw-0.041
 Remy-0.040
una-0.036
Le-0.036
 Sasha-0.036
Token former
Token ID1966
Feature activation-1.42e-01

Pos logit contributions
bell+0.019
days+0.018
 t+0.017
 stuffed+0.017
 unp+0.016
Neg logit contributions
aw-0.020
Le-0.018
 Remy-0.018
imes-0.018
isi-0.018
Token glory
Token ID13476
Feature activation-4.52e-03

Pos logit contributions
bell+0.278
days+0.274
 Mechan+0.262
 t+0.260
 stuffed+0.253
Neg logit contributions
aw-0.232
emy-0.200
 Remy-0.198
una-0.195
iles-0.195
Token!"
Token ID2474
Feature activation-9.87e-03

Pos logit contributions
bell+0.008
 Mechan+0.008
 stuffed+0.007
 t+0.007
days+0.007
Neg logit contributions
aw-0.008
imes-0.007
una-0.007
 Sasha-0.007
 Remy-0.007
Token
Token ID220
Feature activation-1.03e-02

Pos logit contributions
bell+0.017
days+0.015
 t+0.015
 stuffed+0.015
 Mechan+0.014
Neg logit contributions
aw-0.021
 Remy-0.019
Le-0.019
imes-0.018
isi-0.018
Token
Token ID198
Feature activation+1.80e-03

Pos logit contributions
bell+0.017
days+0.016
 t+0.015
 unp+0.015
 stuffed+0.015
Neg logit contributions
aw-0.020
Le-0.019
isi-0.019
imes-0.018
 Remy-0.018
Token
Token ID198
Feature activation+2.65e-03

Pos logit contributions
aw+0.003
imes+0.003
Le+0.003
 Remy+0.003
isi+0.003
Neg logit contributions
bell-0.003
days-0.003
 t-0.003
 stuffed-0.003
 unp-0.003
Token pond
Token ID16723
Feature activation+2.91e-02

Pos logit contributions
bell+0.030
days+0.029
 Mechan+0.026
 unp+0.026
 t+0.025
Neg logit contributions
aw-0.030
 Remy-0.027
crow-0.026
 Sasha-0.026
Le-0.026
Token and
Token ID290
Feature activation-1.23e-02

Pos logit contributions
aw+0.061
Le+0.055
 Remy+0.055
imes+0.055
isi+0.054
Neg logit contributions
bell-0.045
days-0.043
 t-0.041
 stuffed-0.040
 Mechan-0.039
Token it
Token ID340
Feature activation-1.46e-02

Pos logit contributions
bell+0.021
days+0.021
 Mechan+0.019
 t+0.019
 stuffed+0.018
Neg logit contributions
aw-0.023
 Remy-0.021
Le-0.021
 Sasha-0.020
imes-0.020
Token was
Token ID373
Feature activation-1.06e-02

Pos logit contributions
days+0.023
bell+0.023
 Mechan+0.022
 t+0.020
 py+0.020
Neg logit contributions
aw-0.029
 Remy-0.026
Le-0.026
 Sasha-0.024
imes-0.024
Token the
Token ID262
Feature activation-2.51e-02

Pos logit contributions
bell+0.018
days+0.017
 Mechan+0.016
 t+0.016
 stuffed+0.015
Neg logit contributions
aw-0.021
 Remy-0.019
Le-0.019
imes-0.019
 Sasha-0.018
Token tid
Token ID29770
Feature activation-1.41e-01

Pos logit contributions
bell+0.040
 t+0.038
days+0.038
 stuffed+0.037
 unp+0.035
Neg logit contributions
aw-0.051
imes-0.047
Le-0.047
isi-0.046
 Remy-0.046
Tokeniest
Token ID6386
Feature activation-4.71e-02

Pos logit contributions
 t+0.309
bell+0.307
 stuffed+0.303
 Mechan+0.298
days+0.296
Neg logit contributions
aw-0.197
imes-0.181
crow-0.171
iles-0.169
una-0.167
Token water
Token ID1660
Feature activation+1.25e-02

Pos logit contributions
bell+0.094
days+0.090
 t+0.086
 stuffed+0.084
 Mechan+0.084
Neg logit contributions
aw-0.079
Le-0.070
 Remy-0.069
imes-0.068
isi-0.067
Token she
Token ID673
Feature activation-6.89e-02

Pos logit contributions
aw+0.024
imes+0.021
Le+0.021
 Remy+0.021
isi+0.021
Neg logit contributions
bell-0.022
days-0.021
 t-0.020
 stuffed-0.019
 Mechan-0.019
Token had
Token ID550
Feature activation-3.21e-02

Pos logit contributions
bell+0.108
 Mechan+0.103
days+0.103
 t+0.096
 stuffed+0.093
Neg logit contributions
aw-0.138
Le-0.126
 Remy-0.125
imes-0.125
isi-0.122
Token ever
Token ID1683
Feature activation-2.32e-02

Pos logit contributions
bell+0.053
days+0.049
 t+0.047
 Mechan+0.047
 stuffed+0.046
Neg logit contributions
aw-0.065
Le-0.059
imes-0.058
isi-0.057
una-0.057
Token She
Token ID1375
Feature activation-1.12e-02

Pos logit contributions
bell+0.007
days+0.006
 t+0.006
 stuffed+0.006
 unp+0.006
Neg logit contributions
aw-0.007
Le-0.006
 Remy-0.006
imes-0.006
isi-0.006
Token thought
Token ID1807
Feature activation-1.32e-02

Pos logit contributions
days+0.020
bell+0.020
 Mechan+0.019
 spoiler+0.017
 py+0.017
Neg logit contributions
aw-0.020
 Remy-0.018
Le-0.018
una-0.017
 Sasha-0.017
Token it
Token ID340
Feature activation-6.92e-03

Pos logit contributions
days+0.028
bell+0.028
 Mechan+0.027
 t+0.025
 spoiler+0.025
Neg logit contributions
aw-0.019
imes-0.018
una-0.018
 Remy-0.018
 Sasha-0.017
Token was
Token ID373
Feature activation-1.28e-02

Pos logit contributions
bell+0.013
days+0.012
 Mechan+0.012
 spoiler+0.011
 py+0.011
Neg logit contributions
aw-0.011
Le-0.010
 Remy-0.010
una-0.010
 Patty-0.010
Token the
Token ID262
Feature activation-2.33e-02

Pos logit contributions
bell+0.023
days+0.022
 Mechan+0.021
 t+0.020
 stuffed+0.020
Neg logit contributions
aw-0.023
 Remy-0.021
Le-0.021
imes-0.021
isi-0.021
Token tid
Token ID29770
Feature activation-1.41e-01

Pos logit contributions
bell+0.048
days+0.046
 t+0.044
 stuffed+0.043
 unp+0.042
Neg logit contributions
aw-0.037
Le-0.034
 Remy-0.033
imes-0.033
isi-0.033
Tokeniest
Token ID6386
Feature activation-4.29e-02

Pos logit contributions
 t+0.302
bell+0.300
 py+0.295
 stuffed+0.295
 Mechan+0.288
Neg logit contributions
aw-0.196
imes-0.193
crow-0.178
arling-0.176
una-0.174
Token thing
Token ID1517
Feature activation+3.95e-02

Pos logit contributions
bell+0.080
days+0.077
 Mechan+0.073
 t+0.070
 unp+0.069
Neg logit contributions
aw-0.075
 Remy-0.068
isi-0.067
imes-0.066
 Sasha-0.065
Token ever
Token ID1683
Feature activation-3.91e-02

Pos logit contributions
aw+0.070
Le+0.064
 Remy+0.063
imes+0.063
isi+0.062
Neg logit contributions
bell-0.073
days-0.069
 t-0.067
 stuffed-0.065
 Mechan-0.065
Token and
Token ID290
Feature activation-4.09e-03

Pos logit contributions
bell+0.070
days+0.066
 Mechan+0.064
 t+0.063
 stuffed+0.062
Neg logit contributions
aw-0.075
isi-0.064
 Remy-0.064
imes-0.064
Le-0.064
Token knew
Token ID2993
Feature activation+1.29e-02

Pos logit contributions
bell+0.008
days+0.007
 Mechan+0.007
 t+0.007
 stuffed+0.007
Neg logit contributions
aw-0.007
 Remy-0.006
imes-0.006
Le-0.006
 Sasha-0.006
Token you
Token ID345
Feature activation-2.55e-03

Pos logit contributions
bell+0.002
days+0.002
 t+0.002
 unp+0.002
 stuffed+0.002
Neg logit contributions
aw-0.002
isi-0.002
Le-0.002
una-0.002
imes-0.001
Token?
Token ID30
Feature activation-3.02e-02

Pos logit contributions
bell+0.005
days+0.005
 stuffed+0.004
 Mechan+0.004
 t+0.004
Neg logit contributions
aw-0.004
 Remy-0.004
imes-0.004
una-0.004
iles-0.004
Token This
Token ID770
Feature activation-2.99e-02

Pos logit contributions
bell+0.055
days+0.053
 stuffed+0.053
 t+0.052
 lit+0.049
Neg logit contributions
aw-0.050
 Remy-0.048
imes-0.048
Le-0.046
crow-0.044
Token is
Token ID318
Feature activation-1.64e-02

Pos logit contributions
bell+0.060
days+0.059
 stuffed+0.053
 unp+0.052
 Mechan+0.051
Neg logit contributions
aw-0.051
una-0.044
 Remy-0.043
crow-0.042
Le-0.042
Token my
Token ID616
Feature activation-3.29e-02

Pos logit contributions
bell+0.025
 t+0.023
days+0.022
 stuffed+0.022
 unp+0.022
Neg logit contributions
aw-0.035
Le-0.032
imes-0.032
isi-0.032
arling-0.031
Token wardrobe
Token ID35593
Feature activation-1.41e-01

Pos logit contributions
bell+0.057
days+0.055
 Mechan+0.050
 unp+0.048
 stuffed+0.046
Neg logit contributions
aw-0.063
 Remy-0.057
una-0.056
Le-0.056
isi-0.055
Token.
Token ID13
Feature activation-1.96e-02

Pos logit contributions
 Mechan+0.277
days+0.270
 stuffed+0.269
 py+0.266
 Will+0.259
Neg logit contributions
aw-0.208
 wrong-0.151
imes-0.147
una-0.144
ile-0.143
Token Go
Token ID1514
Feature activation-5.73e-03

Pos logit contributions
bell+0.034
days+0.033
 stuffed+0.032
 t+0.032
 unp+0.030
Neg logit contributions
aw-0.036
 Remy-0.034
imes-0.033
Le-0.033
una-0.033
Token away
Token ID1497
Feature activation+1.33e-02

Pos logit contributions
bell+0.012
 stuffed+0.012
 Mechan+0.012
lights+0.012
days+0.011
Neg logit contributions
aw-0.007
crow-0.006
 Remy-0.006
arling-0.006
Le-0.006
Token!"
Token ID2474
Feature activation-4.02e-03

Pos logit contributions
aw+0.023
 Remy+0.021
una+0.020
 Sasha+0.020
Le+0.020
Neg logit contributions
bell-0.025
days-0.023
 Mechan-0.023
 stuffed-0.022
 lit-0.021
Token
Token ID198
Feature activation+8.97e-03

Pos logit contributions
bell+0.008
days+0.008
 t+0.007
 stuffed+0.007
 Mechan+0.007
Neg logit contributions
aw-0.007
 Remy-0.006
Le-0.006
imes-0.006
isi-0.006
Token.
Token ID13
Feature activation+1.44e-03

Pos logit contributions
aw+0.056
Le+0.051
imes+0.050
isi+0.049
 Remy+0.049
Neg logit contributions
bell-0.057
days-0.054
 t-0.053
 stuffed-0.051
 unp-0.050
Token She
Token ID1375
Feature activation-7.84e-03

Pos logit contributions
aw+0.003
Le+0.003
imes+0.003
isi+0.003
 Remy+0.003
Neg logit contributions
bell-0.002
days-0.002
 t-0.002
 stuffed-0.002
 unp-0.002
Token learned
Token ID4499
Feature activation+4.50e-03

Pos logit contributions
days+0.015
bell+0.015
 Mechan+0.014
 py+0.013
 stuffed+0.013
Neg logit contributions
aw-0.014
Le-0.012
 Remy-0.012
una-0.012
isi-0.012
Token that
Token ID326
Feature activation+8.53e-03

Pos logit contributions
aw+0.008
Le+0.008
imes+0.007
iles+0.007
opard+0.007
Neg logit contributions
bell-0.008
 t-0.008
 Gr-0.008
 stuffed-0.008
 unp-0.008
Token birth
Token ID4082
Feature activation-7.67e-02

Pos logit contributions
aw+0.016
Le+0.015
 Remy+0.015
imes+0.015
isi+0.014
Neg logit contributions
bell-0.015
days-0.014
 t-0.013
 stuffed-0.013
 Mechan-0.013
Tokendays
Token ID12545
Feature activation-1.40e-01

Pos logit contributions
bell+0.098
 t+0.096
 stuffed+0.095
 py+0.093
 Mechan+0.092
Neg logit contributions
aw-0.151
imes-0.146
iles-0.144
arling-0.137
isi-0.136
Token are
Token ID389
Feature activation-6.93e-03

Pos logit contributions
bell+0.265
 Mechan+0.252
days+0.250
 stuffed+0.247
 t+0.247
Neg logit contributions
aw-0.230
imes-0.193
iles-0.188
crow-0.187
isi-0.183
Token not
Token ID407
Feature activation-1.60e-02

Pos logit contributions
bell+0.010
 t+0.010
days+0.010
 stuffed+0.010
 unp+0.010
Neg logit contributions
aw-0.015
Le-0.014
imes-0.013
arling-0.013
isi-0.013
Token about
Token ID546
Feature activation-4.86e-02

Pos logit contributions
bell+0.032
days+0.031
 t+0.028
 Mechan+0.028
 stuffed+0.027
Neg logit contributions
aw-0.026
 Remy-0.024
isi-0.023
Le-0.023
imes-0.023
Token cakes
Token ID30849
Feature activation+3.40e-03

Pos logit contributions
bell+0.093
days+0.088
 t+0.082
 stuffed+0.081
 Mechan+0.080
Neg logit contributions
aw-0.083
 Remy-0.077
Le-0.076
imes-0.075
una-0.074
Token and
Token ID290
Feature activation-1.84e-02

Pos logit contributions
aw+0.007
imes+0.006
 Remy+0.006
una+0.006
isi+0.006
Neg logit contributions
bell-0.006
days-0.006
 Mechan-0.005
 stuffed-0.005
 t-0.005
Token!
Token ID0
Feature activation+5.32e-03

Pos logit contributions
 Mechan+0.007
days+0.007
bell+0.007
 stuffed+0.007
 py+0.006
Neg logit contributions
aw-0.006
 Remy-0.005
 Sasha-0.005
imes-0.005
arling-0.005
Token
Token ID198
Feature activation+2.91e-03

Pos logit contributions
aw+0.010
Le+0.010
 Remy+0.010
imes+0.010
isi+0.009
Neg logit contributions
bell-0.009
days-0.009
 t-0.008
 stuffed-0.008
 unp-0.008
Token
Token ID198
Feature activation+5.95e-03

Pos logit contributions
aw+0.006
imes+0.006
iles+0.006
isi+0.006
 Remy+0.006
Neg logit contributions
bell-0.004
days-0.004
 t-0.004
 unp-0.004
 Gr-0.003
TokenThe
Token ID464
Feature activation+8.81e-04

Pos logit contributions
aw+0.011
imes+0.010
iles+0.010
isi+0.010
 Remy+0.010
Neg logit contributions
bell-0.011
days-0.011
 t-0.010
 unp-0.010
 stuffed-0.009
Token town
Token ID3240
Feature activation-5.70e-02

Pos logit contributions
aw+0.002
Le+0.002
 Remy+0.001
imes+0.001
isi+0.001
Neg logit contributions
bell-0.002
days-0.001
 t-0.001
 stuffed-0.001
 unp-0.001
Tokenspe
Token ID4125
Feature activation-1.39e-01

Pos logit contributions
bell+0.086
days+0.085
 t+0.080
 Mechan+0.078
 py+0.077
Neg logit contributions
aw-0.121
Le-0.106
crow-0.103
 Remy-0.102
imes-0.102
Tokenople
Token ID643
Feature activation-3.33e-02

Pos logit contributions
bell+0.234
days+0.223
 t+0.215
 stuffed+0.209
 unp+0.202
Neg logit contributions
aw-0.276
Le-0.251
imes-0.246
 Remy-0.245
isi-0.244
Token were
Token ID547
Feature activation-1.56e-02

Pos logit contributions
bell+0.055
days+0.052
 Mechan+0.050
 py+0.047
 t+0.047
Neg logit contributions
aw-0.068
Le-0.059
 Remy-0.057
imes-0.056
crow-0.054
Token sad
Token ID6507
Feature activation+1.08e-02

Pos logit contributions
bell+0.024
days+0.023
 t+0.023
 stuffed+0.022
 unp+0.022
Neg logit contributions
aw-0.032
Le-0.030
imes-0.030
isi-0.030
 Remy-0.030
Token and
Token ID290
Feature activation-2.50e-03

Pos logit contributions
aw+0.022
 Remy+0.020
Le+0.019
imes+0.019
arling+0.019
Neg logit contributions
bell-0.018
days-0.017
 Mechan-0.016
 t-0.016
 stuffed-0.015
Token scared
Token ID12008
Feature activation+3.64e-03

Pos logit contributions
bell+0.004
days+0.004
 t+0.004
 stuffed+0.004
 Mechan+0.004
Neg logit contributions
aw-0.005
 Remy-0.004
Le-0.004
imes-0.004
isi-0.004
Token with
Token ID351
Feature activation+2.71e-03

Pos logit contributions
bell+0.030
 Mechan+0.027
days+0.027
 t+0.024
 Gr+0.023
Neg logit contributions
aw-0.027
 Remy-0.023
Le-0.022
crow-0.021
una-0.021
Token the
Token ID262
Feature activation+1.95e-02

Pos logit contributions
aw+0.005
 Remy+0.004
Le+0.004
imes+0.004
 Sasha+0.004
Neg logit contributions
bell-0.005
days-0.005
 Mechan-0.005
 t-0.005
 unp-0.004
Token things
Token ID1243
Feature activation+9.15e-03

Pos logit contributions
aw+0.033
Le+0.030
 Remy+0.029
imes+0.029
isi+0.029
Neg logit contributions
bell-0.038
days-0.037
 t-0.034
 unp-0.033
 stuffed-0.033
Token the
Token ID262
Feature activation-8.46e-03

Pos logit contributions
aw+0.016
 Remy+0.014
imes+0.014
Le+0.014
isi+0.013
Neg logit contributions
bell-0.017
days-0.017
 Mechan-0.016
 t-0.016
 stuffed-0.016
Token driver
Token ID4639
Feature activation-3.50e-02

Pos logit contributions
bell+0.017
days+0.016
 t+0.015
 stuffed+0.015
 unp+0.015
Neg logit contributions
aw-0.014
Le-0.013
 Remy-0.013
imes-0.012
isi-0.012
Token unp
Token ID8593
Feature activation-1.39e-01

Pos logit contributions
bell+0.056
days+0.054
 t+0.051
 Mechan+0.051
 stuffed+0.050
Neg logit contributions
aw-0.072
Le-0.062
 Remy-0.062
imes-0.061
isi-0.060
Tokenacked
Token ID6021
Feature activation+2.46e-02

Pos logit contributions
bell+0.301
days+0.294
 t+0.292
 stuffed+0.287
 unp+0.273
Neg logit contributions
aw-0.206
Le-0.173
imes-0.173
isi-0.171
 Remy-0.169
Token.
Token ID13
Feature activation-3.99e-03

Pos logit contributions
aw+0.047
imes+0.039
Le+0.038
 Remy+0.038
una+0.037
Neg logit contributions
bell-0.044
days-0.044
 Mechan-0.043
 t-0.039
 stuffed-0.038
Token
Token ID220
Feature activation-1.95e-02

Pos logit contributions
bell+0.007
days+0.006
 t+0.006
 stuffed+0.006
 Mechan+0.006
Neg logit contributions
aw-0.008
 Remy-0.007
Le-0.007
imes-0.007
isi-0.007
Token
Token ID198
Feature activation-2.53e-03

Pos logit contributions
bell+0.032
days+0.031
 t+0.029
 unp+0.028
 stuffed+0.027
Neg logit contributions
aw-0.039
Le-0.036
isi-0.035
imes-0.035
 Remy-0.035
Token
Token ID198
Feature activation-1.43e-04

Pos logit contributions
bell+0.004
days+0.004
 t+0.004
 unp+0.004
 stuffed+0.004
Neg logit contributions
aw-0.005
imes-0.005
isi-0.005
Le-0.005
 Remy-0.005
Token back
Token ID736
Feature activation+4.11e-02

Pos logit contributions
bell+0.027
days+0.026
 t+0.024
 stuffed+0.024
 Mechan+0.023
Neg logit contributions
aw-0.028
Le-0.025
 Remy-0.025
imes-0.025
isi-0.025
Token the
Token ID262
Feature activation+1.05e-02

Pos logit contributions
aw+0.077
Le+0.070
 Remy+0.069
imes+0.069
isi+0.067
Neg logit contributions
bell-0.074
days-0.070
 t-0.067
 stuffed-0.065
 Mechan-0.064
Token village
Token ID7404
Feature activation-3.21e-02

Pos logit contributions
aw+0.019
Le+0.017
imes+0.017
 Remy+0.016
isi+0.016
Neg logit contributions
bell-0.020
days-0.019
 t-0.018
 stuffed-0.018
 Mechan-0.017
Token to
Token ID284
Feature activation-1.56e-02

Pos logit contributions
bell+0.059
 Mechan+0.057
days+0.054
 t+0.052
 stuffed+0.052
Neg logit contributions
aw-0.056
imes-0.047
 Sasha-0.047
 Remy-0.046
Le-0.045
Token its
Token ID663
Feature activation-7.98e-03

Pos logit contributions
bell+0.032
days+0.029
 Mechan+0.027
 t+0.027
 stuffed+0.027
Neg logit contributions
 Remy-0.024
aw-0.024
 Sasha-0.022
Le-0.022
una-0.021
Token former
Token ID1966
Feature activation-1.38e-01

Pos logit contributions
bell+0.014
days+0.014
 t+0.013
 stuffed+0.013
 unp+0.012
Neg logit contributions
aw-0.015
Le-0.014
imes-0.013
 Remy-0.013
isi-0.013
Token state
Token ID1181
Feature activation-7.25e-02

Pos logit contributions
bell+0.278
days+0.276
 Mechan+0.267
 t+0.263
 stuffed+0.255
Neg logit contributions
aw-0.215
emy-0.184
 Remy-0.180
iles-0.179
una-0.178
Token.
Token ID13
Feature activation-5.25e-03

Pos logit contributions
bell+0.138
 Mechan+0.135
days+0.132
 t+0.128
 stuffed+0.126
Neg logit contributions
aw-0.129
imes-0.101
una-0.100
 Sasha-0.099
crow-0.099
Token With
Token ID2080
Feature activation+3.97e-02

Pos logit contributions
bell+0.010
days+0.009
 t+0.009
 stuffed+0.009
 unp+0.008
Neg logit contributions
aw-0.010
Le-0.009
 Remy-0.009
imes-0.009
isi-0.009
Token the
Token ID262
Feature activation+2.54e-02

Pos logit contributions
aw+0.076
Le+0.070
 Remy+0.070
imes+0.069
isi+0.068
Neg logit contributions
bell-0.069
days-0.066
 t-0.062
 stuffed-0.060
 Mechan-0.059
Token help
Token ID1037
Feature activation-3.69e-02

Pos logit contributions
aw+0.049
Le+0.045
 Remy+0.044
imes+0.044
isi+0.044
Neg logit contributions
bell-0.044
days-0.042
 t-0.041
 stuffed-0.040
 unp-0.039
Token it
Token ID340
Feature activation+1.34e-02

Pos logit contributions
bell+0.035
days+0.033
 t+0.033
 stuffed+0.032
 unp+0.031
Neg logit contributions
aw-0.048
Le-0.044
isi-0.044
imes-0.044
 Remy-0.043
Token on
Token ID319
Feature activation-1.02e-02

Pos logit contributions
aw+0.021
Le+0.019
 Remy+0.019
imes+0.018
arling+0.018
Neg logit contributions
bell-0.027
days-0.026
 Mechan-0.025
 stuffed-0.024
 t-0.024
Token a
Token ID257
Feature activation-1.38e-02

Pos logit contributions
days+0.020
bell+0.019
 Mechan+0.017
 stuffed+0.017
 t+0.017
Neg logit contributions
aw-0.018
 Remy-0.017
Le-0.017
una-0.016
 Sasha-0.015
Token nearby
Token ID6716
Feature activation+3.08e-03

Pos logit contributions
bell+0.026
days+0.025
 t+0.024
 stuffed+0.023
 unp+0.023
Neg logit contributions
aw-0.024
Le-0.022
 Remy-0.022
imes-0.022
isi-0.021
Token tree
Token ID5509
Feature activation+2.91e-02

Pos logit contributions
aw+0.005
Le+0.004
imes+0.004
isi+0.004
 Remy+0.004
Neg logit contributions
bell-0.006
days-0.006
 t-0.006
 stuffed-0.006
 unp-0.006
Token branch
Token ID8478
Feature activation+6.60e-02

Pos logit contributions
aw+0.056
Le+0.051
 Remy+0.050
imes+0.050
isi+0.048
Neg logit contributions
bell-0.050
days-0.047
 t-0.045
 Mechan-0.044
 stuffed-0.044
Token.
Token ID13
Feature activation-8.87e-05

Pos logit contributions
aw+0.134
Le+0.123
 Remy+0.121
imes+0.121
isi+0.120
Neg logit contributions
bell-0.106
days-0.102
 t-0.097
 stuffed-0.094
 unp-0.091
Token The
Token ID383
Feature activation-4.80e-03

Pos logit contributions
bell+0.000
days+0.000
 t+0.000
 stuffed+0.000
 Mechan+0.000
Neg logit contributions
aw-0.000
 Remy-0.000
Le-0.000
imes-0.000
 Sasha-0.000
Token squirrel
Token ID33039
Feature activation+2.27e-02

Pos logit contributions
 t+0.010
 stuffed+0.009
bell+0.009
 Gr+0.008
days+0.008
Neg logit contributions
aw-0.009
imes-0.008
Le-0.008
isi-0.008
arling-0.007
Token happily
Token ID18177
Feature activation+1.66e-02

Pos logit contributions
aw+0.046
Le+0.042
 Remy+0.041
imes+0.040
isi+0.039
Neg logit contributions
bell-0.037
days-0.035
 Mechan-0.033
 t-0.033
 py-0.032
Token chat
Token ID8537
Feature activation-2.95e-02

Pos logit contributions
aw+0.030
 Remy+0.027
Le+0.027
imes+0.026
isi+0.026
Neg logit contributions
bell-0.031
days-0.030
 Mechan-0.027
 t-0.027
 py-0.026
Token lake
Token ID13546
Feature activation+3.53e-03

Pos logit contributions
imes+0.034
isi+0.034
aw+0.033
arling+0.033
 Sasha+0.033
Neg logit contributions
 t-0.025
bell-0.024
 stuffed-0.023
 unp-0.022
 Mechan-0.022
Token and
Token ID290
Feature activation+1.93e-03

Pos logit contributions
aw+0.007
 Remy+0.006
Le+0.006
iles+0.006
una+0.006
Neg logit contributions
bell-0.006
 Mechan-0.006
days-0.006
 t-0.006
 stuffed-0.006
Token catch
Token ID4929
Feature activation+6.04e-02

Pos logit contributions
aw+0.004
 Remy+0.004
Le+0.004
imes+0.004
isi+0.004
Neg logit contributions
bell-0.003
days-0.003
 t-0.003
 Mechan-0.003
 stuffed-0.003
Token lots
Token ID6041
Feature activation-6.42e-03

Pos logit contributions
isi+0.123
live+0.118
arling+0.111
Le+0.110
 Sasha+0.109
Neg logit contributions
 t-0.095
 stuffed-0.091
 unp-0.085
 decor-0.083
bell-0.080
Token of
Token ID286
Feature activation-1.11e-02

Pos logit contributions
bell+0.009
 t+0.009
days+0.008
 stuffed+0.008
 unp+0.008
Neg logit contributions
Le-0.013
isi-0.013
aw-0.013
 Sasha-0.012
 Remy-0.012
Token fish
Token ID5916
Feature activation+7.87e-02

Pos logit contributions
 t+0.019
 stuffed+0.019
 unp+0.018
 py+0.018
 decor+0.018
Neg logit contributions
isi-0.019
Le-0.019
live-0.018
arling-0.018
imes-0.018
Token.
Token ID13
Feature activation-3.24e-03

Pos logit contributions
isi+0.192
aw+0.182
 Sasha+0.179
Le+0.177
live+0.176
Neg logit contributions
days-0.089
 t-0.088
 stuffed-0.081
 unp-0.079
 decor-0.074
Token Sometimes
Token ID8975
Feature activation-3.35e-02

Pos logit contributions
bell+0.006
days+0.006
 t+0.006
 stuffed+0.006
 Mechan+0.005
Neg logit contributions
aw-0.006
 Remy-0.005
Le-0.005
imes-0.005
isi-0.005
Token the
Token ID262
Feature activation+3.96e-03

Pos logit contributions
bell+0.053
days+0.051
 t+0.048
 stuffed+0.047
 unp+0.045
Neg logit contributions
aw-0.069
Le-0.064
 Remy-0.063
imes-0.063
isi-0.062
Token fish
Token ID5916
Feature activation+3.03e-02

Pos logit contributions
aw+0.006
Le+0.006
imes+0.006
isi+0.006
 Remy+0.006
Neg logit contributions
bell-0.008
days-0.008
 t-0.008
 stuffed-0.007
 unp-0.007
Token were
Token ID547
Feature activation-1.43e-02

Pos logit contributions
aw+0.067
Le+0.062
imes+0.061
isi+0.061
 Remy+0.061
Neg logit contributions
bell-0.043
days-0.041
 t-0.039
 stuffed-0.038
 unp-0.036
Token of
Token ID286
Feature activation-6.74e-03

Pos logit contributions
bell+0.006
days+0.006
 t+0.006
 stuffed+0.005
 unp+0.005
Neg logit contributions
aw-0.005
Le-0.005
 Remy-0.005
imes-0.005
isi-0.005
Token y
Token ID331
Feature activation+5.43e-02

Pos logit contributions
 t+0.012
 stuffed+0.012
bell+0.011
days+0.011
 unp+0.011
Neg logit contributions
aw-0.013
Le-0.012
isi-0.011
arling-0.011
imes-0.011
Tokenummy
Token ID13513
Feature activation+7.60e-02

Pos logit contributions
Le+0.108
aw+0.106
opard+0.101
 Remy+0.100
crow+0.099
Neg logit contributions
bell-0.081
days-0.077
 t-0.076
 unp-0.075
 stuffed-0.072
Token treats
Token ID18432
Feature activation+4.61e-02

Pos logit contributions
aw+0.123
Le+0.115
isi+0.110
 Remy+0.110
imes+0.108
Neg logit contributions
bell-0.147
 t-0.146
days-0.144
 stuffed-0.142
 unp-0.136
Token.
Token ID13
Feature activation-4.54e-03

Pos logit contributions
aw+0.094
Le+0.088
 Remy+0.086
imes+0.085
isi+0.085
Neg logit contributions
bell-0.073
days-0.069
 t-0.067
 stuffed-0.065
 unp-0.063
Token Strip
Token ID18508
Feature activation+6.42e-02

Pos logit contributions
bell+0.005
 t+0.005
 Gr+0.005
days+0.005
 stuffed+0.005
Neg logit contributions
aw-0.011
arling-0.010
imes-0.010
iles-0.010
isi-0.010
Token was
Token ID373
Feature activation-5.11e-03

Pos logit contributions
aw+0.118
Le+0.107
 Remy+0.105
imes+0.104
isi+0.103
Neg logit contributions
bell-0.118
days-0.112
 t-0.107
 stuffed-0.104
 unp-0.102
Token a
Token ID257
Feature activation-3.33e-02

Pos logit contributions
bell+0.009
days+0.008
 t+0.008
 stuffed+0.008
 Mechan+0.008
Neg logit contributions
aw-0.010
Le-0.009
 Remy-0.009
imes-0.009
isi-0.009
Token very
Token ID845
Feature activation-1.31e-02

Pos logit contributions
bell+0.066
days+0.064
lights+0.057
 unp+0.057
 Mechan+0.056
Neg logit contributions
aw-0.053
Le-0.050
 Remy-0.050
opard-0.048
emy-0.046
Token clever
Token ID14169
Feature activation+7.45e-03

Pos logit contributions
bell+0.023
days+0.023
 t+0.021
 Mechan+0.021
 stuffed+0.021
Neg logit contributions
aw-0.024
Le-0.022
 Remy-0.022
imes-0.022
isi-0.021
Token k
Token ID479
Feature activation+9.49e-03

Pos logit contributions
aw+0.012
 Remy+0.011
una+0.010
Le+0.010
isi+0.010
Neg logit contributions
bell-0.016
days-0.015
 unp-0.014
 Mechan-0.014
 lit-0.013
Token pretended
Token ID36766
Feature activation-5.27e-02

Pos logit contributions
aw+0.004
imes+0.003
 Remy+0.003
isi+0.003
Le+0.003
Neg logit contributions
 Mechan-0.004
bell-0.004
days-0.004
 py-0.004
lights-0.004
Token to
Token ID284
Feature activation-1.13e-02

Pos logit contributions
bell+0.094
days+0.090
 t+0.086
 stuffed+0.083
 Mechan+0.082
Neg logit contributions
aw-0.098
Le-0.089
 Remy-0.088
imes-0.088
isi-0.087
Token sip
Token ID31145
Feature activation+6.18e-02

Pos logit contributions
 Mechan+0.020
bell+0.019
days+0.019
bul+0.018
 unp+0.017
Neg logit contributions
una-0.017
aw-0.017
Le-0.017
 Remy-0.017
isi-0.017
Token and
Token ID290
Feature activation+1.58e-02

Pos logit contributions
aw+0.119
imes+0.107
 Remy+0.107
Le+0.105
una+0.104
Neg logit contributions
bell-0.109
days-0.105
 Mechan-0.098
 t-0.096
 stuffed-0.094
Token nib
Token ID33272
Feature activation+6.21e-02

Pos logit contributions
aw+0.029
 Remy+0.029
Le+0.028
 Sasha+0.027
imes+0.027
Neg logit contributions
bell-0.025
 Mechan-0.024
days-0.022
 py-0.020
 unp-0.019
Tokenble
Token ID903
Feature activation+8.85e-02

Pos logit contributions
aw+0.096
Le+0.086
imes+0.084
 Remy+0.084
isi+0.083
Neg logit contributions
bell-0.131
days-0.126
 t-0.122
 stuffed-0.119
 unp-0.117
Token and
Token ID290
Feature activation+2.19e-02

Pos logit contributions
aw+0.164
imes+0.146
 Remy+0.145
Le+0.144
una+0.141
Neg logit contributions
bell-0.162
days-0.158
 Mechan-0.147
 t-0.144
 stuffed-0.142
Token chat
Token ID8537
Feature activation-6.72e-03

Pos logit contributions
aw+0.040
 Remy+0.039
Le+0.039
imes+0.038
 Sasha+0.037
Neg logit contributions
bell-0.037
days-0.033
 Mechan-0.033
 stuffed-0.029
 suitcase-0.028
Token.
Token ID13
Feature activation+4.17e-03

Pos logit contributions
days+0.011
bell+0.011
 Mechan+0.011
 t+0.010
 py+0.010
Neg logit contributions
aw-0.013
una-0.011
Le-0.011
 Remy-0.011
isi-0.011
Token
Token ID198
Feature activation+5.01e-03

Pos logit contributions
aw+0.009
Le+0.008
isi+0.008
una+0.008
imes+0.008
Neg logit contributions
bell-0.006
days-0.006
 t-0.006
 stuffed-0.005
 unp-0.005
Token
Token ID198
Feature activation+7.47e-03

Pos logit contributions
aw+0.010
imes+0.009
isi+0.009
 Remy+0.009
Le+0.009
Neg logit contributions
bell-0.008
days-0.008
 t-0.007
 unp-0.007
 stuffed-0.007
TokenSit
Token ID46655
Feature activation+2.98e-03

Pos logit contributions
bell+0.005
days+0.005
 t+0.005
 stuffed+0.004
 unp+0.004
Neg logit contributions
aw-0.004
Le-0.003
isi-0.003
imes-0.003
 Remy-0.003
Token."
Token ID526
Feature activation-3.70e-02

Pos logit contributions
aw+0.005
 Remy+0.005
arling+0.005
 Sasha+0.004
Le+0.004
Neg logit contributions
bell-0.006
days-0.005
 stuffed-0.005
 Mechan-0.005
 t-0.005
Token The
Token ID383
Feature activation-1.36e-02

Pos logit contributions
bell+0.052
days+0.048
 t+0.046
 unp+0.045
 Gr+0.045
Neg logit contributions
aw-0.079
Le-0.074
una-0.073
isi-0.073
iles-0.072
Token children
Token ID1751
Feature activation-2.58e-02

Pos logit contributions
bell+0.029
days+0.028
 t+0.027
 stuffed+0.026
 unp+0.026
Neg logit contributions
aw-0.021
Le-0.019
 Remy-0.018
imes-0.018
isi-0.018
Token did
Token ID750
Feature activation+7.32e-03

Pos logit contributions
bell+0.043
 Mechan+0.042
days+0.042
 py+0.039
 stuffed+0.038
Neg logit contributions
aw-0.050
Le-0.041
 Remy-0.040
isi-0.039
 Sasha-0.039
Token as
Token ID355
Feature activation+7.30e-02

Pos logit contributions
aw+0.009
 Remy+0.008
una+0.008
 Sasha+0.008
 Duke+0.007
Neg logit contributions
days-0.017
bell-0.017
 Mechan-0.017
 stuffed-0.015
 t-0.015
Token they
Token ID484
Feature activation-4.24e-03

Pos logit contributions
aw+0.133
 Remy+0.126
Le+0.123
imes+0.119
una+0.116
Neg logit contributions
bell-0.135
days-0.132
 t-0.120
 Mechan-0.119
 stuffed-0.117
Token were
Token ID547
Feature activation-6.18e-03

Pos logit contributions
bell+0.007
days+0.007
 Mechan+0.006
 stuffed+0.006
 py+0.006
Neg logit contributions
aw-0.008
Le-0.008
 Remy-0.007
isi-0.007
imes-0.007
Token told
Token ID1297
Feature activation-1.49e-02

Pos logit contributions
bell+0.011
days+0.010
 t+0.010
 stuffed+0.010
 Mechan+0.010
Neg logit contributions
aw-0.012
Le-0.011
 Remy-0.011
imes-0.010
isi-0.010
Token and
Token ID290
Feature activation+3.87e-03

Pos logit contributions
bell+0.024
days+0.023
 t+0.021
 Mechan+0.021
 stuffed+0.021
Neg logit contributions
aw-0.031
 Remy-0.028
Le-0.027
imes-0.027
isi-0.027
Token sat
Token ID3332
Feature activation+1.37e-04

Pos logit contributions
aw+0.007
 Remy+0.007
Le+0.007
imes+0.007
 Sasha+0.006
Neg logit contributions
bell-0.007
days-0.006
 t-0.006
 stuffed-0.006
 Mechan-0.006
Token to
Token ID284
Feature activation-5.98e-03

Pos logit contributions
bell+0.048
days+0.046
 t+0.045
 stuffed+0.043
 unp+0.042
Neg logit contributions
aw-0.052
Le-0.048
imes-0.047
 Remy-0.046
isi-0.046
Token play
Token ID711
Feature activation-2.19e-02

Pos logit contributions
bell+0.011
days+0.010
spe+0.010
 Mechan+0.010
lights+0.010
Neg logit contributions
 Remy-0.009
isi-0.009
aw-0.009
imes-0.009
Le-0.009
Token outside
Token ID2354
Feature activation-2.43e-02

Pos logit contributions
bell+0.040
days+0.037
 Mechan+0.034
 t+0.033
 stuffed+0.032
Neg logit contributions
aw-0.042
 Remy-0.038
Le-0.038
una-0.037
imes-0.037
Token in
Token ID287
Feature activation-4.47e-03

Pos logit contributions
bell+0.055
 Mechan+0.053
days+0.050
 spoiler+0.049
 stuffed+0.046
Neg logit contributions
aw-0.034
Le-0.029
 Remy-0.028
imes-0.027
P-0.026
Token her
Token ID607
Feature activation+3.40e-03

Pos logit contributions
bell+0.009
days+0.009
 Mechan+0.008
 stuffed+0.008
 t+0.008
Neg logit contributions
aw-0.007
Le-0.007
 Remy-0.006
 Sasha-0.006
isi-0.006
Token backyard
Token ID24296
Feature activation+9.34e-03

Pos logit contributions
aw+0.006
imes+0.006
isi+0.006
Le+0.006
 Remy+0.006
Neg logit contributions
bell-0.006
 t-0.006
days-0.006
 stuffed-0.005
 unp-0.005
Token.
Token ID13
Feature activation+2.07e-03

Pos logit contributions
aw+0.017
Le+0.015
 Remy+0.015
imes+0.015
una+0.015
Neg logit contributions
bell-0.017
days-0.016
 Mechan-0.015
 stuffed-0.015
 t-0.015
Token One
Token ID1881
Feature activation-1.24e-02

Pos logit contributions
aw+0.004
 Remy+0.004
Le+0.004
imes+0.004
isi+0.004
Neg logit contributions
bell-0.003
days-0.003
 t-0.003
 Mechan-0.003
 stuffed-0.003
Token day
Token ID1110
Feature activation+7.22e-03

Pos logit contributions
bell+0.020
days+0.020
 t+0.019
 stuffed+0.018
 unp+0.017
Neg logit contributions
aw-0.025
imes-0.023
Le-0.023
isi-0.022
 Remy-0.022
Token,
Token ID11
Feature activation+2.41e-02

Pos logit contributions
aw+0.018
isi+0.017
Le+0.017
iles+0.017
una+0.016
Neg logit contributions
 t-0.008
bell-0.008
days-0.008
 stuffed-0.008
 unp-0.007
Token she
Token ID673
Feature activation-1.53e-02

Pos logit contributions
aw+0.041
Le+0.037
 Remy+0.037
imes+0.037
isi+0.036
Neg logit contributions
bell-0.047
days-0.045
 Mechan-0.042
 t-0.042
 stuffed-0.041
Token the
Token ID262
Feature activation+1.88e-02

Pos logit contributions
days+0.021
 Mechan+0.021
bell+0.019
 stuffed+0.018
 vacuum+0.017
Neg logit contributions
aw-0.013
 Remy-0.011
Le-0.011
 Sasha-0.011
una-0.011
Token bed
Token ID3996
Feature activation-4.39e-02

Pos logit contributions
aw+0.034
una+0.033
Le+0.032
crow+0.031
arling+0.030
Neg logit contributions
days-0.028
 Mechan-0.028
bell-0.026
 Sus-0.023
 spoiler-0.023
Token.
Token ID13
Feature activation+4.99e-03

Pos logit contributions
 Mechan+0.094
days+0.086
 stuffed+0.084
 spoiler+0.084
 py+0.083
Neg logit contributions
aw-0.068
una-0.054
imes-0.049
arling-0.048
Le-0.047
Token
Token ID198
Feature activation+7.45e-03

Pos logit contributions
aw+0.012
iles+0.011
isi+0.011
ile+0.011
una+0.010
Neg logit contributions
bell-0.007
 t-0.006
days-0.006
 Gr-0.006
 py-0.006
Token
Token ID198
Feature activation+9.04e-03

Pos logit contributions
aw+0.017
imes+0.016
isi+0.016
iles+0.016
arling+0.015
Neg logit contributions
bell-0.010
days-0.009
 t-0.009
 unp-0.009
 Gr-0.008
TokenShe
Token ID3347
Feature activation-4.13e-03

Pos logit contributions
aw+0.016
imes+0.014
iles+0.014
isi+0.014
 Remy+0.014
Neg logit contributions
bell-0.017
days-0.016
 t-0.016
 unp-0.015
 stuffed-0.015
Token put
Token ID1234
Feature activation-5.42e-03

Pos logit contributions
days+0.007
 Mechan+0.007
bell+0.007
 spoiler+0.006
etti+0.006
Neg logit contributions
aw-0.008
Le-0.007
una-0.007
 Remy-0.007
 Sasha-0.007
Token her
Token ID607
Feature activation-7.89e-03

Pos logit contributions
bell+0.013
days+0.012
 Mechan+0.012
 stuffed+0.011
spe+0.011
Neg logit contributions
aw-0.007
Le-0.007
imes-0.007
 Remy-0.006
una-0.006
Token dolls
Token ID36062
Feature activation-1.21e-02

Pos logit contributions
bell+0.014
 Mechan+0.014
days+0.013
etti+0.012
 Sus+0.012
Neg logit contributions
Le-0.012
una-0.012
imes-0.012
aw-0.011
 Remy-0.011
Token and
Token ID290
Feature activation-4.15e-03

Pos logit contributions
 Mechan+0.028
bell+0.028
days+0.026
 Gr+0.026
 Jos+0.026
Neg logit contributions
aw-0.015
Le-0.012
imes-0.012
 Remy-0.011
una-0.011
Token her
Token ID607
Feature activation-1.75e-02

Pos logit contributions
bell+0.006
days+0.006
 Mechan+0.006
 Sus+0.005
 unp+0.005
Neg logit contributions
aw-0.009
Le-0.008
 Remy-0.008
una-0.008
 Sasha-0.008
Token be
Token ID307
Feature activation+1.76e-02

Pos logit contributions
bell+0.011
 Mechan+0.011
days+0.010
 stuffed+0.010
 t+0.010
Neg logit contributions
aw-0.013
isi-0.012
 Sasha-0.012
 Remy-0.012
Le-0.012
Token careful
Token ID8161
Feature activation-1.31e-02

Pos logit contributions
aw+0.032
imes+0.026
 Sasha+0.026
 Remy+0.025
Le+0.025
Neg logit contributions
bell-0.034
 Mechan-0.031
days-0.031
 t-0.030
 stuffed-0.029
Token with
Token ID351
Feature activation-2.98e-03

Pos logit contributions
bell+0.023
 Mechan+0.022
days+0.022
 stuffed+0.021
 t+0.021
Neg logit contributions
aw-0.024
 Sasha-0.021
imes-0.021
una-0.020
arling-0.020
Token the
Token ID262
Feature activation+1.17e-02

Pos logit contributions
bell+0.006
days+0.005
 Mechan+0.005
 t+0.005
 stuffed+0.005
Neg logit contributions
aw-0.005
 Remy-0.005
imes-0.005
Le-0.005
 Sasha-0.005
Token tickets
Token ID8587
Feature activation-3.72e-02

Pos logit contributions
aw+0.019
isi+0.016
Le+0.015
una+0.015
opard+0.015
Neg logit contributions
bell-0.023
days-0.023
 Mechan-0.021
 Gr-0.020
 Jos-0.020
Token because
Token ID780
Feature activation-4.50e-03

Pos logit contributions
bell+0.065
days+0.064
 Mechan+0.064
 stuffed+0.059
 py+0.059
Neg logit contributions
aw-0.068
imes-0.058
isi-0.057
 Sasha-0.056
 Remy-0.056
Token they
Token ID484
Feature activation-3.62e-02

Pos logit contributions
bell+0.009
days+0.008
 Mechan+0.008
 t+0.008
 py+0.008
Neg logit contributions
aw-0.007
imes-0.006
 Sasha-0.006
 Remy-0.006
crow-0.006
Token both
Token ID1111
Feature activation+1.91e-02

Pos logit contributions
bell+0.065
 Mechan+0.058
 py+0.057
days+0.057
 t+0.053
Neg logit contributions
aw-0.063
imes-0.058
 Remy-0.058
isi-0.057
iles-0.056
Token wanted
Token ID2227
Feature activation-3.51e-03

Pos logit contributions
aw+0.037
 Remy+0.031
Le+0.031
imes+0.031
 Sasha+0.030
Neg logit contributions
bell-0.032
 Mechan-0.030
days-0.029
 py-0.028
 t-0.028
Token to
Token ID284
Feature activation+3.11e-03

Pos logit contributions
bell+0.007
days+0.007
 Mechan+0.006
 t+0.006
 stuffed+0.006
Neg logit contributions
aw-0.006
 Remy-0.005
Le-0.005
imes-0.005
 Sasha-0.005
Token celebrate
Token ID10648
Feature activation-4.27e-02

Pos logit contributions
aw+0.005
 Remy+0.005
isi+0.005
 Sasha+0.005
Le+0.005
Neg logit contributions
bell-0.005
 Mechan-0.005
days-0.005
 stuffed-0.005
 py-0.005
Token very
Token ID845
Feature activation+2.32e-02

Pos logit contributions
aw+0.003
Le+0.003
imes+0.003
 Remy+0.003
isi+0.003
Neg logit contributions
bell-0.002
days-0.002
 t-0.002
 stuffed-0.002
 unp-0.002
Token charming
Token ID23332
Feature activation+1.98e-03

Pos logit contributions
aw+0.051
Le+0.047
imes+0.047
isi+0.047
 Remy+0.046
Neg logit contributions
bell-0.034
days-0.032
 t-0.031
 stuffed-0.030
 unp-0.029
Token and
Token ID290
Feature activation-1.44e-02

Pos logit contributions
aw+0.004
 Remy+0.003
una+0.003
imes+0.003
Le+0.003
Neg logit contributions
bell-0.003
days-0.003
 Mechan-0.003
 stuffed-0.003
 t-0.003
Token friendly
Token ID8030
Feature activation+3.78e-02

Pos logit contributions
days+0.026
bell+0.025
 Mechan+0.023
 t+0.022
 py+0.021
Neg logit contributions
aw-0.027
 Remy-0.025
Le-0.024
imes-0.023
una-0.023
Token.
Token ID13
Feature activation+9.86e-03

Pos logit contributions
aw+0.081
Le+0.076
imes+0.074
 Remy+0.074
isi+0.074
Neg logit contributions
bell-0.057
days-0.054
 t-0.052
 stuffed-0.050
 unp-0.048
Token
Token ID198
Feature activation+1.04e-02

Pos logit contributions
aw+0.019
Le+0.017
 Remy+0.017
imes+0.017
isi+0.017
Neg logit contributions
bell-0.017
days-0.016
 t-0.016
 stuffed-0.015
 unp-0.015
Token
Token ID198
Feature activation+1.24e-02

Pos logit contributions
aw+0.022
imes+0.020
isi+0.020
Le+0.020
 Remy+0.020
Neg logit contributions
bell-0.016
days-0.014
 t-0.014
 unp-0.013
 stuffed-0.013
Token"
Token ID1
Feature activation-1.65e-03

Pos logit contributions
aw+0.022
isi+0.020
imes+0.020
 Remy+0.020
una+0.019
Neg logit contributions
bell-0.023
days-0.021
 t-0.021
 stuffed-0.020
 unp-0.020
TokenYes
Token ID5297
Feature activation+4.91e-03

Pos logit contributions
bell+0.003
days+0.003
 t+0.003
 stuffed+0.003
 unp+0.003
Neg logit contributions
aw-0.003
Le-0.003
 Remy-0.003
imes-0.003
isi-0.003
Token,
Token ID11
Feature activation+6.01e-03

Pos logit contributions
aw+0.008
 Remy+0.008
una+0.007
 Sasha+0.007
Le+0.007
Neg logit contributions
days-0.010
bell-0.009
 Mechan-0.009
 stuffed-0.008
 py-0.008
Token please
Token ID3387
Feature activation+3.30e-02

Pos logit contributions
aw+0.011
 Remy+0.010
imes+0.010
una+0.010
isi+0.009
Neg logit contributions
days-0.012
bell-0.011
 Mechan-0.010
 py-0.010
 unp-0.010
Token was
Token ID373
Feature activation-5.61e-03

Pos logit contributions
bell+0.004
days+0.004
 spoiler+0.004
 Mechan+0.004
 sponge+0.004
Neg logit contributions
aw-0.003
 Remy-0.003
Le-0.003
live-0.003
una-0.003
Token so
Token ID523
Feature activation-1.24e-03

Pos logit contributions
days+0.012
bell+0.011
 Mechan+0.011
 py+0.010
 stuffed+0.010
Neg logit contributions
aw-0.008
 Remy-0.007
una-0.007
 Sasha-0.007
imes-0.007
Token tidy
Token ID43044
Feature activation-6.86e-02

Pos logit contributions
 Mechan+0.002
days+0.002
bell+0.002
 stuffed+0.002
 py+0.002
Neg logit contributions
aw-0.002
 Remy-0.002
imes-0.002
Le-0.002
una-0.001
Token!
Token ID0
Feature activation+9.27e-03

Pos logit contributions
bell+0.141
days+0.138
 Mechan+0.134
 stuffed+0.121
 py+0.121
Neg logit contributions
aw-0.116
 Remy-0.096
una-0.093
 Sasha-0.086
arling-0.085
Token Inside
Token ID14384
Feature activation-1.29e-02

Pos logit contributions
aw+0.018
 Remy+0.017
Le+0.016
imes+0.016
 Sasha+0.016
Neg logit contributions
bell-0.016
days-0.015
 stuffed-0.015
 t-0.014
 Mechan-0.014
Token,
Token ID11
Feature activation+2.68e-02

Pos logit contributions
bell+0.022
days+0.021
 t+0.020
 stuffed+0.020
 Mechan+0.019
Neg logit contributions
aw-0.025
Le-0.023
 Remy-0.022
imes-0.022
isi-0.022
Token there
Token ID612
Feature activation-3.88e-02

Pos logit contributions
aw+0.044
 Remy+0.039
imes+0.038
Le+0.038
 Sasha+0.037
Neg logit contributions
bell-0.054
days-0.050
 Mechan-0.049
 py-0.046
 stuffed-0.045
Token lived
Token ID5615
Feature activation-1.46e-02

Pos logit contributions
bell+0.067
days+0.061
 Mechan+0.058
 stuffed+0.056
 py+0.056
Neg logit contributions
aw-0.078
Le-0.067
 Remy-0.067
imes-0.065
una-0.065
Token a
Token ID257
Feature activation-1.72e-02

Pos logit contributions
bell+0.025
days+0.023
 t+0.022
 stuffed+0.021
 Mechan+0.021
Neg logit contributions
aw-0.029
Le-0.027
imes-0.026
 Remy-0.026
isi-0.026
Token kind
Token ID1611
Feature activation+1.18e-02

Pos logit contributions
bell+0.028
days+0.028
 Mechan+0.024
 t+0.024
 unp+0.024
Neg logit contributions
aw-0.033
Le-0.031
 Remy-0.031
isi-0.029
emy-0.029
Token princess
Token ID21752
Feature activation-2.00e-02

Pos logit contributions
aw+0.021
isi+0.019
 Remy+0.018
una+0.018
Le+0.018
Neg logit contributions
days-0.022
bell-0.022
 Mechan-0.020
 unp-0.019
 py-0.019
Token through
Token ID832
Feature activation+3.28e-03

Pos logit contributions
aw+0.014
 Remy+0.012
Le+0.012
 vine+0.012
imes+0.012
Neg logit contributions
days-0.013
bell-0.012
 Mechan-0.011
 Gr-0.011
 Sn-0.011
Token nature
Token ID3450
Feature activation+4.22e-02

Pos logit contributions
aw+0.006
Le+0.005
 Remy+0.005
 Sasha+0.005
imes+0.005
Neg logit contributions
bell-0.006
days-0.006
 Mechan-0.005
 t-0.005
 stuffed-0.005
Token.
Token ID13
Feature activation-3.48e-03

Pos logit contributions
aw+0.089
Le+0.081
 Remy+0.080
imes+0.080
isi+0.079
Neg logit contributions
bell-0.065
days-0.062
 t-0.059
 stuffed-0.057
 Mechan-0.056
Token He
Token ID679
Feature activation+1.02e-04

Pos logit contributions
bell+0.006
days+0.005
 t+0.005
 stuffed+0.005
 unp+0.005
Neg logit contributions
aw-0.007
Le-0.007
 Remy-0.007
imes-0.006
isi-0.006
Token was
Token ID373
Feature activation-4.80e-03

Pos logit contributions
aw+0.000
Le+0.000
 Remy+0.000
imes+0.000
una+0.000
Neg logit contributions
bell-0.000
days-0.000
 Mechan-0.000
 t-0.000
 stuffed-0.000
Token excited
Token ID6568
Feature activation-4.82e-02

Pos logit contributions
bell+0.008
days+0.007
 t+0.007
 stuffed+0.007
 unp+0.006
Neg logit contributions
aw-0.010
Le-0.009
imes-0.009
 Remy-0.009
isi-0.009
Token to
Token ID284
Feature activation-2.23e-03

Pos logit contributions
bell+0.087
days+0.084
 t+0.079
 stuffed+0.078
 Mechan+0.078
Neg logit contributions
aw-0.089
 Remy-0.080
Le-0.079
isi-0.078
imes-0.078
Token explore
Token ID7301
Feature activation-3.48e-02

Pos logit contributions
bell+0.004
days+0.003
 t+0.003
 stuffed+0.003
 Mechan+0.003
Neg logit contributions
aw-0.005
Le-0.004
 Remy-0.004
imes-0.004
isi-0.004
Token the
Token ID262
Feature activation+1.90e-02

Pos logit contributions
bell+0.058
days+0.055
 t+0.052
 stuffed+0.050
 Mechan+0.050
Neg logit contributions
aw-0.070
Le-0.064
 Remy-0.064
imes-0.063
isi-0.062
Token world
Token ID995
Feature activation-2.90e-02

Pos logit contributions
aw+0.035
imes+0.033
Le+0.032
isi+0.032
 Remy+0.032
Neg logit contributions
bell-0.034
 t-0.032
days-0.031
 stuffed-0.031
 unp-0.029
Token and
Token ID290
Feature activation-2.17e-03

Pos logit contributions
bell+0.053
days+0.052
 Mechan+0.052
 t+0.049
 stuffed+0.049
Neg logit contributions
aw-0.053
 Remy-0.044
Le-0.043
imes-0.042
crow-0.042
Token her
Token ID607
Feature activation-1.62e-03

Pos logit contributions
 t+0.050
 stuffed+0.047
bell+0.047
 Sus+0.044
 Gr+0.043
Neg logit contributions
aw-0.083
opard-0.080
iles-0.078
Le-0.077
emy-0.077
Token Mum
Token ID38367
Feature activation+1.56e-02

Pos logit contributions
bell+0.003
days+0.003
 t+0.003
 stuffed+0.003
 Mechan+0.003
Neg logit contributions
aw-0.003
Le-0.002
 Remy-0.002
imes-0.002
isi-0.002
Token the
Token ID262
Feature activation+5.33e-03

Pos logit contributions
aw+0.028
 Remy+0.026
imes+0.025
Le+0.025
isi+0.025
Neg logit contributions
bell-0.029
days-0.027
 Mechan-0.026
 t-0.025
 stuffed-0.025
Token hook
Token ID8011
Feature activation+3.63e-02

Pos logit contributions
aw+0.010
Le+0.009
imes+0.009
 Remy+0.009
isi+0.009
Neg logit contributions
bell-0.010
days-0.009
 t-0.009
 stuffed-0.009
 unp-0.008
Token.
Token ID13
Feature activation-6.34e-03

Pos logit contributions
aw+0.071
imes+0.064
 Remy+0.064
Le+0.063
una+0.063
Neg logit contributions
bell-0.060
days-0.058
 Mechan-0.054
 t-0.054
 stuffed-0.052
Token Her
Token ID2332
Feature activation-1.72e-02

Pos logit contributions
bell+0.011
days+0.010
 t+0.010
 stuffed+0.009
 unp+0.009
Neg logit contributions
aw-0.012
Le-0.012
 Remy-0.011
imes-0.011
isi-0.011
Token Mum
Token ID38367
Feature activation-1.26e-02

Pos logit contributions
bell+0.032
days+0.031
 t+0.028
 Mechan+0.028
 stuffed+0.028
Neg logit contributions
aw-0.031
Le-0.028
 Remy-0.028
imes-0.028
una-0.027
Token said
Token ID531
Feature activation+1.42e-02

Pos logit contributions
bell+0.020
days+0.020
 Mechan+0.018
 py+0.017
 t+0.017
Neg logit contributions
aw-0.026
 Remy-0.023
Le-0.023
isi-0.022
una-0.022
Token that
Token ID326
Feature activation-4.96e-05

Pos logit contributions
aw+0.022
imes+0.020
 Sasha+0.020
 Remy+0.019
Le+0.019
Neg logit contributions
days-0.029
bell-0.029
 Mechan-0.027
 py-0.026
 t-0.025
Token it
Token ID340
Feature activation-1.23e-02

Pos logit contributions
bell+0.000
days+0.000
 t+0.000
 Mechan+0.000
 stuffed+0.000
Neg logit contributions
aw-0.000
 Remy-0.000
Le-0.000
imes-0.000
una-0.000
Token was
Token ID373
Feature activation-1.80e-02

Pos logit contributions
days+0.022
bell+0.022
 Mechan+0.020
 spoiler+0.019
 py+0.019
Neg logit contributions
aw-0.020
 Remy-0.019
una-0.018
live-0.018
Le-0.017
Token.
Token ID13
Feature activation+4.31e-03

Pos logit contributions
bell+0.021
days+0.020
 t+0.019
 stuffed+0.018
 unp+0.018
Neg logit contributions
aw-0.031
Le-0.028
isi-0.028
imes-0.028
 Remy-0.028
Token
Token ID198
Feature activation+4.66e-03

Pos logit contributions
isi+0.012
una+0.011
aw+0.011
iles+0.011
ile+0.011
Neg logit contributions
 unp-0.003
 Lots-0.002
 t-0.002
 Will-0.002
 Gr-0.002
Token
Token ID198
Feature activation+6.28e-03

Pos logit contributions
aw+0.012
imes+0.011
 unnecessary+0.011
isi+0.011
arling+0.011
Neg logit contributions
days-0.004
bell-0.004
 unp-0.004
 t-0.004
 decor-0.004
TokenThe
Token ID464
Feature activation+6.96e-03

Pos logit contributions
aw+0.011
imes+0.011
arling+0.010
una+0.010
 Sasha+0.010
Neg logit contributions
 unp-0.009
bell-0.009
days-0.009
 t-0.009
 lit-0.009
Token next
Token ID1306
Feature activation-4.72e-02

Pos logit contributions
aw+0.014
Le+0.013
imes+0.013
 Remy+0.013
isi+0.013
Neg logit contributions
bell-0.012
days-0.011
 t-0.011
 stuffed-0.010
 unp-0.010
Token day
Token ID1110
Feature activation-1.36e-02

Pos logit contributions
days+0.075
bell+0.075
 t+0.070
 unp+0.069
 stuffed+0.066
Neg logit contributions
aw-0.098
imes-0.090
isi-0.089
Le-0.088
arling-0.086
Token,
Token ID11
Feature activation+1.07e-02

Pos logit contributions
 t+0.007
 unp+0.007
 stuffed+0.006
bell+0.006
 decor+0.005
Neg logit contributions
isi-0.040
una-0.039
aw-0.038
live-0.037
imes-0.036
Token Fin
Token ID4463
Feature activation+3.84e-02

Pos logit contributions
isi+0.019
aw+0.019
una+0.019
ups+0.018
live+0.018
Neg logit contributions
 t-0.018
 yes-0.016
 stuffed-0.016
 Will-0.016
 unp-0.016
Token and
Token ID290
Feature activation-6.89e-03

Pos logit contributions
aw+0.085
Le+0.079
imes+0.078
isi+0.077
 Remy+0.077
Neg logit contributions
bell-0.055
days-0.052
 t-0.050
 stuffed-0.048
 unp-0.047
Token his
Token ID465
Feature activation-2.42e-02

Pos logit contributions
bell+0.008
 t+0.008
days+0.008
 stuffed+0.008
 unp+0.007
Neg logit contributions
aw-0.017
imes-0.015
Le-0.015
isi-0.015
arling-0.015
Token friends
Token ID2460
Feature activation+4.73e-03

Pos logit contributions
 t+0.050
 stuffed+0.049
bell+0.046
days+0.045
 unp+0.045
Neg logit contributions
aw-0.042
Le-0.036
isi-0.035
imes-0.035
arling-0.035
Token her
Token ID607
Feature activation-1.50e-02

Pos logit contributions
aw+0.083
Le+0.075
 Remy+0.074
imes+0.073
isi+0.073
Neg logit contributions
bell-0.094
days-0.090
 t-0.084
 Mechan-0.083
 stuffed-0.082
Token mom
Token ID1995
Feature activation-2.46e-02

Pos logit contributions
bell+0.027
days+0.025
 Mechan+0.024
 unp+0.022
 Jos+0.022
Neg logit contributions
aw-0.026
 Remy-0.025
Le-0.024
isi-0.024
una-0.024
Tokenmy
Token ID1820
Feature activation-1.98e-02

Pos logit contributions
bell+0.044
 Mechan+0.042
days+0.041
 stuffed+0.039
 t+0.039
Neg logit contributions
aw-0.043
isi-0.039
 Remy-0.038
imes-0.038
Le-0.037
Token.
Token ID13
Feature activation-3.84e-03

Pos logit contributions
bell+0.037
 Mechan+0.035
days+0.035
 spoiler+0.033
 stuffed+0.032
Neg logit contributions
aw-0.032
 Remy-0.030
isi-0.029
imes-0.029
una-0.029
Token Her
Token ID2332
Feature activation-1.42e-02

Pos logit contributions
bell+0.006
days+0.006
 t+0.005
 stuffed+0.005
 unp+0.005
Neg logit contributions
aw-0.008
Le-0.008
imes-0.007
 Remy-0.007
isi-0.007
Token mom
Token ID1995
Feature activation-4.66e-02

Pos logit contributions
days+0.027
bell+0.026
 Mechan+0.024
 Jos+0.022
 spoiler+0.022
Neg logit contributions
aw-0.021
una-0.020
 Remy-0.020
isi-0.020
Le-0.019
Tokenmy
Token ID1820
Feature activation-3.47e-02

Pos logit contributions
bell+0.094
days+0.093
 py+0.092
 Mechan+0.091
 stuffed+0.088
Neg logit contributions
aw-0.061
isi-0.056
 Remy-0.052
una-0.051
 Sasha-0.050
Token saw
Token ID2497
Feature activation-1.69e-02

Pos logit contributions
days+0.070
bell+0.068
 spoiler+0.066
 Mechan+0.065
lights+0.064
Neg logit contributions
aw-0.048
 Remy-0.047
 Sasha-0.044
isi-0.044
Le-0.043
Token her
Token ID607
Feature activation-2.85e-02

Pos logit contributions
bell+0.028
 t+0.027
days+0.026
 stuffed+0.026
 unp+0.025
Neg logit contributions
aw-0.032
Le-0.031
 Remy-0.029
emy-0.029
imes-0.029
Token and
Token ID290
Feature activation-9.14e-03

Pos logit contributions
bell+0.050
days+0.049
 Mechan+0.047
 spoiler+0.042
 Jos+0.041
Neg logit contributions
aw-0.050
imes-0.045
 Sasha-0.045
 Remy-0.043
isi-0.043
Token said
Token ID531
Feature activation+3.21e-02

Pos logit contributions
bell+0.019
days+0.018
 Mechan+0.017
 py+0.017
 t+0.016
Neg logit contributions
aw-0.014
 Remy-0.013
Le-0.012
 Sasha-0.012
isi-0.012
Token big
Token ID1263
Feature activation+3.63e-03

Pos logit contributions
bell+0.023
 t+0.021
days+0.021
 stuffed+0.020
 unp+0.020
Neg logit contributions
aw-0.026
imes-0.024
Le-0.024
isi-0.024
 Remy-0.023
Token hole
Token ID7604
Feature activation+4.62e-02

Pos logit contributions
aw+0.007
 Remy+0.006
Le+0.006
iles+0.006
emy+0.006
Neg logit contributions
days-0.007
bell-0.007
 stuffed-0.006
 Mechan-0.006
 unp-0.006
Token on
Token ID319
Feature activation-1.06e-02

Pos logit contributions
aw+0.079
imes+0.068
 Remy+0.065
una+0.065
Le+0.065
Neg logit contributions
bell-0.088
days-0.087
 Mechan-0.083
 t-0.082
 stuffed-0.081
Token top
Token ID1353
Feature activation+2.15e-02

Pos logit contributions
days+0.023
bell+0.022
 Mechan+0.021
 stuffed+0.020
 py+0.019
Neg logit contributions
aw-0.016
 Remy-0.015
Le-0.015
una-0.014
 Sasha-0.014
Token called
Token ID1444
Feature activation+3.98e-02

Pos logit contributions
aw+0.041
Le+0.037
 Remy+0.037
imes+0.037
isi+0.036
Neg logit contributions
bell-0.037
days-0.036
 t-0.034
 stuffed-0.034
 Mechan-0.033
Token a
Token ID257
Feature activation-1.34e-02

Pos logit contributions
aw+0.073
 Remy+0.068
imes+0.066
Le+0.066
una+0.065
Neg logit contributions
bell-0.073
days-0.073
 stuffed-0.064
 t-0.062
 Mechan-0.062
Token volcano
Token ID32410
Feature activation-8.62e-03

Pos logit contributions
bell+0.023
 t+0.021
days+0.021
 stuffed+0.020
 unp+0.019
Neg logit contributions
aw-0.027
imes-0.025
isi-0.024
Le-0.024
 Remy-0.024
Token.
Token ID13
Feature activation-1.91e-03

Pos logit contributions
bell+0.013
days+0.011
 t+0.011
 stuffed+0.011
 unp+0.011
Neg logit contributions
aw-0.019
Le-0.018
isi-0.018
imes-0.018
 Remy-0.018
Token The
Token ID383
Feature activation-4.11e-03

Pos logit contributions
bell+0.003
days+0.003
 stuffed+0.003
 t+0.003
 Mechan+0.003
Neg logit contributions
aw-0.003
 Remy-0.003
Le-0.003
imes-0.003
 Sasha-0.003
Token volcano
Token ID32410
Feature activation-2.94e-02

Pos logit contributions
bell+0.008
days+0.007
 t+0.007
 stuffed+0.007
 Mechan+0.007
Neg logit contributions
aw-0.007
Le-0.007
 Remy-0.006
imes-0.006
una-0.006
Token was
Token ID373
Feature activation-1.09e-02

Pos logit contributions
bell+0.041
days+0.039
 t+0.036
 stuffed+0.036
 Mechan+0.035
Neg logit contributions
aw-0.066
Le-0.059
 Remy-0.059
imes-0.059
una-0.057
Token had
Token ID550
Feature activation+1.05e-02

Pos logit contributions
days+0.007
bell+0.006
 Mechan+0.006
 spoiler+0.006
lights+0.006
Neg logit contributions
aw-0.006
 Remy-0.005
Le-0.005
una-0.005
emy-0.005
Token gone
Token ID3750
Feature activation-9.70e-03

Pos logit contributions
aw+0.017
Le+0.015
 Remy+0.015
una+0.014
 Sasha+0.014
Neg logit contributions
bell-0.022
days-0.021
 stuffed-0.019
 Mechan-0.019
 t-0.019
Token from
Token ID422
Feature activation-7.11e-03

Pos logit contributions
bell+0.020
days+0.019
 Mechan+0.018
 stuffed+0.018
 t+0.017
Neg logit contributions
aw-0.016
 Remy-0.014
Le-0.013
una-0.013
 Sasha-0.013
Token the
Token ID262
Feature activation+2.24e-02

Pos logit contributions
bell+0.013
days+0.013
 Mechan+0.012
 stuffed+0.012
 t+0.011
Neg logit contributions
aw-0.012
 Remy-0.012
Le-0.011
imes-0.011
 Sasha-0.011
Token hum
Token ID1311
Feature activation-4.17e-02

Pos logit contributions
aw+0.041
Le+0.038
 Remy+0.037
imes+0.037
isi+0.037
Neg logit contributions
bell-0.040
days-0.039
 t-0.037
 stuffed-0.036
 unp-0.035
Tokenbl
Token ID2436
Feature activation-9.15e-02

Pos logit contributions
bell+0.083
days+0.080
 Mechan+0.079
 t+0.079
 stuffed+0.078
Neg logit contributions
aw-0.071
imes-0.058
una-0.057
Le-0.056
crow-0.054
Tokenest
Token ID395
Feature activation-2.39e-02

Pos logit contributions
bell+0.172
days+0.168
 t+0.165
 stuffed+0.160
 unp+0.156
Neg logit contributions
aw-0.163
imes-0.145
isi-0.143
una-0.140
Le-0.138
Token sack
Token ID23704
Feature activation-3.87e-03

Pos logit contributions
bell+0.043
days+0.042
 Mechan+0.040
 unp+0.038
 t+0.037
Neg logit contributions
aw-0.043
isi-0.037
 Remy-0.037
imes-0.037
crow-0.036
Token in
Token ID287
Feature activation-2.61e-02

Pos logit contributions
 Mechan+0.007
days+0.007
bell+0.007
 py+0.007
 spoiler+0.007
Neg logit contributions
aw-0.006
 Remy-0.005
isi-0.005
imes-0.005
una-0.005
Token the
Token ID262
Feature activation+7.47e-03

Pos logit contributions
bell+0.054
days+0.052
 Mechan+0.050
 stuffed+0.047
 t+0.046
Neg logit contributions
aw-0.038
 Remy-0.038
Le-0.037
 Sasha-0.037
una-0.035
Token world
Token ID995
Feature activation-4.08e-02

Pos logit contributions
aw+0.013
 Remy+0.011
Le+0.011
isi+0.011
imes+0.011
Neg logit contributions
bell-0.014
days-0.014
 stuffed-0.013
 t-0.013
 Mechan-0.013
Token it
Token ID340
Feature activation+1.80e-02

Pos logit contributions
bell+0.076
days+0.072
 t+0.070
 stuffed+0.067
 unp+0.066
Neg logit contributions
aw-0.086
Le-0.079
 Remy-0.078
imes-0.078
isi-0.077
Token to
Token ID284
Feature activation-7.42e-03

Pos logit contributions
aw+0.030
 Remy+0.027
Le+0.026
imes+0.026
una+0.026
Neg logit contributions
bell-0.035
days-0.034
 Mechan-0.032
 t-0.032
 stuffed-0.032
Token you
Token ID345
Feature activation+1.60e-02

Pos logit contributions
bell+0.013
days+0.012
 Mechan+0.011
 t+0.011
 stuffed+0.011
Neg logit contributions
aw-0.014
 Remy-0.013
Le-0.013
una-0.013
isi-0.013
Token for
Token ID329
Feature activation+3.65e-02

Pos logit contributions
aw+0.025
 Remy+0.023
una+0.022
imes+0.022
arling+0.021
Neg logit contributions
 Mechan-0.030
bell-0.029
 spoiler-0.028
days-0.027
 stuffed-0.027
Token your
Token ID534
Feature activation-2.49e-02

Pos logit contributions
aw+0.065
 Remy+0.061
Le+0.060
una+0.060
imes+0.059
Neg logit contributions
bell-0.068
days-0.062
 stuffed-0.058
 Mechan-0.057
 t-0.057
Token birthday
Token ID10955
Feature activation-9.40e-02

Pos logit contributions
bell+0.045
 Mechan+0.040
days+0.040
 lit+0.037
 unp+0.036
Neg logit contributions
aw-0.041
 Remy-0.041
imes-0.040
Le-0.040
una-0.039
Token."
Token ID526
Feature activation-2.14e-02

Pos logit contributions
bell+0.156
 Mechan+0.150
days+0.148
 stuffed+0.136
 t+0.132
Neg logit contributions
aw-0.185
una-0.161
isi-0.159
 Remy-0.158
Le-0.155
Token
Token ID198
Feature activation+8.58e-03

Pos logit contributions
bell+0.037
days+0.035
 t+0.034
 stuffed+0.033
 unp+0.032
Neg logit contributions
aw-0.041
Le-0.038
imes-0.037
isi-0.037
 Remy-0.037
Token
Token ID198
Feature activation+9.69e-03

Pos logit contributions
aw+0.020
imes+0.019
iles+0.019
isi+0.019
arling+0.019
Neg logit contributions
 t-0.010
bell-0.010
days-0.010
 Gr-0.009
 stuffed-0.009
TokenAnna
Token ID31160
Feature activation-1.17e-02

Pos logit contributions
aw+0.019
imes+0.019
 Remy+0.018
isi+0.018
arling+0.018
Neg logit contributions
bell-0.015
days-0.015
 t-0.014
 stuffed-0.014
 unp-0.013
Token says
Token ID1139
Feature activation+3.07e-02

Pos logit contributions
bell+0.019
days+0.019
 Mechan+0.017
 stuffed+0.017
 t+0.016
Neg logit contributions
aw-0.024
 Remy-0.021
Le-0.021
una-0.021
imes-0.021
Token help
Token ID1037
Feature activation-2.65e-02

Pos logit contributions
aw+0.071
 Remy+0.067
Le+0.067
una+0.064
isi+0.063
Neg logit contributions
bell-0.071
days-0.067
 Mechan-0.061
 t-0.061
 stuffed-0.059
Token but
Token ID475
Feature activation+3.71e-03

Pos logit contributions
bell+0.039
days+0.037
 t+0.036
 stuffed+0.035
 unp+0.034
Neg logit contributions
aw-0.057
Le-0.053
imes-0.052
 Remy-0.052
isi-0.052
Token they
Token ID484
Feature activation-2.00e-02

Pos logit contributions
aw+0.008
Le+0.007
 Remy+0.007
imes+0.007
isi+0.007
Neg logit contributions
bell-0.006
days-0.006
 t-0.005
 stuffed-0.005
 Mechan-0.005
Token were
Token ID547
Feature activation-1.20e-02

Pos logit contributions
bell+0.030
days+0.028
 t+0.027
 stuffed+0.026
 unp+0.025
Neg logit contributions
aw-0.044
Le-0.041
imes-0.040
 Remy-0.040
isi-0.040
Token both
Token ID1111
Feature activation+3.19e-02

Pos logit contributions
bell+0.020
days+0.020
 t+0.018
 stuffed+0.018
 Mechan+0.018
Neg logit contributions
aw-0.023
Le-0.021
 Remy-0.021
imes-0.021
isi-0.021
Token asleep
Token ID16039
Feature activation-9.01e-02

Pos logit contributions
aw+0.057
 Remy+0.050
Le+0.049
imes+0.049
 Sasha+0.048
Neg logit contributions
bell-0.059
days-0.056
 Mechan-0.053
 t-0.052
 stuffed-0.051
Token.
Token ID13
Feature activation+4.37e-03

Pos logit contributions
bell+0.192
days+0.174
 Mechan+0.169
 stuffed+0.162
 t+0.159
Neg logit contributions
aw-0.146
 Remy-0.130
Le-0.124
arling-0.120
 Duke-0.116
Token In
Token ID554
Feature activation+9.81e-03

Pos logit contributions
aw+0.009
imes+0.009
isi+0.009
Le+0.008
iles+0.008
Neg logit contributions
bell-0.007
days-0.006
 t-0.006
 unp-0.006
 Gr-0.006
Token the
Token ID262
Feature activation+3.49e-02

Pos logit contributions
aw+0.019
Le+0.017
 Remy+0.017
imes+0.017
isi+0.017
Neg logit contributions
bell-0.017
days-0.016
 t-0.015
 stuffed-0.015
 Mechan-0.015
Token end
Token ID886
Feature activation+7.21e-02

Pos logit contributions
imes+0.069
aw+0.065
 Remy+0.062
izards+0.062
emy+0.062
Neg logit contributions
bell-0.063
 t-0.058
 stuffed-0.052
days-0.052
 unp-0.051
Token,
Token ID11
Feature activation+1.23e-02

Pos logit contributions
aw+0.157
Le+0.145
isi+0.144
imes+0.144
 Remy+0.141
Neg logit contributions
bell-0.106
days-0.100
 t-0.097
 stuffed-0.093
 unp-0.091
Token needle
Token ID17598
Feature activation+3.01e-03

Pos logit contributions
bell+0.003
days+0.003
 unp+0.002
 Jos+0.002
 lit+0.002
Neg logit contributions
aw-0.003
 Remy-0.003
imes-0.003
una-0.002
crow-0.002
Token and
Token ID290
Feature activation-1.42e-02

Pos logit contributions
aw+0.005
imes+0.004
una+0.004
opard+0.004
 Remy+0.004
Neg logit contributions
days-0.006
bell-0.006
 Mechan-0.005
 Jos-0.005
 py-0.005
Token a
Token ID257
Feature activation-3.12e-02

Pos logit contributions
days+0.029
bell+0.028
 Mechan+0.025
etti+0.024
 unp+0.023
Neg logit contributions
aw-0.023
 Remy-0.021
imes-0.020
una-0.020
Le-0.019
Token cold
Token ID4692
Feature activation-1.34e-02

Pos logit contributions
days+0.051
bell+0.049
 unp+0.043
 Mechan+0.042
 Jos+0.040
Neg logit contributions
aw-0.059
 Remy-0.055
Le-0.055
imes-0.053
una-0.053
Token st
Token ID336
Feature activation-2.68e-02

Pos logit contributions
bell+0.022
days+0.021
 Jos+0.020
 unp+0.019
 Mechan+0.019
Neg logit contributions
aw-0.025
crow-0.023
una-0.022
 Remy-0.021
opard-0.021
Tokeneth
Token ID2788
Feature activation-1.22e-01

Pos logit contributions
days+0.024
bell+0.024
 t+0.021
 stuffed+0.021
 unp+0.019
Neg logit contributions
aw-0.073
Le-0.067
una-0.067
imes-0.067
 Remy-0.067
Tokenoscope
Token ID40326
Feature activation-4.42e-03

Pos logit contributions
 Mechan+0.209
bell+0.207
days+0.198
 Jos+0.195
etti+0.192
Neg logit contributions
aw-0.216
crow-0.196
una-0.191
opard-0.178
ile-0.173
Token.
Token ID13
Feature activation+1.04e-03

Pos logit contributions
bell+0.008
days+0.008
 stuffed+0.007
 t+0.007
 Mechan+0.007
Neg logit contributions
aw-0.009
imes-0.007
Le-0.007
una-0.007
isi-0.007
Token The
Token ID383
Feature activation-1.01e-02

Pos logit contributions
aw+0.002
 Remy+0.002
imes+0.002
Le+0.002
una+0.002
Neg logit contributions
days-0.002
bell-0.002
 t-0.002
 stuffed-0.002
 Mechan-0.002
Token doctor
Token ID6253
Feature activation-1.13e-02

Pos logit contributions
bell+0.023
days+0.022
 unp+0.020
 stuffed+0.020
 Sus+0.020
Neg logit contributions
aw-0.013
Le-0.012
una-0.012
 Remy-0.011
imes-0.011
Token made
Token ID925
Feature activation-3.14e-02

Pos logit contributions
days+0.023
bell+0.021
 Mechan+0.021
 py+0.021
 matt+0.021
Neg logit contributions
aw-0.017
una-0.013
 Remy-0.013
Le-0.013
opard-0.013
Token.
Token ID13
Feature activation+4.13e-03

Pos logit contributions
bell+0.022
days+0.021
 t+0.020
 stuffed+0.020
 Mechan+0.019
Neg logit contributions
aw-0.028
Le-0.026
imes-0.026
 Remy-0.026
isi-0.025
Token
Token ID198
Feature activation+1.99e-03

Pos logit contributions
aw+0.009
Le+0.008
isi+0.008
imes+0.008
 Remy+0.008
Neg logit contributions
bell-0.007
days-0.006
 t-0.006
 stuffed-0.006
 unp-0.006
Token
Token ID198
Feature activation+4.14e-03

Pos logit contributions
aw+0.004
imes+0.004
isi+0.004
iles+0.004
arling+0.004
Neg logit contributions
bell-0.003
days-0.003
 t-0.003
 unp-0.002
 Gr-0.002
Token"
Token ID1
Feature activation-3.92e-04

Pos logit contributions
aw+0.007
Le+0.006
imes+0.006
 Remy+0.006
isi+0.006
Neg logit contributions
bell-0.008
days-0.008
 t-0.008
 stuffed-0.007
 unp-0.007
TokenA
Token ID32
Feature activation-5.00e-02

Pos logit contributions
bell+0.001
 stuffed+0.001
 t+0.001
days+0.001
 unp+0.001
Neg logit contributions
aw-0.001
Le-0.001
 Remy-0.000
imes-0.000
opard-0.000
Token hotel
Token ID7541
Feature activation-1.00e-01

Pos logit contributions
days+0.077
 hips+0.075
etti+0.074
bell+0.074
 Mechan+0.073
Neg logit contributions
aw-0.088
crow-0.078
iles-0.074
 goose-0.074
una-0.073
Token is
Token ID318
Feature activation-1.10e-02

Pos logit contributions
bell+0.177
days+0.170
 stuffed+0.165
 Mechan+0.164
 t+0.163
Neg logit contributions
aw-0.185
iles-0.151
imes-0.149
crow-0.148
 Remy-0.147
Token a
Token ID257
Feature activation-4.70e-02

Pos logit contributions
days+0.022
bell+0.021
 Mechan+0.020
 stuffed+0.019
 spoiler+0.019
Neg logit contributions
aw-0.017
 Remy-0.015
una-0.014
 Sasha-0.014
iles-0.014
Token big
Token ID1263
Feature activation-1.84e-02

Pos logit contributions
days+0.083
bell+0.083
 Mechan+0.076
etti+0.073
 Jos+0.072
Neg logit contributions
aw-0.073
 Remy-0.065
opard-0.063
 goose-0.063
Le-0.062
Token house
Token ID2156
Feature activation-4.24e-02

Pos logit contributions
days+0.032
bell+0.032
 Mechan+0.030
 lit+0.030
cel+0.029
Neg logit contributions
aw-0.028
 goose-0.025
crow-0.025
 strangers-0.024
 hawk-0.023
Token with
Token ID351
Feature activation-5.13e-03

Pos logit contributions
days+0.076
bell+0.075
 Mechan+0.075
 py+0.073
 stuffed+0.073
Neg logit contributions
aw-0.073
una-0.054
 Remy-0.054
isi-0.054
crow-0.054