TOP ACTIVATIONS
MAX = 10.924

hugged each other with g lee . After playing
her g iggle with g lee . The girl
and ran off in g lee . <|endoftext|> The little girl
stopped . Kay lee was excited and said ,
and qu acked with g lee . He opened the basket
two friends laughed with g lee . They had found a
Sarah smiled with g lee , and started to wonder
and gigg led with g lee . They loved their new
jumped and laughed with g lee . As he
The princess laughed with g lee . She pointed and pointed
and spark led with g lee . From then on ,
to dance around in g lee ! The little girl was
danced and shouted with g lee . Jack
started to chase after Kay lee . She screamed and ran
the girl laughed with g lee . The cookies were delicious
from her , but Kay lee was determined to catch it
her . Kay lee was too scared to move
, he screamed with g lee ! " Can
George yelled with g lee and scrambled onto Cloud y
, he shouted with g lee . The other

MIN ACTIVATIONS
MIN = -9.446

them . They watched in horror as their cart crashed into
destroyed clock and gasped in horror . The old
looked up and to her horror she saw a giant scary
father and daughter watched in horror as the teenager cr ue
, Sarah , watched in horror as Tim my fell off
looked at each other in horror . They had no way
. L ila watched in horror as her balloon got smaller
The flower watched in horror as the potato began to
saw the fear and the horror . He saw the crash
air . Sam watched in horror as R oo landed on
, reluctantly . To his horror , it was bitter and
times , but to no avail . Jane 's
out , but to no avail . He felt sad and
him . But to no avail , they were too scared
deep paws , to no avail . He finally thought of
eat his treat . The end . <|endoftext|> Once there was
restored . The end . <|endoftext|> John was walking
cozy and content . The end . <|endoftext|> Once upon a
peacefully and happily . The end . <|endoftext|> Once upon a
it flew away . The end . <|endoftext|> Once upon a

INTERVAL 5.831 - 10.924
CONTAINS 0.111%

and he didn 't know how he could do it .
hopped away , no matter how the monster yelled .
L ily showed Max how to pretend to be a
girl was very happy with how it looked . <|endoftext|> Once
with joy when he saw how beautiful it looked .

INTERVAL 0.739 - 5.831
CONTAINS 24.496%

favorite drink . He proudly took it and marched back to
a microphone and wanted to play . But a man yelled
raining !" Lily exclaimed . " It 's
realised that its friend had been trying to help it and
reached the temple , the little girl gazed in wonder .

INTERVAL -4.353 - 0.739
CONTAINS 74.897%

yellow flower in the grass . It made her heart happy
Tim my !" Lily said . " Hi Lily
do it , Tim my ! Keep trying and don 't
€ Max opened the box , and to the
Sammy wanted to arrive at the truth and understand it ,

INTERVAL -9.446 - -4.353
CONTAINS 0.495%

Her mom replied , " No , we can 't go
loved . The end . M
crawl into the hay and start to dig and pile and
toys and no TV and no dessert . L
he dropped something . The end . <|endoftext|> Once upon a
Token hugged
Token ID41130
Feature activation+3.13e+00

Pos logit contributions
nam+0.019
ooter+0.018
anna+0.018
ilda+0.017
lee+0.016
Neg logit contributions
aw-0.024
Run-0.024
 horror-0.022
oc-0.021
Is-0.020
Token each
Token ID1123
Feature activation-3.69e-01

Pos logit contributions
nam+0.185
anna+0.171
ooter+0.168
ilda+0.167
lee+0.167
Neg logit contributions
aw-0.161
Run-0.158
oc-0.140
 horror-0.136
Is-0.127
Token other
Token ID584
Feature activation-4.02e+00

Pos logit contributions
aw+0.021
Run+0.021
oc+0.019
 horror+0.019
Is+0.018
Neg logit contributions
nam-0.018
anna-0.018
ooter-0.017
ilda-0.017
 Jackie-0.016
Token with
Token ID351
Feature activation-8.73e-01

Pos logit contributions
aw+0.217
Run+0.205
oc+0.190
 horror+0.189
Is+0.166
Neg logit contributions
nam-0.222
ooter-0.209
anna-0.202
ilda-0.199
lee-0.198
Token g
Token ID308
Feature activation+2.95e-01

Pos logit contributions
aw+0.056
Run+0.055
oc+0.051
 horror+0.047
Is+0.047
Neg logit contributions
nam-0.041
lee-0.036
 Jackie-0.036
anna-0.035
ilda-0.035
Tokenlee
Token ID7197
Feature activation+1.09e+01

Pos logit contributions
nam+0.010
ooter+0.007
ilda+0.006
ppa+0.006
 Emmy+0.005
Neg logit contributions
aw-0.025
 horror-0.022
Run-0.022
oc-0.021
der-0.019
Token.
Token ID13
Feature activation+6.08e-01

Pos logit contributions
nam+0.658
ooter+0.588
 handsome+0.564
anna+0.563
 Jackie+0.560
Neg logit contributions
aw-0.586
Run-0.519
oc-0.482
 horror-0.458
Is-0.382
Token
Token ID198
Feature activation+1.99e-01

Pos logit contributions
nam+0.036
ooter+0.033
anna+0.031
ilda+0.031
 handsome+0.030
Neg logit contributions
aw-0.032
Run-0.031
 horror-0.029
oc-0.028
Is-0.027
Token
Token ID198
Feature activation+1.48e-01

Pos logit contributions
nam+0.014
ooter+0.012
anna+0.011
 handsome+0.011
ilda+0.011
Neg logit contributions
aw-0.009
Run-0.009
oc-0.008
 horror-0.008
Is-0.008
TokenAfter
Token ID3260
Feature activation-3.52e+00

Pos logit contributions
nam+0.009
anna+0.009
ilda+0.009
 Jackie+0.009
lee+0.009
Neg logit contributions
aw-0.007
Run-0.007
 horror-0.006
oc-0.006
Is-0.005
Token playing
Token ID2712
Feature activation+3.91e+00

Pos logit contributions
aw+0.181
Run+0.177
oc+0.158
 horror+0.155
Is+0.142
Neg logit contributions
nam-0.208
ooter-0.191
anna-0.191
ilda-0.187
lee-0.185
Token her
Token ID607
Feature activation+2.36e+00

Pos logit contributions
aw+0.053
Run+0.051
 horror+0.046
oc+0.045
Is+0.042
Neg logit contributions
nam-0.055
ooter-0.052
anna-0.051
ilda-0.048
lee-0.048
Token g
Token ID308
Feature activation+2.90e-01

Pos logit contributions
nam+0.093
anna+0.087
ooter+0.085
ilda+0.084
lee+0.079
Neg logit contributions
aw-0.163
Run-0.156
 horror-0.156
oc-0.149
Is-0.135
Tokeniggle
Token ID24082
Feature activation+7.36e-01

Pos logit contributions
nam+0.017
ooter+0.013
ilda+0.013
 handsome+0.013
 Emmy+0.012
Neg logit contributions
aw-0.017
 horror-0.015
oc-0.015
Run-0.015
 disaster-0.012
Token with
Token ID351
Feature activation-8.66e-01

Pos logit contributions
nam+0.043
ooter+0.040
anna+0.039
ilda+0.038
lee+0.037
Neg logit contributions
aw-0.039
Run-0.037
oc-0.034
 horror-0.033
Is-0.030
Token g
Token ID308
Feature activation+3.13e-01

Pos logit contributions
aw+0.052
Run+0.050
 horror+0.046
oc+0.045
Is+0.041
Neg logit contributions
nam-0.044
ooter-0.042
anna-0.041
ilda-0.040
aj-0.038
Tokenlee
Token ID7197
Feature activation+1.09e+01

Pos logit contributions
nam+0.012
ooter+0.008
ilda+0.007
ppa+0.007
 Emmy+0.006
Neg logit contributions
aw-0.027
 horror-0.023
Run-0.022
oc-0.022
Ble-0.020
Token.
Token ID13
Feature activation+3.13e-01

Pos logit contributions
nam+0.699
ooter+0.611
 Jackie+0.589
 handsome+0.589
aj+0.583
Neg logit contributions
aw-0.565
Run-0.481
oc-0.464
 horror-0.416
cer-0.348
Token
Token ID198
Feature activation+2.05e-02

Pos logit contributions
nam+0.019
ooter+0.017
anna+0.017
inations+0.017
ilda+0.017
Neg logit contributions
aw-0.016
Run-0.015
oc-0.014
 horror-0.014
Is-0.013
Token
Token ID198
Feature activation+5.22e-03

Pos logit contributions
nam+0.001
ooter+0.001
anna+0.001
ilda+0.001
 handsome+0.001
Neg logit contributions
aw-0.001
Run-0.001
oc-0.001
Is-0.001
 horror-0.001
TokenThe
Token ID464
Feature activation-7.25e-01

Pos logit contributions
nam+0.000
anna+0.000
ooter+0.000
ilda+0.000
 Jackie+0.000
Neg logit contributions
aw-0.000
Run-0.000
 horror-0.000
oc-0.000
Is-0.000
Token girl
Token ID2576
Feature activation-7.45e-01

Pos logit contributions
aw+0.045
Run+0.044
oc+0.040
 horror+0.040
Is+0.037
Neg logit contributions
nam-0.035
ooter-0.032
anna-0.032
ilda-0.031
lee-0.030
Token and
Token ID290
Feature activation+1.86e-01

Pos logit contributions
nam+0.074
lee+0.068
ooter+0.067
 Jackie+0.067
anna+0.067
Neg logit contributions
Run-0.080
aw-0.078
oc-0.070
 horror-0.068
Is-0.065
Token ran
Token ID4966
Feature activation+1.00e+00

Pos logit contributions
nam+0.009
ooter+0.008
anna+0.008
ilda+0.008
lee+0.008
Neg logit contributions
aw-0.011
Run-0.011
oc-0.010
 horror-0.010
Is-0.009
Token off
Token ID572
Feature activation-2.33e-02

Pos logit contributions
nam+0.053
ooter+0.044
anna+0.044
ilda+0.043
aj+0.043
Neg logit contributions
aw-0.062
Run-0.059
 horror-0.054
oc-0.053
Is-0.048
Token in
Token ID287
Feature activation+1.70e+00

Pos logit contributions
Run+0.001
aw+0.001
 horror+0.001
oc+0.001
Is+0.001
Neg logit contributions
nam-0.001
anna-0.001
ooter-0.001
aj-0.001
ilda-0.001
Token g
Token ID308
Feature activation+1.97e-01

Pos logit contributions
nam+0.089
ooter+0.080
 Jackie+0.080
lee+0.080
anna+0.078
Neg logit contributions
aw-0.101
Run-0.097
oc-0.087
 horror-0.081
Is-0.080
Tokenlee
Token ID7197
Feature activation+1.09e+01

Pos logit contributions
nam+0.007
ooter+0.004
ilda+0.004
ppa+0.004
 Emmy+0.004
Neg logit contributions
aw-0.017
Run-0.015
 horror-0.015
oc-0.015
 disaster-0.013
Token.
Token ID13
Feature activation+2.07e-01

Pos logit contributions
nam+0.636
ooter+0.575
anna+0.562
 handsome+0.549
 Jackie+0.547
Neg logit contributions
aw-0.593
Run-0.533
oc-0.504
 horror-0.476
Is-0.403
Token<|endoftext|>
Token ID50256
Feature activation-1.79e+00

Pos logit contributions
nam+0.012
ooter+0.011
anna+0.011
ilda+0.010
lee+0.010
Neg logit contributions
aw-0.011
Run-0.011
oc-0.010
 horror-0.010
Is-0.009
TokenThe
Token ID464
Feature activation-1.05e+00

Pos logit contributions
aw+0.092
Run+0.090
oc+0.080
 horror+0.079
Is+0.073
Neg logit contributions
nam-0.106
ooter-0.098
anna-0.097
ilda-0.094
lee-0.093
Token little
Token ID1310
Feature activation+1.08e+00

Pos logit contributions
Run+0.066
aw+0.066
 horror+0.056
oc+0.055
Is+0.052
Neg logit contributions
nam-0.052
anna-0.049
ilda-0.048
ooter-0.047
ppa-0.044
Token girl
Token ID2576
Feature activation-1.10e+00

Pos logit contributions
nam+0.070
anna+0.066
ooter+0.065
ilda+0.065
lee+0.063
Neg logit contributions
aw-0.050
Run-0.048
oc-0.041
 horror-0.040
Is-0.036
Token stopped
Token ID5025
Feature activation+8.48e-01

Pos logit contributions
aw+0.185
Run+0.178
 horror+0.157
oc+0.155
Is+0.143
Neg logit contributions
nam-0.191
ooter-0.178
anna-0.175
ilda-0.170
lee-0.165
Token.
Token ID13
Feature activation+4.41e-03

Pos logit contributions
nam+0.044
ooter+0.041
anna+0.041
ilda+0.040
lee+0.039
Neg logit contributions
aw-0.049
Run-0.048
oc-0.043
 horror-0.043
Is-0.040
Token
Token ID198
Feature activation-3.09e-01

Pos logit contributions
nam+0.000
anna+0.000
inations+0.000
ooter+0.000
ilda+0.000
Neg logit contributions
aw-0.000
Run-0.000
 horror-0.000
oc-0.000
Is-0.000
Token
Token ID198
Feature activation-3.03e-01

Pos logit contributions
aw+0.014
Run+0.014
oc+0.012
Is+0.012
 horror+0.011
Neg logit contributions
nam-0.021
ooter-0.019
anna-0.018
nie-0.018
 handsome-0.018
TokenKay
Token ID37247
Feature activation+3.45e+00

Pos logit contributions
aw+0.015
Run+0.015
oc+0.013
 horror+0.013
Is+0.012
Neg logit contributions
nam-0.018
ooter-0.017
anna-0.017
ilda-0.017
lee-0.016
Tokenlee
Token ID7197
Feature activation+1.09e+01

Pos logit contributions
nam+0.148
 handsome+0.117
ooter+0.117
inations+0.112
anna+0.109
Neg logit contributions
aw-0.262
Run-0.235
oc-0.219
 horror-0.207
Is-0.205
Token was
Token ID373
Feature activation-1.89e+00

Pos logit contributions
nam+0.532
anna+0.520
ooter+0.504
lee+0.502
ilda+0.498
Neg logit contributions
Run-0.617
aw-0.604
 horror-0.567
oc-0.555
Is-0.526
Token excited
Token ID6568
Feature activation+3.93e-01

Pos logit contributions
aw+0.124
Run+0.118
 horror+0.112
oc+0.102
Is+0.099
Neg logit contributions
nam-0.087
ooter-0.080
ilda-0.078
anna-0.077
ooters-0.075
Token and
Token ID290
Feature activation-9.58e-02

Pos logit contributions
nam+0.023
ooter+0.021
aj+0.020
anna+0.019
ouses+0.019
Neg logit contributions
aw-0.022
Run-0.020
 horror-0.018
oc-0.017
 disaster-0.016
Token said
Token ID531
Feature activation+1.52e-01

Pos logit contributions
aw+0.005
Run+0.005
 horror+0.004
oc+0.004
Is+0.004
Neg logit contributions
nam-0.005
ooter-0.005
ilda-0.005
aj-0.005
anna-0.005
Token,
Token ID11
Feature activation-3.82e-02

Pos logit contributions
nam+0.008
ilda+0.008
ooter+0.007
anna+0.007
aj+0.007
Neg logit contributions
aw-0.009
Run-0.008
 horror-0.007
Is-0.007
oc-0.007
Token and
Token ID290
Feature activation+5.67e-02

Pos logit contributions
nam+0.002
ooter+0.002
anna+0.002
ilda+0.002
lee+0.002
Neg logit contributions
aw-0.002
Run-0.002
oc-0.002
 horror-0.002
Is-0.002
Token qu
Token ID627
Feature activation+2.35e+00

Pos logit contributions
ooter+0.003
anna+0.003
nam+0.003
ilda+0.003
ooters+0.003
Neg logit contributions
Run-0.003
aw-0.003
oc-0.003
 horror-0.003
Is-0.002
Tokenacked
Token ID6021
Feature activation+3.80e-02

Pos logit contributions
nam+0.173
ooter+0.157
ilda+0.152
anna+0.150
 handsome+0.147
Neg logit contributions
aw-0.102
Run-0.089
oc-0.081
 horror-0.073
Is-0.065
Token with
Token ID351
Feature activation-9.58e-01

Pos logit contributions
nam+0.002
ooter+0.002
anna+0.002
lee+0.002
ilda+0.002
Neg logit contributions
aw-0.002
Run-0.002
oc-0.002
 horror-0.002
Is-0.002
Token g
Token ID308
Feature activation+1.89e-01

Pos logit contributions
aw+0.056
Run+0.054
 horror+0.049
oc+0.049
Is+0.045
Neg logit contributions
nam-0.050
ooter-0.047
anna-0.047
ilda-0.046
lee-0.044
Tokenlee
Token ID7197
Feature activation+1.09e+01

Pos logit contributions
nam+0.007
ooter+0.004
ilda+0.004
nie+0.004
ppa+0.004
Neg logit contributions
aw-0.017
 horror-0.014
Run-0.014
oc-0.013
der-0.012
Token.
Token ID13
Feature activation+7.21e-02

Pos logit contributions
nam+0.640
ooter+0.582
anna+0.564
 handsome+0.558
ilda+0.556
Neg logit contributions
aw-0.589
Run-0.524
oc-0.494
 horror-0.458
cer-0.385
Token He
Token ID679
Feature activation-6.54e-01

Pos logit contributions
nam+0.005
ilda+0.004
anna+0.004
ooter+0.004
inations+0.004
Neg logit contributions
aw-0.003
Run-0.003
 horror-0.003
oc-0.003
Is-0.003
Token opened
Token ID4721
Feature activation+1.37e+00

Pos logit contributions
aw+0.039
Run+0.038
oc+0.034
 horror+0.033
Is+0.031
Neg logit contributions
nam-0.034
ooter-0.032
anna-0.030
ilda-0.030
ooters-0.029
Token the
Token ID262
Feature activation+8.57e-01

Pos logit contributions
nam+0.084
ooter+0.080
anna+0.079
ilda+0.076
lee+0.073
Neg logit contributions
aw-0.067
Run-0.064
 horror-0.057
oc-0.057
Is-0.052
Token basket
Token ID7988
Feature activation-2.79e-01

Pos logit contributions
nam+0.047
anna+0.046
ilda+0.044
ooter+0.043
lee+0.043
Neg logit contributions
aw-0.047
Run-0.045
 horror-0.041
oc-0.039
Is-0.037
Token two
Token ID734
Feature activation-1.46e+00

Pos logit contributions
nam+0.002
anna+0.002
ooter+0.002
ilda+0.002
lee+0.002
Neg logit contributions
aw-0.002
Run-0.002
oc-0.002
 horror-0.002
Is-0.002
Token friends
Token ID2460
Feature activation+2.60e+00

Pos logit contributions
aw+0.092
Run+0.090
oc+0.081
 horror+0.081
Is+0.075
Neg logit contributions
nam-0.070
ooter-0.064
anna-0.063
ilda-0.062
lee-0.060
Token laughed
Token ID13818
Feature activation+1.06e+00

Pos logit contributions
nam+0.149
ooter+0.138
ilda+0.132
anna+0.132
aj+0.131
Neg logit contributions
aw-0.143
Run-0.137
oc-0.123
 horror-0.121
Is-0.107
Token with
Token ID351
Feature activation-8.07e-01

Pos logit contributions
nam+0.061
anna+0.057
ooter+0.056
lee+0.055
ilda+0.055
Neg logit contributions
aw-0.055
Run-0.054
oc-0.048
 horror-0.048
Is-0.044
Token g
Token ID308
Feature activation+2.92e-01

Pos logit contributions
aw+0.047
Run+0.047
oc+0.043
 horror+0.041
Is+0.040
Neg logit contributions
nam-0.041
lee-0.037
anna-0.036
 Jackie-0.036
ooter-0.036
Tokenlee
Token ID7197
Feature activation+1.09e+01

Pos logit contributions
nam+0.013
ooter+0.009
ilda+0.009
 Emmy+0.008
ppa+0.008
Neg logit contributions
aw-0.023
oc-0.020
Run-0.020
 horror-0.019
Too-0.017
Token.
Token ID13
Feature activation+5.57e-02

Pos logit contributions
nam+0.642
ooter+0.588
anna+0.576
ilda+0.566
lee+0.555
Neg logit contributions
aw-0.572
Run-0.544
oc-0.490
 horror-0.473
Is-0.424
Token They
Token ID1119
Feature activation-1.15e+00

Pos logit contributions
nam+0.003
ooter+0.003
ilda+0.003
anna+0.003
 handsome+0.003
Neg logit contributions
aw-0.003
Run-0.003
oc-0.002
 horror-0.002
Is-0.002
Token had
Token ID550
Feature activation+2.34e+00

Pos logit contributions
aw+0.066
Run+0.064
oc+0.057
 horror+0.055
Is+0.050
Neg logit contributions
nam-0.061
ooter-0.061
anna-0.057
ilda-0.056
aj-0.056
Token found
Token ID1043
Feature activation+1.77e+00

Pos logit contributions
nam+0.125
ooter+0.119
anna+0.113
ilda+0.110
ooters+0.105
Neg logit contributions
aw-0.144
Run-0.129
 horror-0.118
oc-0.114
Is-0.107
Token a
Token ID257
Feature activation+7.25e-02

Pos logit contributions
nam+0.090
ooter+0.080
 Jackie+0.079
lee+0.079
ilda+0.078
Neg logit contributions
Run-0.104
aw-0.100
 horror-0.091
oc-0.091
Is-0.087
Token
Token ID198
Feature activation-1.65e-01

Pos logit contributions
Run+0.006
aw+0.006
oc+0.005
Is+0.005
 horror+0.005
Neg logit contributions
nam-0.009
ooter-0.008
anna-0.007
 handsome-0.007
ilda-0.007
TokenSarah
Token ID29284
Feature activation+3.10e+00

Pos logit contributions
aw+0.008
Run+0.008
oc+0.007
 horror+0.007
Is+0.006
Neg logit contributions
nam-0.010
ooter-0.010
anna-0.010
ilda-0.009
lee-0.009
Token smiled
Token ID13541
Feature activation+1.20e+00

Pos logit contributions
nam+0.166
ooter+0.154
anna+0.153
ilda+0.149
lee+0.146
Neg logit contributions
aw-0.174
Run-0.171
oc-0.153
 horror-0.152
Is-0.140
Token with
Token ID351
Feature activation-9.72e-01

Pos logit contributions
nam+0.071
ooter+0.065
anna+0.065
ilda+0.063
lee+0.063
Neg logit contributions
aw-0.062
Run-0.061
oc-0.054
 horror-0.053
Is-0.049
Token g
Token ID308
Feature activation+2.18e-01

Pos logit contributions
aw+0.064
Run+0.063
oc+0.058
 horror+0.057
Is+0.054
Neg logit contributions
nam-0.043
ooter-0.039
anna-0.038
ilda-0.037
lee-0.037
Tokenlee
Token ID7197
Feature activation+1.09e+01

Pos logit contributions
nam+0.007
ooter+0.004
ilda+0.004
 Emmy+0.003
ppa+0.003
Neg logit contributions
aw-0.020
 horror-0.017
Run-0.017
oc-0.016
Ble-0.015
Token,
Token ID11
Feature activation+1.25e-01

Pos logit contributions
nam+0.646
ooter+0.584
anna+0.571
ilda+0.554
 handsome+0.553
Neg logit contributions
aw-0.577
Run-0.537
oc-0.482
 horror-0.470
Is-0.410
Token and
Token ID290
Feature activation+1.68e-01

Pos logit contributions
nam+0.007
ooter+0.007
anna+0.006
ilda+0.006
ooters+0.006
Neg logit contributions
aw-0.007
Run-0.007
 horror-0.006
oc-0.006
Is-0.006
Token started
Token ID2067
Feature activation-6.10e-01

Pos logit contributions
nam+0.009
anna+0.008
ooter+0.008
ilda+0.008
lee+0.007
Neg logit contributions
aw-0.010
Run-0.010
oc-0.009
 horror-0.009
Is-0.008
Token to
Token ID284
Feature activation+6.36e-01

Pos logit contributions
aw+0.038
Run+0.036
 horror+0.035
oc+0.033
Is+0.032
Neg logit contributions
nam-0.028
anna-0.026
ooter-0.026
ilda-0.024
inations-0.024
Token wonder
Token ID4240
Feature activation-3.89e-01

Pos logit contributions
nam+0.030
anna+0.029
ooter+0.028
ilda+0.027
lee+0.026
Neg logit contributions
Run-0.039
aw-0.038
 horror-0.036
oc-0.035
Is-0.032
Token and
Token ID290
Feature activation-8.42e-02

Pos logit contributions
nam+0.052
 Jackie+0.047
anna+0.047
lee+0.047
 handsome+0.047
Neg logit contributions
Run-0.057
aw-0.057
oc-0.053
 horror-0.051
Is-0.049
Token gigg
Token ID30442
Feature activation+2.77e+00

Pos logit contributions
aw+0.005
Run+0.005
 horror+0.005
oc+0.005
Is+0.004
Neg logit contributions
nam-0.004
ooter-0.004
anna-0.004
ilda-0.004
lee-0.003
Tokenled
Token ID992
Feature activation-6.95e-01

Pos logit contributions
nam+0.162
ooter+0.154
ilda+0.146
anna+0.145
 Jackie+0.141
Neg logit contributions
aw-0.151
Run-0.142
oc-0.124
 horror-0.121
Is-0.110
Token with
Token ID351
Feature activation-1.20e+00

Pos logit contributions
aw+0.043
Run+0.043
oc+0.039
 horror+0.038
Is+0.037
Neg logit contributions
nam-0.033
lee-0.029
anna-0.029
 Jackie-0.029
ooter-0.028
Token g
Token ID308
Feature activation+9.78e-02

Pos logit contributions
aw+0.081
Run+0.080
oc+0.074
Is+0.070
 horror+0.069
Neg logit contributions
nam-0.051
lee-0.046
 Jackie-0.044
 Emmy-0.043
 handsome-0.043
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.003
ooter+0.002
ilda+0.002
ppa+0.002
nie+0.002
Neg logit contributions
aw-0.009
 horror-0.007
Run-0.007
oc-0.007
der-0.007
Token.
Token ID13
Feature activation+8.21e-02

Pos logit contributions
nam+0.626
ooter+0.565
anna+0.555
 Jackie+0.538
ilda+0.537
Neg logit contributions
aw-0.595
Run-0.545
oc-0.508
 horror-0.488
Is-0.417
Token They
Token ID1119
Feature activation-1.34e+00

Pos logit contributions
nam+0.006
ooter+0.005
anna+0.005
ilda+0.005
lee+0.005
Neg logit contributions
aw-0.004
Run-0.003
 horror-0.003
oc-0.003
Is-0.003
Token loved
Token ID6151
Feature activation+1.45e+00

Pos logit contributions
aw+0.076
Run+0.073
 horror+0.065
oc+0.064
Is+0.057
Neg logit contributions
ooter-0.070
anna-0.070
nam-0.069
aj-0.066
ilda-0.064
Token their
Token ID511
Feature activation-2.00e+00

Pos logit contributions
nam+0.081
ooter+0.081
anna+0.079
aj+0.075
ilda+0.074
Neg logit contributions
aw-0.076
Run-0.073
 horror-0.068
oc-0.065
Is-0.061
Token new
Token ID649
Feature activation-1.52e+00

Pos logit contributions
aw+0.129
 horror+0.128
Run+0.128
oc+0.122
Is+0.109
Neg logit contributions
nam-0.085
anna-0.080
ppa-0.074
ooter-0.074
ilda-0.072
Token jumped
Token ID11687
Feature activation-7.99e-01

Pos logit contributions
aw+0.071
Run+0.070
 horror+0.064
oc+0.063
Is+0.058
Neg logit contributions
nam-0.060
anna-0.056
ooter-0.055
lee-0.054
ilda-0.054
Token and
Token ID290
Feature activation+6.03e-02

Pos logit contributions
aw+0.044
Run+0.042
 horror+0.037
oc+0.036
Is+0.033
Neg logit contributions
nam-0.047
anna-0.042
ooter-0.042
ilda-0.042
lee-0.040
Token laughed
Token ID13818
Feature activation+1.03e+00

Pos logit contributions
nam+0.003
ooter+0.003
ilda+0.003
anna+0.003
aj+0.003
Neg logit contributions
Run-0.003
aw-0.003
oc-0.003
 horror-0.003
Is-0.002
Token with
Token ID351
Feature activation-1.13e+00

Pos logit contributions
nam+0.053
ooter+0.049
anna+0.049
ilda+0.047
lee+0.047
Neg logit contributions
aw-0.059
Run-0.058
oc-0.053
 horror-0.052
Is-0.048
Token g
Token ID308
Feature activation+1.68e-01

Pos logit contributions
aw+0.075
Run+0.074
oc+0.067
 horror+0.065
Is+0.064
Neg logit contributions
nam-0.050
ooter-0.044
lee-0.043
anna-0.043
 Jackie-0.042
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.006
ooter+0.004
ilda+0.004
 Emmy+0.004
ppa+0.004
Neg logit contributions
aw-0.015
Run-0.012
 horror-0.012
oc-0.012
der-0.011
Token.
Token ID13
Feature activation+3.55e-02

Pos logit contributions
nam+0.642
ooter+0.580
anna+0.564
 Jackie+0.555
ilda+0.554
Neg logit contributions
aw-0.587
Run-0.528
oc-0.492
 horror-0.463
Is-0.395
Token
Token ID198
Feature activation-2.28e-01

Pos logit contributions
nam+0.002
ooter+0.002
ilda+0.002
inations+0.002
ppa+0.002
Neg logit contributions
aw-0.002
Run-0.002
oc-0.002
 horror-0.001
Is-0.001
Token
Token ID198
Feature activation-2.35e-01

Pos logit contributions
aw+0.010
Run+0.010
oc+0.009
Is+0.008
 horror+0.008
Neg logit contributions
nam-0.016
ooter-0.014
anna-0.013
lee-0.013
ilda-0.013
TokenAs
Token ID1722
Feature activation-1.54e+00

Pos logit contributions
aw+0.011
Run+0.010
 horror+0.009
oc+0.009
Is+0.008
Neg logit contributions
nam-0.015
ooter-0.014
anna-0.014
ilda-0.014
lee-0.014
Token he
Token ID339
Feature activation-1.33e+00

Pos logit contributions
aw+0.107
Run+0.101
oc+0.096
 horror+0.094
Ble+0.090
Neg logit contributions
nam-0.062
 Jackie-0.059
 Emmy-0.053
 handsome-0.051
 upon-0.050
TokenThe
Token ID464
Feature activation-8.39e-01

Pos logit contributions
aw+0.012
Run+0.012
oc+0.010
 horror+0.010
Is+0.009
Neg logit contributions
nam-0.018
ooter-0.017
anna-0.017
ilda-0.017
lee-0.016
Token princess
Token ID21752
Feature activation+3.66e-01

Pos logit contributions
Run+0.047
aw+0.046
 horror+0.041
oc+0.040
Is+0.038
Neg logit contributions
nam-0.045
anna-0.043
ooter-0.043
ilda-0.042
ooters-0.040
Token laughed
Token ID13818
Feature activation+1.01e+00

Pos logit contributions
nam+0.022
ooter+0.020
anna+0.019
ilda+0.019
 Jackie+0.019
Neg logit contributions
aw-0.019
Run-0.018
oc-0.017
 horror-0.016
Is-0.015
Token with
Token ID351
Feature activation-9.77e-01

Pos logit contributions
nam+0.059
ooter+0.055
anna+0.055
ilda+0.053
lee+0.053
Neg logit contributions
aw-0.051
Run-0.051
oc-0.045
 horror-0.044
Is-0.041
Token g
Token ID308
Feature activation+2.06e-01

Pos logit contributions
aw+0.061
Run+0.060
oc+0.056
 horror+0.052
Is+0.051
Neg logit contributions
nam-0.047
lee-0.041
anna-0.041
 Jackie-0.041
ooter-0.041
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.006
ooter+0.004
ilda+0.004
ppa+0.003
nie+0.003
Neg logit contributions
aw-0.019
Run-0.016
 horror-0.016
oc-0.015
der-0.014
Token.
Token ID13
Feature activation+2.15e-01

Pos logit contributions
nam+0.658
ooter+0.600
anna+0.581
ilda+0.571
 handsome+0.566
Neg logit contributions
aw-0.567
Run-0.526
oc-0.469
 horror-0.451
Is-0.394
Token She
Token ID1375
Feature activation+1.30e+00

Pos logit contributions
nam+0.013
inations+0.012
ppa+0.012
ooter+0.012
ilda+0.012
Neg logit contributions
aw-0.011
Run-0.010
 horror-0.009
Is-0.009
oc-0.008
Token pointed
Token ID6235
Feature activation-1.33e+00

Pos logit contributions
nam+0.072
ooter+0.067
ilda+0.064
anna+0.064
ooters+0.061
Neg logit contributions
aw-0.075
Run-0.071
oc-0.064
 horror-0.061
Is-0.058
Token and
Token ID290
Feature activation+3.98e-01

Pos logit contributions
aw+0.080
Run+0.073
 horror+0.068
oc+0.062
Is+0.060
Neg logit contributions
nam-0.071
ooter-0.067
ilda-0.066
anna-0.065
inations-0.063
Token pointed
Token ID6235
Feature activation-1.30e+00

Pos logit contributions
ooter+0.023
anna+0.022
nam+0.021
ilda+0.021
ooters+0.020
Neg logit contributions
Run-0.022
aw-0.021
 horror-0.018
oc-0.017
Is-0.017
Token and
Token ID290
Feature activation-9.86e-02

Pos logit contributions
nam+0.018
ooter+0.017
anna+0.017
ilda+0.016
lee+0.016
Neg logit contributions
aw-0.017
Run-0.016
oc-0.014
 horror-0.014
Is-0.013
Token spark
Token ID9009
Feature activation+2.28e+00

Pos logit contributions
aw+0.006
Run+0.006
oc+0.005
 horror+0.005
Is+0.005
Neg logit contributions
nam-0.005
 Jackie-0.004
ilda-0.004
lee-0.004
 Emmy-0.004
Tokenled
Token ID992
Feature activation-5.96e-01

Pos logit contributions
anna+0.093
nam+0.091
lee+0.086
ilda+0.085
ooter+0.082
Neg logit contributions
Run-0.149
 horror-0.142
aw-0.139
oc-0.135
Is-0.133
Token with
Token ID351
Feature activation-1.02e+00

Pos logit contributions
Run+0.037
aw+0.037
oc+0.034
 horror+0.033
Is+0.032
Neg logit contributions
nam-0.028
 Jackie-0.024
lee-0.024
ooter-0.024
anna-0.024
Token g
Token ID308
Feature activation+1.89e-01

Pos logit contributions
aw+0.065
Run+0.065
oc+0.059
 horror+0.057
Is+0.055
Neg logit contributions
nam-0.047
ooter-0.041
anna-0.041
lee-0.041
ilda-0.040
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.006
ooter+0.004
ilda+0.004
ppa+0.003
 Emmy+0.003
Neg logit contributions
aw-0.017
 horror-0.014
Run-0.014
oc-0.014
der-0.013
Token.
Token ID13
Feature activation+9.45e-02

Pos logit contributions
nam+0.636
ooter+0.573
anna+0.559
 Jackie+0.547
ilda+0.546
Neg logit contributions
aw-0.593
Run-0.533
oc-0.504
 horror-0.472
Is-0.397
Token From
Token ID3574
Feature activation+1.47e+00

Pos logit contributions
nam+0.006
ooter+0.005
anna+0.005
ilda+0.005
lee+0.005
Neg logit contributions
aw-0.005
Run-0.005
oc-0.004
 horror-0.004
Is-0.004
Token then
Token ID788
Feature activation-2.63e+00

Pos logit contributions
nam+0.097
ooter+0.090
anna+0.089
ilda+0.088
lee+0.088
Neg logit contributions
aw-0.064
Run-0.063
oc-0.057
 horror-0.056
Is-0.050
Token on
Token ID319
Feature activation+8.96e-01

Pos logit contributions
aw+0.183
Run+0.176
 horror+0.166
oc+0.160
Bad+0.151
Neg logit contributions
ooter-0.095
nam-0.093
anna-0.088
ilda-0.087
 Jackie-0.082
Token,
Token ID11
Feature activation+1.78e-02

Pos logit contributions
nam+0.038
 Jackie+0.036
lee+0.035
anna+0.035
 Emmy+0.035
Neg logit contributions
aw-0.059
Run-0.058
oc-0.053
 horror-0.052
Is-0.050
Token to
Token ID284
Feature activation+4.56e-01

Pos logit contributions
aw+0.049
Run+0.047
 horror+0.044
oc+0.041
Is+0.040
Neg logit contributions
nam-0.034
ooter-0.031
anna-0.029
aj-0.028
ilda-0.028
Token dance
Token ID9280
Feature activation+3.10e-01

Pos logit contributions
nam+0.026
ooter+0.024
ilda+0.023
anna+0.023
aj+0.023
Neg logit contributions
Run-0.024
aw-0.024
 horror-0.022
oc-0.021
Is-0.019
Token around
Token ID1088
Feature activation+2.06e+00

Pos logit contributions
nam+0.018
ooter+0.016
anna+0.016
ilda+0.015
lee+0.015
Neg logit contributions
aw-0.017
Run-0.016
oc-0.014
 horror-0.014
Is-0.013
Token in
Token ID287
Feature activation+1.55e+00

Pos logit contributions
nam+0.113
ooter+0.105
anna+0.104
ilda+0.101
lee+0.100
Neg logit contributions
aw-0.113
Run-0.111
oc-0.099
 horror-0.099
Is-0.091
Token g
Token ID308
Feature activation+1.56e-01

Pos logit contributions
nam+0.084
ooter+0.075
anna+0.074
lee+0.074
 Jackie+0.074
Neg logit contributions
aw-0.089
Run-0.086
oc-0.078
 horror-0.074
Is-0.070
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.005
ooter+0.003
ilda+0.003
 Emmy+0.003
ppa+0.003
Neg logit contributions
aw-0.014
Run-0.012
 horror-0.012
oc-0.012
Is-0.011
Token!
Token ID0
Feature activation-9.04e-01

Pos logit contributions
nam+0.637
ooter+0.586
anna+0.560
 Jackie+0.553
 handsome+0.553
Neg logit contributions
aw-0.590
Run-0.526
oc-0.484
 horror-0.460
Is-0.395
Token The
Token ID383
Feature activation+1.19e-01

Pos logit contributions
aw+0.048
Run+0.047
oc+0.042
 horror+0.041
Is+0.038
Neg logit contributions
nam-0.053
anna-0.048
ilda-0.047
ooter-0.047
inations-0.046
Token little
Token ID1310
Feature activation+1.21e+00

Pos logit contributions
nam+0.005
ooter+0.005
anna+0.005
ilda+0.005
lee+0.005
Neg logit contributions
aw-0.008
Run-0.007
oc-0.007
 horror-0.007
Is-0.006
Token girl
Token ID2576
Feature activation-9.79e-01

Pos logit contributions
nam+0.056
ooter+0.051
anna+0.050
 Jackie+0.050
nie+0.048
Neg logit contributions
aw-0.076
Run-0.072
oc-0.070
 horror-0.068
Is-0.065
Token was
Token ID373
Feature activation-1.86e+00

Pos logit contributions
aw+0.055
Run+0.051
oc+0.046
 horror+0.045
Is+0.042
Neg logit contributions
nam-0.057
ooter-0.052
ilda-0.049
anna-0.048
ooters-0.047
Token danced
Token ID39480
Feature activation+2.60e+00

Pos logit contributions
nam+0.008
ooter+0.007
anna+0.007
ilda+0.007
aj+0.007
Neg logit contributions
aw-0.008
Run-0.008
 horror-0.007
oc-0.007
Is-0.006
Token and
Token ID290
Feature activation+4.18e-02

Pos logit contributions
nam+0.161
ooter+0.149
anna+0.146
ilda+0.143
lee+0.138
Neg logit contributions
aw-0.133
Run-0.123
oc-0.109
 horror-0.108
Is-0.095
Token shouted
Token ID17293
Feature activation+3.34e-02

Pos logit contributions
ooter+0.002
nam+0.002
anna+0.002
ilda+0.002
aj+0.002
Neg logit contributions
aw-0.002
Run-0.002
oc-0.002
 horror-0.002
Is-0.002
Token with
Token ID351
Feature activation-1.02e+00

Pos logit contributions
nam+0.002
ooter+0.002
anna+0.002
ilda+0.002
ppa+0.002
Neg logit contributions
aw-0.002
Run-0.002
 horror-0.001
oc-0.001
Is-0.001
Token g
Token ID308
Feature activation+1.60e-01

Pos logit contributions
Run+0.068
aw+0.068
oc+0.063
 horror+0.059
Is+0.059
Neg logit contributions
nam-0.043
lee-0.037
 Jackie-0.037
anna-0.037
ooter-0.036
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.007
ooter+0.005
ilda+0.004
ppa+0.004
ety+0.004
Neg logit contributions
aw-0.013
 horror-0.011
Run-0.011
oc-0.010
der-0.010
Token.
Token ID13
Feature activation+3.02e-01

Pos logit contributions
nam+0.656
ooter+0.582
 handsome+0.565
anna+0.565
inations+0.561
Neg logit contributions
aw-0.574
Run-0.502
oc-0.469
 horror-0.437
cer-0.374
Token
Token ID220
Feature activation+4.88e+00

Pos logit contributions
nam+0.018
ooter+0.017
ilda+0.017
anna+0.016
 handsome+0.016
Neg logit contributions
aw-0.015
Run-0.015
 horror-0.013
oc-0.013
Is-0.012
Token
Token ID198
Feature activation-6.21e-02

Pos logit contributions
nam+0.347
ooter+0.300
 handsome+0.298
anna+0.297
 blank+0.292
Neg logit contributions
aw-0.221
Run-0.192
oc-0.173
 horror-0.166
Is-0.158
Token
Token ID198
Feature activation-9.02e-02

Pos logit contributions
aw+0.003
Run+0.003
oc+0.003
Is+0.003
 horror+0.003
Neg logit contributions
nam-0.004
ooter-0.004
anna-0.003
ilda-0.003
lee-0.003
TokenJack
Token ID14295
Feature activation+2.06e-02

Pos logit contributions
aw+0.004
Run+0.004
 horror+0.004
oc+0.004
Is+0.003
Neg logit contributions
nam-0.005
anna-0.005
ooter-0.005
ilda-0.005
 Jackie-0.005
Token started
Token ID2067
Feature activation-7.17e-01

Pos logit contributions
aw+0.010
Run+0.010
oc+0.009
 horror+0.009
Is+0.008
Neg logit contributions
nam-0.009
ooter-0.009
anna-0.009
ilda-0.008
ooters-0.008
Token to
Token ID284
Feature activation+4.78e-01

Pos logit contributions
aw+0.047
Run+0.047
 horror+0.043
oc+0.041
Is+0.040
Neg logit contributions
nam-0.031
anna-0.029
ooter-0.029
ilda-0.028
nie-0.027
Token chase
Token ID15505
Feature activation-1.74e+00

Pos logit contributions
nam+0.025
anna+0.024
ooter+0.024
ilda+0.023
lee+0.022
Neg logit contributions
Run-0.028
aw-0.027
 horror-0.025
oc-0.025
Is-0.023
Token after
Token ID706
Feature activation-4.32e+00

Pos logit contributions
aw+0.094
Run+0.093
 horror+0.084
oc+0.084
Is+0.079
Neg logit contributions
nam-0.094
anna-0.086
ooter-0.085
lee-0.085
 Jackie-0.082
Token Kay
Token ID17356
Feature activation+3.53e+00

Pos logit contributions
aw+0.240
Run+0.235
 horror+0.205
oc+0.202
Is+0.189
Neg logit contributions
nam-0.238
ooter-0.224
anna-0.223
ilda-0.214
aj-0.211
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.193
 handsome+0.161
inations+0.158
 blank+0.152
nie+0.151
Neg logit contributions
aw-0.236
Run-0.194
oc-0.179
 horror-0.168
Is-0.159
Token.
Token ID13
Feature activation+8.75e-04

Pos logit contributions
nam+0.606
ooter+0.547
anna+0.544
ilda+0.530
 Jackie+0.521
Neg logit contributions
aw-0.610
Run-0.580
oc-0.521
 horror-0.509
Is-0.456
Token She
Token ID1375
Feature activation+1.10e+00

Pos logit contributions
nam+0.000
anna+0.000
inations+0.000
ilda+0.000
aj+0.000
Neg logit contributions
aw-0.000
Run-0.000
 horror-0.000
oc-0.000
Is-0.000
Token screamed
Token ID25421
Feature activation-1.95e+00

Pos logit contributions
nam+0.056
anna+0.052
ooter+0.052
lee+0.050
ilda+0.050
Neg logit contributions
aw-0.063
Run-0.062
 horror-0.056
oc-0.056
Is-0.052
Token and
Token ID290
Feature activation-2.15e-01

Pos logit contributions
aw+0.106
Run+0.104
oc+0.093
 horror+0.092
Is+0.085
Neg logit contributions
nam-0.108
ooter-0.100
anna-0.099
ilda-0.097
lee-0.095
Token ran
Token ID4966
Feature activation+8.37e-01

Pos logit contributions
aw+0.012
Run+0.012
oc+0.011
 horror+0.011
Is+0.010
Neg logit contributions
nam-0.011
ooter-0.010
anna-0.010
ilda-0.010
lee-0.010
Token the
Token ID262
Feature activation+6.47e-01

Pos logit contributions
aw+0.016
Run+0.016
oc+0.014
 horror+0.014
Is+0.013
Neg logit contributions
nam-0.018
anna-0.016
ooter-0.016
ilda-0.016
lee-0.016
Token girl
Token ID2576
Feature activation-9.54e-01

Pos logit contributions
nam+0.032
anna+0.030
ooter+0.030
ilda+0.029
lee+0.028
Neg logit contributions
aw-0.039
Run-0.038
 horror-0.035
oc-0.035
Is-0.032
Token laughed
Token ID13818
Feature activation+1.01e+00

Pos logit contributions
aw+0.055
Run+0.051
oc+0.049
 horror+0.048
Is+0.042
Neg logit contributions
nam-0.052
ooter-0.047
anna-0.046
ilda-0.045
 handsome-0.044
Token with
Token ID351
Feature activation-1.18e+00

Pos logit contributions
nam+0.052
anna+0.046
ooter+0.046
 Jackie+0.046
lee+0.046
Neg logit contributions
aw-0.059
Run-0.059
oc-0.053
 horror-0.052
Is-0.049
Token g
Token ID308
Feature activation+1.40e-01

Pos logit contributions
aw+0.076
Run+0.076
oc+0.072
Is+0.067
 horror+0.063
Neg logit contributions
nam-0.053
lee-0.047
 Jackie-0.046
 Emmy-0.045
 handsome-0.044
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.005
ooter+0.003
ilda+0.003
 Emmy+0.003
 handsome+0.003
Neg logit contributions
aw-0.012
 horror-0.011
Run-0.010
oc-0.010
Ble-0.009
Token.
Token ID13
Feature activation-4.67e-02

Pos logit contributions
nam+0.623
ooter+0.558
anna+0.545
 handsome+0.533
ilda+0.530
Neg logit contributions
aw-0.598
Run-0.552
oc-0.506
 horror-0.492
Is-0.420
Token The
Token ID383
Feature activation+1.93e-01

Pos logit contributions
aw+0.003
Run+0.003
 horror+0.002
oc+0.002
Is+0.002
Neg logit contributions
nam-0.003
ooter-0.002
anna-0.002
ilda-0.002
 handsome-0.002
Token cookies
Token ID14746
Feature activation-1.24e+00

Pos logit contributions
nam+0.009
ooter+0.009
anna+0.009
ilda+0.008
lee+0.008
Neg logit contributions
aw-0.012
Run-0.012
oc-0.011
 horror-0.011
Is-0.010
Token were
Token ID547
Feature activation-1.42e+00

Pos logit contributions
aw+0.072
Run+0.069
oc+0.064
 horror+0.063
Is+0.059
Neg logit contributions
nam-0.064
anna-0.058
ooter-0.058
ilda-0.057
lee-0.056
Token delicious
Token ID12625
Feature activation-1.55e+00

Pos logit contributions
aw+0.091
Run+0.087
 horror+0.083
oc+0.078
Is+0.074
Neg logit contributions
nam-0.065
ooter-0.064
anna-0.062
ilda-0.059
ooters-0.057
Token from
Token ID422
Feature activation-8.58e-01

Pos logit contributions
aw+0.015
Run+0.015
 horror+0.013
oc+0.013
Is+0.011
Neg logit contributions
nam-0.018
ooter-0.017
anna-0.017
ilda-0.016
lee-0.016
Token her
Token ID607
Feature activation+2.25e+00

Pos logit contributions
aw+0.050
Run+0.049
oc+0.044
 horror+0.043
Is+0.041
Neg logit contributions
nam-0.045
ooter-0.041
anna-0.041
ilda-0.040
lee-0.039
Token,
Token ID11
Feature activation+1.15e-01

Pos logit contributions
nam+0.118
anna+0.112
ooter+0.109
ilda+0.109
 Jackie+0.104
Neg logit contributions
aw-0.128
Run-0.121
 horror-0.117
oc-0.113
Is-0.098
Token but
Token ID475
Feature activation-1.01e+00

Pos logit contributions
nam+0.006
ooter+0.006
anna+0.005
ilda+0.005
lee+0.005
Neg logit contributions
aw-0.007
Run-0.007
 horror-0.006
oc-0.006
Is-0.005
Token Kay
Token ID17356
Feature activation+3.59e+00

Pos logit contributions
aw+0.059
Run+0.057
oc+0.053
 horror+0.051
Is+0.047
Neg logit contributions
nam-0.055
 Jackie-0.047
anna-0.047
ilda-0.047
 Emmy-0.046
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.197
ooter+0.170
ooters+0.164
 handsome+0.163
inations+0.160
Neg logit contributions
aw-0.236
Run-0.197
oc-0.185
 horror-0.175
Is-0.169
Token was
Token ID373
Feature activation-1.79e+00

Pos logit contributions
nam+0.554
ooter+0.509
anna+0.503
ilda+0.489
lee+0.480
Neg logit contributions
aw-0.637
Run-0.622
oc-0.559
 horror-0.555
Is-0.515
Token determined
Token ID5295
Feature activation+9.72e-01

Pos logit contributions
aw+0.106
Run+0.101
 horror+0.094
Is+0.084
Bad+0.082
Neg logit contributions
nam-0.091
ooter-0.089
ilda-0.087
anna-0.085
ooters-0.083
Token to
Token ID284
Feature activation+6.34e-01

Pos logit contributions
nam+0.048
ooter+0.042
anna+0.041
ilda+0.040
aj+0.040
Neg logit contributions
aw-0.061
Run-0.057
 horror-0.053
oc-0.050
Is-0.049
Token catch
Token ID4929
Feature activation-2.99e+00

Pos logit contributions
nam+0.037
ooter+0.034
anna+0.034
ilda+0.033
lee+0.032
Neg logit contributions
aw-0.033
Run-0.033
oc-0.029
 horror-0.029
Is-0.027
Token it
Token ID340
Feature activation-3.82e-01

Pos logit contributions
Run+0.142
aw+0.142
oc+0.126
 horror+0.124
Is+0.113
Neg logit contributions
nam-0.185
ooter-0.169
anna-0.169
lee-0.166
ilda-0.166
Token her
Token ID607
Feature activation+2.06e+00

Pos logit contributions
aw+0.179
Run+0.177
oc+0.159
 horror+0.157
Is+0.146
Neg logit contributions
nam-0.171
ooter-0.157
anna-0.156
ilda-0.152
lee-0.151
Token.
Token ID13
Feature activation-1.48e-02

Pos logit contributions
nam+0.122
anna+0.111
ooter+0.110
ilda+0.109
lee+0.106
Neg logit contributions
aw-0.110
Run-0.102
oc-0.094
 horror-0.092
Is-0.082
Token
Token ID198
Feature activation-3.74e-01

Pos logit contributions
aw+0.001
Run+0.001
 horror+0.001
oc+0.001
Is+0.001
Neg logit contributions
nam-0.001
anna-0.001
ooter-0.001
ilda-0.001
inations-0.001
Token
Token ID198
Feature activation-3.76e-01

Pos logit contributions
aw+0.019
Run+0.018
oc+0.016
 horror+0.016
Is+0.015
Neg logit contributions
nam-0.024
anna-0.021
ooter-0.021
nie-0.021
ilda-0.020
TokenKay
Token ID37247
Feature activation+3.38e+00

Pos logit contributions
Run+0.023
aw+0.023
 horror+0.021
oc+0.021
Is+0.019
Neg logit contributions
nam-0.017
ooter-0.016
anna-0.016
lee-0.016
ilda-0.016
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.118
ooter+0.086
 handsome+0.086
inations+0.085
aj+0.081
Neg logit contributions
aw-0.280
Run-0.257
oc-0.240
 horror-0.233
Is-0.227
Token was
Token ID373
Feature activation-1.97e+00

Pos logit contributions
nam+0.521
anna+0.512
ooter+0.498
ilda+0.493
lee+0.489
Neg logit contributions
Run-0.618
aw-0.609
 horror-0.562
oc-0.555
Is-0.526
Token too
Token ID1165
Feature activation+1.78e+00

Pos logit contributions
aw+0.129
Run+0.123
 horror+0.116
oc+0.109
Is+0.104
Neg logit contributions
nam-0.092
ooter-0.083
anna-0.081
ilda-0.081
lee-0.077
Token scared
Token ID12008
Feature activation+7.52e-01

Pos logit contributions
nam+0.084
ooter+0.077
anna+0.074
ilda+0.073
lee+0.071
Neg logit contributions
aw-0.116
Run-0.115
oc-0.104
 horror-0.102
Is-0.094
Token to
Token ID284
Feature activation+4.30e-01

Pos logit contributions
nam+0.040
ooter+0.033
anna+0.032
aj+0.032
ouses+0.032
Neg logit contributions
aw-0.047
Run-0.044
 horror-0.041
oc-0.037
Is-0.036
Token move
Token ID1445
Feature activation-2.25e+00

Pos logit contributions
nam+0.025
anna+0.022
ilda+0.022
ooter+0.022
aj+0.022
Neg logit contributions
Run-0.023
aw-0.023
 horror-0.021
oc-0.020
Is-0.018
Token,
Token ID11
Feature activation+2.62e-01

Pos logit contributions
aw+0.020
Run+0.019
 horror+0.017
oc+0.017
Is+0.016
Neg logit contributions
nam-0.026
anna-0.024
ooter-0.023
lee-0.023
ilda-0.023
Token he
Token ID339
Feature activation-1.29e+00

Pos logit contributions
nam+0.016
anna+0.015
ooter+0.015
ilda+0.015
lee+0.014
Neg logit contributions
Run-0.013
aw-0.013
 horror-0.011
oc-0.011
Is-0.010
Token screamed
Token ID25421
Feature activation-2.03e+00

Pos logit contributions
aw+0.069
Run+0.064
oc+0.059
 horror+0.054
Is+0.054
Neg logit contributions
nam-0.074
ooter-0.073
ooters-0.069
anna-0.067
ilda-0.067
Token with
Token ID351
Feature activation-1.08e+00

Pos logit contributions
aw+0.117
Run+0.114
oc+0.103
 horror+0.102
Is+0.094
Neg logit contributions
nam-0.107
ooter-0.099
anna-0.098
ilda-0.096
lee-0.094
Token g
Token ID308
Feature activation+1.72e-01

Pos logit contributions
aw+0.065
Run+0.062
oc+0.057
 horror+0.054
Is+0.053
Neg logit contributions
nam-0.056
ooter-0.049
anna-0.048
lee-0.048
 Jackie-0.048
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.005
ooter+0.004
ilda+0.003
anna+0.003
 Emmy+0.003
Neg logit contributions
aw-0.015
Run-0.013
 horror-0.013
oc-0.012
 disaster-0.012
Token!
Token ID0
Feature activation-8.19e-01

Pos logit contributions
nam+0.609
anna+0.558
ooter+0.557
 handsome+0.537
inations+0.534
Neg logit contributions
aw-0.586
Run-0.545
oc-0.496
 horror-0.483
Is-0.415
Token
Token ID198
Feature activation-2.99e-01

Pos logit contributions
aw+0.035
Run+0.034
 horror+0.031
Is+0.029
oc+0.029
Neg logit contributions
nam-0.055
inations-0.051
ppa-0.051
anna-0.050
ooter-0.049
Token
Token ID198
Feature activation-3.12e-01

Pos logit contributions
aw+0.014
Run+0.013
oc+0.012
 horror+0.011
Is+0.011
Neg logit contributions
nam-0.020
ooter-0.018
anna-0.017
lee-0.017
ilda-0.017
Token"
Token ID1
Feature activation-7.11e-02

Pos logit contributions
aw+0.016
Run+0.016
 horror+0.014
oc+0.014
Is+0.012
Neg logit contributions
nam-0.018
anna-0.017
ooter-0.017
ilda-0.017
lee-0.017
TokenCan
Token ID6090
Feature activation-8.69e-01

Pos logit contributions
aw+0.004
oc+0.003
 horror+0.003
Run+0.003
 beast+0.002
Neg logit contributions
nam-0.005
 Jackie-0.004
 Emmy-0.004
any-0.004
 Grac-0.004
Token
Token ID198
Feature activation+1.03e-01

Pos logit contributions
nam+0.010
ooter+0.009
anna+0.009
lee+0.009
ilda+0.009
Neg logit contributions
aw-0.008
Run-0.007
oc-0.007
 horror-0.006
Is-0.006
TokenGeorge
Token ID20191
Feature activation+8.90e-01

Pos logit contributions
nam+0.006
anna+0.005
ilda+0.005
ooter+0.005
 Jackie+0.005
Neg logit contributions
aw-0.006
Run-0.005
 horror-0.005
oc-0.005
Is-0.004
Token yelled
Token ID22760
Feature activation+5.65e-01

Pos logit contributions
nam+0.056
ooter+0.049
ilda+0.046
ooters+0.046
 handsome+0.045
Neg logit contributions
aw-0.047
Run-0.044
oc-0.042
 horror-0.038
Is-0.035
Token with
Token ID351
Feature activation-1.04e+00

Pos logit contributions
nam+0.032
ooter+0.030
anna+0.029
ilda+0.029
lee+0.028
Neg logit contributions
aw-0.030
Run-0.030
 horror-0.027
oc-0.026
Is-0.024
Token g
Token ID308
Feature activation+1.65e-01

Pos logit contributions
aw+0.065
Run+0.063
oc+0.058
 horror+0.056
Is+0.053
Neg logit contributions
nam-0.050
ooter-0.045
anna-0.044
lee-0.044
ilda-0.043
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.005
ooter+0.003
ilda+0.003
 Emmy+0.003
ppa+0.003
Neg logit contributions
aw-0.015
 horror-0.013
Run-0.013
oc-0.012
der-0.011
Token and
Token ID290
Feature activation+2.31e-02

Pos logit contributions
nam+0.697
ooter+0.614
 handsome+0.602
inations+0.600
anna+0.600
Neg logit contributions
aw-0.522
Run-0.475
oc-0.440
 horror-0.417
Is-0.348
Token scrambled
Token ID34351
Feature activation-1.88e+00

Pos logit contributions
nam+0.001
ooter+0.001
anna+0.001
ilda+0.001
lee+0.001
Neg logit contributions
aw-0.001
Run-0.001
oc-0.001
 horror-0.001
Is-0.001
Token onto
Token ID4291
Feature activation-1.52e+00

Pos logit contributions
aw+0.112
Run+0.108
 horror+0.099
oc+0.097
Is+0.090
Neg logit contributions
nam-0.096
anna-0.085
ooter-0.084
ilda-0.082
inations-0.081
Token Cloud
Token ID10130
Feature activation+1.35e+00

Pos logit contributions
aw+0.090
Run+0.086
oc+0.078
 horror+0.075
Is+0.072
Neg logit contributions
nam-0.080
ooter-0.072
anna-0.071
ilda-0.070
 Jackie-0.070
Tokeny
Token ID88
Feature activation+1.68e+00

Pos logit contributions
nam+0.085
ooter+0.070
ilda+0.068
 handsome+0.068
 Emmy+0.066
Neg logit contributions
aw-0.075
Run-0.065
oc-0.063
 horror-0.057
Is-0.050
Token,
Token ID11
Feature activation+1.44e-01

Pos logit contributions
aw+0.185
Run+0.183
oc+0.165
 horror+0.163
Is+0.151
Neg logit contributions
nam-0.171
ooter-0.161
anna-0.158
ilda-0.154
lee-0.153
Token he
Token ID339
Feature activation-1.36e+00

Pos logit contributions
nam+0.008
 Jackie+0.007
 Emmy+0.007
ilda+0.007
 Grac+0.007
Neg logit contributions
aw-0.008
oc-0.008
Run-0.008
 horror-0.007
Is-0.007
Token shouted
Token ID17293
Feature activation-5.53e-02

Pos logit contributions
aw+0.080
Run+0.078
oc+0.070
 horror+0.069
Is+0.064
Neg logit contributions
nam-0.071
ooter-0.066
anna-0.065
ilda-0.063
lee-0.062
Token with
Token ID351
Feature activation-1.02e+00

Pos logit contributions
aw+0.003
Run+0.003
oc+0.003
 horror+0.003
Is+0.003
Neg logit contributions
nam-0.003
ooter-0.003
anna-0.003
ilda-0.002
lee-0.002
Token g
Token ID308
Feature activation+2.02e-01

Pos logit contributions
aw+0.067
Run+0.066
oc+0.062
Is+0.057
 horror+0.057
Neg logit contributions
nam-0.045
lee-0.038
 Jackie-0.038
 handsome-0.038
ooter-0.038
Tokenlee
Token ID7197
Feature activation+1.08e+01

Pos logit contributions
nam+0.005
ooter+0.003
ilda+0.003
 Emmy+0.003
any+0.003
Neg logit contributions
aw-0.019
Run-0.017
 horror-0.016
oc-0.016
 disaster-0.015
Token.
Token ID13
Feature activation+2.44e-01

Pos logit contributions
nam+0.624
ooter+0.559
anna+0.557
 handsome+0.539
inations+0.538
Neg logit contributions
aw-0.590
Run-0.545
oc-0.493
 horror-0.479
Is-0.421
Token
Token ID198
Feature activation-1.19e-01

Pos logit contributions
nam+0.015
anna+0.013
ooter+0.013
ilda+0.013
inations+0.013
Neg logit contributions
aw-0.013
Run-0.012
oc-0.011
 horror-0.011
Is-0.010
Token
Token ID198
Feature activation-1.52e-01

Pos logit contributions
aw+0.006
Run+0.006
oc+0.005
 horror+0.005
Is+0.005
Neg logit contributions
nam-0.007
ooter-0.007
anna-0.006
ilda-0.006
lee-0.006
TokenThe
Token ID464
Feature activation-8.62e-01

Pos logit contributions
aw+0.007
Run+0.007
 horror+0.006
oc+0.006
Is+0.005
Neg logit contributions
nam-0.010
ooter-0.009
anna-0.009
ilda-0.009
lee-0.009
Token other
Token ID584
Feature activation-4.10e+00

Pos logit contributions
aw+0.053
Run+0.053
 horror+0.046
oc+0.044
Is+0.042
Neg logit contributions
nam-0.042
anna-0.040
ooter-0.037
aj-0.037
ilda-0.037
Token them
Token ID606
Feature activation+3.20e+00

Pos logit contributions
aw+0.136
Run+0.134
 horror+0.121
oc+0.110
Bad+0.104
Neg logit contributions
ooter-0.149
nam-0.149
anna-0.147
ilda-0.141
aj-0.135
Token.
Token ID13
Feature activation-2.97e-01

Pos logit contributions
nam+0.207
anna+0.193
ilda+0.189
ooter+0.185
lee+0.184
Neg logit contributions
aw-0.142
Run-0.132
 horror-0.122
oc-0.109
 disaster-0.101
Token They
Token ID1119
Feature activation-1.21e+00

Pos logit contributions
aw+0.015
Run+0.015
oc+0.013
 horror+0.013
Is+0.012
Neg logit contributions
nam-0.018
ooter-0.016
ilda-0.016
anna-0.016
inations-0.015
Token watched
Token ID7342
Feature activation+9.38e-02

Pos logit contributions
aw+0.071
Run+0.069
oc+0.062
 horror+0.061
Is+0.056
Neg logit contributions
nam-0.063
ooter-0.059
anna-0.059
ilda-0.057
lee-0.056
Token in
Token ID287
Feature activation+1.64e+00

Pos logit contributions
nam+0.005
anna+0.005
ooter+0.005
lee+0.004
ilda+0.004
Neg logit contributions
aw-0.005
Run-0.005
oc-0.005
 horror-0.005
Is-0.004
Token horror
Token ID9961
Feature activation-7.81e+00

Pos logit contributions
nam+0.088
lee+0.076
 blank+0.075
 neat+0.074
 pretty+0.074
Neg logit contributions
aw-0.093
Run-0.090
oc-0.084
Is-0.074
Too-0.073
Token as
Token ID355
Feature activation+7.15e-01

Pos logit contributions
aw+0.440
Run+0.433
oc+0.391
 horror+0.384
Is+0.360
Neg logit contributions
nam-0.417
anna-0.385
ooter-0.382
ilda-0.372
lee-0.370
Token their
Token ID511
Feature activation-1.87e+00

Pos logit contributions
nam+0.042
ooter+0.041
anna+0.040
ilda+0.039
lee+0.038
Neg logit contributions
aw-0.036
Run-0.036
 horror-0.031
oc-0.030
Is-0.028
Token cart
Token ID6383
Feature activation+2.38e+00

Pos logit contributions
aw+0.106
Run+0.103
 horror+0.095
oc+0.087
Is+0.081
Neg logit contributions
nam-0.101
anna-0.095
ilda-0.093
ooter-0.090
 Jackie-0.089
Token crashed
Token ID14997
Feature activation-1.33e+00

Pos logit contributions
ooter+0.114
nam+0.112
ilda+0.104
anna+0.101
ail+0.100
Neg logit contributions
Run-0.136
aw-0.135
oc-0.129
 horror-0.129
Is-0.117
Token into
Token ID656
Feature activation-1.56e-01

Pos logit contributions
aw+0.079
Run+0.077
 horror+0.068
oc+0.068
Is+0.063
Neg logit contributions
nam-0.068
anna-0.063
ooter-0.063
ilda-0.061
lee-0.059
Token destroyed
Token ID6572
Feature activation-2.28e-01

Pos logit contributions
nam+0.024
anna+0.023
ooter+0.022
ilda+0.022
lee+0.021
Neg logit contributions
aw-0.025
Run-0.024
 horror-0.021
oc-0.021
Is-0.019
Token clock
Token ID8801
Feature activation-1.94e+00

Pos logit contributions
aw+0.013
Run+0.013
oc+0.012
 horror+0.012
Is+0.011
Neg logit contributions
nam-0.012
ooter-0.011
anna-0.011
ilda-0.011
lee-0.010
Token and
Token ID290
Feature activation-1.39e-01

Pos logit contributions
aw+0.113
Run+0.112
oc+0.100
 horror+0.099
Is+0.093
Neg logit contributions
nam-0.100
ooter-0.092
anna-0.091
ilda-0.089
lee-0.087
Token gasped
Token ID45236
Feature activation-1.40e+00

Pos logit contributions
aw+0.008
Run+0.008
 horror+0.007
oc+0.007
Is+0.006
Neg logit contributions
nam-0.007
ooter-0.007
anna-0.007
ilda-0.006
lee-0.006
Token in
Token ID287
Feature activation+1.67e+00

Pos logit contributions
Run+0.086
aw+0.086
oc+0.078
 horror+0.077
Is+0.072
Neg logit contributions
nam-0.068
anna-0.060
ooter-0.060
lee-0.059
ilda-0.059
Token horror
Token ID9961
Feature activation-7.80e+00

Pos logit contributions
nam+0.094
lee+0.083
 Jackie+0.083
 Emmy+0.082
 blank+0.079
Neg logit contributions
aw-0.092
Run-0.088
oc-0.081
Is-0.071
 horror-0.070
Token.
Token ID13
Feature activation+6.95e-02

Pos logit contributions
aw+0.439
Run+0.420
 horror+0.381
oc+0.368
Is+0.341
Neg logit contributions
nam-0.427
ooter-0.401
anna-0.388
ilda-0.382
 Jackie-0.366
Token
Token ID198
Feature activation-2.57e-01

Pos logit contributions
nam+0.004
ooter+0.004
inations+0.004
anna+0.004
ilda+0.004
Neg logit contributions
aw-0.003
Run-0.003
 horror-0.003
oc-0.003
Is-0.003
Token
Token ID198
Feature activation-2.74e-01

Pos logit contributions
aw+0.012
Run+0.012
oc+0.010
 horror+0.010
Is+0.010
Neg logit contributions
nam-0.018
ooter-0.016
anna-0.015
 handsome-0.015
ilda-0.015
TokenThe
Token ID464
Feature activation-9.11e-01

Pos logit contributions
aw+0.012
Run+0.012
oc+0.010
 horror+0.010
Is+0.009
Neg logit contributions
nam-0.018
ooter-0.017
anna-0.017
ilda-0.017
lee-0.016
Token old
Token ID1468
Feature activation+1.80e+00

Pos logit contributions
aw+0.049
Run+0.048
 horror+0.043
oc+0.042
Is+0.039
Neg logit contributions
nam-0.051
ooter-0.048
anna-0.048
ilda-0.047
lee-0.046
Token looked
Token ID3114
Feature activation+3.30e+00

Pos logit contributions
nam+0.058
ooter+0.053
anna+0.051
ilda+0.050
 Jackie+0.049
Neg logit contributions
aw-0.062
Run-0.058
oc-0.052
 horror-0.051
Is-0.047
Token up
Token ID510
Feature activation-1.82e+00

Pos logit contributions
nam+0.167
ooter+0.166
ilda+0.158
anna+0.156
ooters+0.153
Neg logit contributions
aw-0.199
Run-0.187
 horror-0.175
oc-0.157
Is-0.146
Token and
Token ID290
Feature activation-3.23e-04

Pos logit contributions
aw+0.101
Run+0.098
oc+0.088
 horror+0.087
Is+0.080
Neg logit contributions
nam-0.100
ooter-0.092
anna-0.092
ilda-0.089
lee-0.088
Token to
Token ID284
Feature activation+5.91e-01

Pos logit contributions
aw+0.000
Run+0.000
 horror+0.000
oc+0.000
Is+0.000
Neg logit contributions
ooter-0.000
nam-0.000
anna-0.000
ooters-0.000
inations-0.000
Token her
Token ID607
Feature activation+2.13e+00

Pos logit contributions
nam+0.031
ooter+0.030
anna+0.029
aj+0.028
ilda+0.028
Neg logit contributions
aw-0.033
Run-0.033
 horror-0.031
oc-0.029
Is-0.028
Token horror
Token ID9961
Feature activation-7.70e+00

Pos logit contributions
nam+0.114
anna+0.107
ooter+0.106
ooters+0.102
ilda+0.101
Neg logit contributions
aw-0.120
 horror-0.112
Run-0.112
oc-0.103
Is-0.095
Token she
Token ID673
Feature activation+2.67e-01

Pos logit contributions
aw+0.413
Run+0.396
 horror+0.370
oc+0.344
Is+0.325
Neg logit contributions
nam-0.440
ooter-0.400
anna-0.389
ilda-0.388
 handsome-0.372
Token saw
Token ID2497
Feature activation-2.09e-01

Pos logit contributions
nam+0.016
ooter+0.015
anna+0.014
ooters+0.014
ilda+0.013
Neg logit contributions
aw-0.015
Run-0.014
oc-0.012
 horror-0.012
Is-0.012
Token a
Token ID257
Feature activation+9.60e-02

Pos logit contributions
aw+0.011
Run+0.011
oc+0.010
 horror+0.010
Is+0.009
Neg logit contributions
nam-0.012
ooter-0.011
anna-0.011
ilda-0.010
lee-0.010
Token giant
Token ID6175
Feature activation-7.98e-01

Pos logit contributions
nam+0.004
anna+0.004
ooter+0.004
ilda+0.004
lee+0.004
Neg logit contributions
aw-0.006
Run-0.006
oc-0.006
 horror-0.005
Is-0.005
Token scary
Token ID14343
Feature activation-1.24e+00

Pos logit contributions
aw+0.045
Run+0.045
 horror+0.039
oc+0.039
Is+0.037
Neg logit contributions
nam-0.040
ooter-0.038
anna-0.037
ilda-0.036
lee-0.036
Token father
Token ID2988
Feature activation+8.89e-01

Pos logit contributions
nam+0.000
ooter+0.000
anna+0.000
ilda+0.000
lee+0.000
Neg logit contributions
aw-0.000
Run-0.000
oc-0.000
 horror-0.000
Is-0.000
Token and
Token ID290
Feature activation-2.86e-01

Pos logit contributions
nam+0.041
anna+0.038
ooter+0.038
ilda+0.036
lee+0.036
Neg logit contributions
aw-0.056
Run-0.055
 horror-0.050
oc-0.050
Is-0.047
Token daughter
Token ID4957
Feature activation+4.55e-01

Pos logit contributions
Run+0.017
aw+0.016
 horror+0.015
oc+0.015
Is+0.014
Neg logit contributions
nam-0.015
ooter-0.014
anna-0.014
ilda-0.013
lee-0.013
Token watched
Token ID7342
Feature activation-1.48e-01

Pos logit contributions
nam+0.023
ooter+0.021
anna+0.021
ilda+0.020
lee+0.020
Neg logit contributions
aw-0.027
Run-0.027
oc-0.025
 horror-0.024
Is-0.023
Token in
Token ID287
Feature activation+1.45e+00

Pos logit contributions
aw+0.009
Run+0.009
oc+0.008
 horror+0.008
Is+0.007
Neg logit contributions
nam-0.007
 Jackie-0.007
lee-0.007
anna-0.007
 Emmy-0.007
Token horror
Token ID9961
Feature activation-7.64e+00

Pos logit contributions
nam+0.088
 blank+0.081
 smile+0.080
 Jackie+0.080
lee+0.079
Neg logit contributions
aw-0.074
Run-0.065
oc-0.060
Is-0.052
Too-0.051
Token as
Token ID355
Feature activation+3.59e-01

Pos logit contributions
aw+0.452
Run+0.445
oc+0.405
 horror+0.396
Is+0.377
Neg logit contributions
nam-0.385
anna-0.357
ooter-0.348
ilda-0.343
lee-0.343
Token the
Token ID262
Feature activation+6.16e-01

Pos logit contributions
nam+0.020
ooter+0.018
anna+0.018
ilda+0.018
lee+0.018
Neg logit contributions
aw-0.020
Run-0.019
oc-0.017
 horror-0.017
Is-0.016
Token teenager
Token ID15287
Feature activation-5.93e-01

Pos logit contributions
nam+0.033
anna+0.031
ooter+0.031
ilda+0.029
lee+0.029
Neg logit contributions
aw-0.035
Run-0.034
 horror-0.031
oc-0.030
Is-0.028
Token cr
Token ID1067
Feature activation+8.01e-01

Pos logit contributions
aw+0.035
Run+0.034
oc+0.031
 horror+0.031
Is+0.029
Neg logit contributions
nam-0.030
ooter-0.028
anna-0.028
ilda-0.027
lee-0.026
Tokenue
Token ID518
Feature activation-9.19e-01

Pos logit contributions
nam+0.047
anna+0.042
ooter+0.042
ilda+0.041
 Jackie+0.040
Neg logit contributions
aw-0.043
Run-0.041
oc-0.036
 horror-0.036
Is-0.033
Token,
Token ID11
Feature activation-2.11e-01

Pos logit contributions
aw+0.053
Run+0.052
oc+0.048
 horror+0.047
Is+0.045
Neg logit contributions
nam-0.043
ooter-0.041
anna-0.040
ilda-0.039
lee-0.039
Token Sarah
Token ID10490
Feature activation+3.23e+00

Pos logit contributions
aw+0.012
Run+0.012
oc+0.011
 horror+0.011
Is+0.010
Neg logit contributions
nam-0.011
ooter-0.010
anna-0.010
ilda-0.010
 Jackie-0.010
Token,
Token ID11
Feature activation-2.13e-01

Pos logit contributions
nam+0.186
ooter+0.172
anna+0.169
ilda+0.165
lee+0.162
Neg logit contributions
aw-0.173
Run-0.168
 horror-0.150
oc-0.149
Is-0.136
Token watched
Token ID7342
Feature activation-1.06e-01

Pos logit contributions
aw+0.012
Run+0.012
oc+0.011
 horror+0.011
Is+0.010
Neg logit contributions
nam-0.011
ooter-0.010
anna-0.010
ilda-0.010
lee-0.010
Token in
Token ID287
Feature activation+1.45e+00

Pos logit contributions
aw+0.006
Run+0.006
oc+0.005
 horror+0.005
Is+0.005
Neg logit contributions
nam-0.006
anna-0.005
ooter-0.005
lee-0.005
ilda-0.005
Token horror
Token ID9961
Feature activation-7.60e+00

Pos logit contributions
nam+0.091
 blank+0.080
 Emmy+0.080
lee+0.080
 neat+0.079
Neg logit contributions
aw-0.072
Run-0.065
oc-0.062
Is-0.053
Too-0.052
Token as
Token ID355
Feature activation+4.23e-01

Pos logit contributions
aw+0.437
Run+0.428
oc+0.385
 horror+0.381
Is+0.354
Neg logit contributions
nam-0.402
ooter-0.370
anna-0.368
ilda-0.358
lee-0.352
Token Tim
Token ID5045
Feature activation+5.25e-02

Pos logit contributions
nam+0.026
ooter+0.026
anna+0.026
ilda+0.024
aj+0.024
Neg logit contributions
Run-0.020
aw-0.019
 horror-0.018
oc-0.016
Is-0.015
Tokenmy
Token ID1820
Feature activation+5.17e+00

Pos logit contributions
nam+0.002
 handsome+0.002
anna+0.002
 fashionable+0.002
ouses+0.002
Neg logit contributions
aw-0.004
Run-0.004
oc-0.003
 horror-0.003
Is-0.003
Token fell
Token ID3214
Feature activation-2.79e+00

Pos logit contributions
lee+0.203
anna+0.200
ilda+0.199
ooter+0.196
nam+0.193
Neg logit contributions
Run-0.319
aw-0.306
 horror-0.294
oc-0.288
Is-0.279
Token off
Token ID572
Feature activation-2.39e-01

Pos logit contributions
Run+0.145
aw+0.144
 horror+0.127
oc+0.113
 disaster+0.110
Neg logit contributions
nam-0.159
anna-0.153
inations-0.146
ilda-0.144
ppa-0.142
Token looked
Token ID3114
Feature activation+3.34e+00

Pos logit contributions
aw+0.135
Run+0.134
oc+0.124
 horror+0.120
Is+0.116
Neg logit contributions
nam-0.115
ooter-0.099
anna-0.099
lee-0.099
ilda-0.096
Token at
Token ID379
Feature activation-2.03e+00

Pos logit contributions
nam+0.207
ooter+0.195
anna+0.194
ilda+0.190
lee+0.184
Neg logit contributions
aw-0.165
Run-0.158
 horror-0.140
oc-0.138
Is-0.121
Token each
Token ID1123
Feature activation-7.83e-01

Pos logit contributions
aw+0.129
Run+0.124
oc+0.114
Is+0.108
Ble+0.105
Neg logit contributions
nam-0.098
 Jackie-0.080
 Emmy-0.078
lee-0.077
 Grac-0.077
Token other
Token ID584
Feature activation-4.22e+00

Pos logit contributions
aw+0.056
Run+0.053
oc+0.047
 horror+0.046
Too+0.045
Neg logit contributions
nam-0.029
ooter-0.027
ilda-0.027
nie-0.026
 Jackie-0.026
Token in
Token ID287
Feature activation+1.53e+00

Pos logit contributions
Run+0.247
aw+0.242
oc+0.212
Is+0.205
 horror+0.204
Neg logit contributions
nam-0.220
anna-0.201
ooter-0.199
ilda-0.196
lee-0.191
Token horror
Token ID9961
Feature activation-7.57e+00

Pos logit contributions
nam+0.081
 Emmy+0.073
 Jackie+0.072
 blank+0.070
 pretty+0.070
Neg logit contributions
aw-0.094
Run-0.083
oc-0.077
Is-0.068
Too-0.066
Token.
Token ID13
Feature activation+6.37e-02

Pos logit contributions
Run+0.481
aw+0.476
oc+0.443
 horror+0.422
Is+0.421
Neg logit contributions
nam-0.334
anna-0.319
lee-0.308
ooter-0.292
ilda-0.291
Token They
Token ID1119
Feature activation-1.41e+00

Pos logit contributions
nam+0.004
anna+0.003
ooter+0.003
lee+0.003
 Jackie+0.003
Neg logit contributions
aw-0.003
Run-0.003
oc-0.003
 horror-0.003
Is-0.003
Token had
Token ID550
Feature activation+2.26e+00

Pos logit contributions
aw+0.083
Run+0.081
oc+0.073
 horror+0.073
Is+0.067
Neg logit contributions
nam-0.073
ooter-0.067
anna-0.067
ilda-0.065
lee-0.064
Token no
Token ID645
Feature activation-4.79e+00

Pos logit contributions
nam+0.116
anna+0.113
ooter+0.111
ilda+0.107
 Jackie+0.102
Neg logit contributions
aw-0.134
Run-0.128
 horror-0.116
oc-0.111
Is-0.105
Token way
Token ID835
Feature activation-1.69e+00

Pos logit contributions
aw+0.310
Run+0.302
oc+0.269
Is+0.264
 horror+0.256
Neg logit contributions
nam-0.227
ooter-0.205
anna-0.190
 Jackie-0.188
 handsome-0.186
Token.
Token ID13
Feature activation+2.22e-01

Pos logit contributions
aw+0.041
Run+0.040
oc+0.037
 horror+0.036
Is+0.034
Neg logit contributions
nam-0.033
ooter-0.030
anna-0.030
ilda-0.029
lee-0.029
Token L
Token ID406
Feature activation+1.97e+00

Pos logit contributions
nam+0.012
ooter+0.011
anna+0.011
ilda+0.011
lee+0.010
Neg logit contributions
aw-0.013
Run-0.012
 horror-0.011
oc-0.011
Is-0.010
Tokenila
Token ID10102
Feature activation+6.67e-01

Pos logit contributions
nam+0.155
 handsome+0.134
ooter+0.133
 Jackie+0.133
 Emmy+0.133
Neg logit contributions
aw-0.079
Run-0.065
 horror-0.053
oc-0.052
Is-0.051
Token watched
Token ID7342
Feature activation+1.01e-01

Pos logit contributions
nam+0.038
ooter+0.036
anna+0.036
ilda+0.035
lee+0.034
Neg logit contributions
aw-0.035
Run-0.034
oc-0.030
 horror-0.030
Is-0.028
Token in
Token ID287
Feature activation+1.59e+00

Pos logit contributions
nam+0.005
anna+0.005
ooter+0.005
lee+0.005
ilda+0.005
Neg logit contributions
aw-0.006
Run-0.006
oc-0.005
 horror-0.005
Is-0.005
Token horror
Token ID9961
Feature activation-7.54e+00

Pos logit contributions
nam+0.094
 blank+0.085
 smile+0.084
lee+0.082
 Jackie+0.082
Neg logit contributions
aw-0.083
Run-0.077
oc-0.076
Is-0.063
Too-0.063
Token as
Token ID355
Feature activation+6.26e-01

Pos logit contributions
aw+0.442
Run+0.438
oc+0.400
 horror+0.389
Is+0.368
Neg logit contributions
nam-0.386
anna-0.354
ooter-0.351
ilda-0.341
lee-0.341
Token her
Token ID607
Feature activation+2.16e+00

Pos logit contributions
nam+0.036
ooter+0.033
anna+0.033
ilda+0.032
lee+0.032
Neg logit contributions
aw-0.033
Run-0.033
oc-0.029
 horror-0.029
Is-0.026
Token balloon
Token ID21190
Feature activation-2.43e+00

Pos logit contributions
nam+0.160
anna+0.152
ooter+0.152
ilda+0.149
lee+0.146
Neg logit contributions
aw-0.078
Run-0.076
 horror-0.063
oc-0.061
Is-0.053
Token got
Token ID1392
Feature activation+1.14e+00

Pos logit contributions
Run+0.149
aw+0.147
oc+0.144
 horror+0.143
Is+0.131
Neg logit contributions
nam-0.094
ooter-0.092
lee-0.092
ail-0.088
anna-0.088
Token smaller
Token ID4833
Feature activation-1.97e+00

Pos logit contributions
anna+0.068
ooter+0.065
ilda+0.064
nam+0.063
ouses+0.060
Neg logit contributions
aw-0.060
Run-0.059
 horror-0.050
 disaster-0.046
Is-0.045
Token
Token ID198
Feature activation-9.15e-02

Pos logit contributions
aw+0.003
Run+0.003
oc+0.002
 horror+0.002
Is+0.002
Neg logit contributions
nam-0.003
ooter-0.003
anna-0.003
ilda-0.003
lee-0.003
TokenThe
Token ID464
Feature activation-9.59e-01

Pos logit contributions
aw+0.005
 horror+0.005
Run+0.004
oc+0.004
 disaster+0.004
Neg logit contributions
nam-0.005
anna-0.005
ooter-0.004
ilda-0.004
 Jackie-0.004
Token flower
Token ID15061
Feature activation-1.81e+00

Pos logit contributions
Run+0.061
aw+0.060
 horror+0.056
oc+0.055
Is+0.052
Neg logit contributions
nam-0.045
ooter-0.043
anna-0.041
ooters-0.040
ilda-0.039
Token watched
Token ID7342
Feature activation-1.95e-02

Pos logit contributions
aw+0.101
Run+0.100
oc+0.089
 horror+0.089
Is+0.083
Neg logit contributions
nam-0.092
anna-0.089
ooter-0.087
lee-0.085
ilda-0.083
Token in
Token ID287
Feature activation+1.52e+00

Pos logit contributions
aw+0.001
Run+0.001
oc+0.001
 horror+0.001
Is+0.001
Neg logit contributions
nam-0.001
anna-0.001
ooter-0.001
ilda-0.001
lee-0.001
Token horror
Token ID9961
Feature activation-7.52e+00

Pos logit contributions
nam+0.079
 Jackie+0.076
 blank+0.074
lee+0.073
 smile+0.072
Neg logit contributions
aw-0.086
Run-0.079
oc-0.074
Is-0.067
Too-0.067
Token as
Token ID355
Feature activation+5.62e-01

Pos logit contributions
aw+0.430
Run+0.424
oc+0.384
 horror+0.378
Is+0.354
Neg logit contributions
nam-0.394
anna-0.365
ooter-0.362
ilda-0.352
lee-0.350
Token the
Token ID262
Feature activation+6.77e-01

Pos logit contributions
nam+0.033
ooter+0.031
anna+0.031
ilda+0.030
lee+0.030
Neg logit contributions
aw-0.029
Run-0.028
oc-0.025
 horror-0.025
Is-0.023
Token potato
Token ID21219
Feature activation-2.57e-01

Pos logit contributions
nam+0.042
ooter+0.039
anna+0.038
ooters+0.037
ilda+0.037
Neg logit contributions
Run-0.034
aw-0.033
 horror-0.030
oc-0.028
Is-0.026
Token began
Token ID2540
Feature activation-8.50e-01

Pos logit contributions
aw+0.015
Run+0.015
oc+0.014
 horror+0.014
Is+0.013
Neg logit contributions
nam-0.012
anna-0.012
lee-0.011
ooter-0.011
ilda-0.011
Token to
Token ID284
Feature activation+4.99e-01

Pos logit contributions
aw+0.059
Run+0.058
 horror+0.055
oc+0.052
Is+0.049
Neg logit contributions
nam-0.036
ooter-0.031
anna-0.031
ilda-0.030
 handsome-0.028
Token saw
Token ID2497
Feature activation-2.24e-01

Pos logit contributions
aw+0.034
Run+0.033
 horror+0.031
oc+0.031
Is+0.027
Neg logit contributions
nam-0.030
lee-0.027
ooter-0.026
ilda-0.026
 handsome-0.026
Token the
Token ID262
Feature activation+5.81e-01

Pos logit contributions
aw+0.014
Run+0.014
oc+0.013
 horror+0.012
Is+0.011
Neg logit contributions
nam-0.011
ooter-0.010
anna-0.010
ilda-0.009
lee-0.009
Token fear
Token ID3252
Feature activation-2.22e+00

Pos logit contributions
nam+0.031
anna+0.029
ooter+0.029
ilda+0.028
lee+0.027
Neg logit contributions
aw-0.033
Run-0.032
oc-0.029
 horror-0.029
Is-0.027
Token and
Token ID290
Feature activation-2.76e-01

Pos logit contributions
aw+0.126
Run+0.123
oc+0.114
 horror+0.111
Is+0.103
Neg logit contributions
nam-0.112
ooter-0.107
anna-0.104
ilda-0.102
lee-0.100
Token the
Token ID262
Feature activation+5.65e-01

Pos logit contributions
aw+0.016
Run+0.016
oc+0.014
 horror+0.014
Is+0.013
Neg logit contributions
nam-0.015
ooter-0.013
anna-0.013
lee-0.013
ilda-0.012
Token horror
Token ID9961
Feature activation-7.49e+00

Pos logit contributions
nam+0.033
anna+0.032
ilda+0.031
ooter+0.030
lee+0.030
Neg logit contributions
aw-0.030
Run-0.029
 horror-0.026
oc-0.025
Is-0.023
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
aw+0.475
Run+0.470
oc+0.438
 horror+0.418
Is+0.401
Neg logit contributions
nam-0.329
ooter-0.317
anna-0.311
lee-0.298
ilda-0.297
Token He
Token ID679
Feature activation-6.18e-01

Pos logit contributions
nam+0.012
ooter+0.011
anna+0.011
ilda+0.011
lee+0.011
Neg logit contributions
aw-0.013
Run-0.013
oc-0.011
 horror-0.011
Is-0.010
Token saw
Token ID2497
Feature activation-2.55e-01

Pos logit contributions
aw+0.038
Run+0.038
 horror+0.036
oc+0.036
 conclusions+0.033
Neg logit contributions
nam-0.026
lee-0.024
 handsome-0.022
 pretty-0.021
ooter-0.021
Token the
Token ID262
Feature activation+5.63e-01

Pos logit contributions
aw+0.016
Run+0.016
oc+0.015
 horror+0.014
Is+0.014
Neg logit contributions
nam-0.012
lee-0.010
ooter-0.010
 Jackie-0.010
ilda-0.010
Token crash
Token ID7014
Feature activation+8.43e-01

Pos logit contributions
nam+0.030
ooter+0.027
anna+0.027
ilda+0.026
lee+0.026
Neg logit contributions
aw-0.032
Run-0.032
oc-0.029
 horror-0.028
Is-0.026
Token air
Token ID1633
Feature activation-5.91e-01

Pos logit contributions
nam+0.053
ooter+0.051
anna+0.049
lee+0.048
ilda+0.047
Neg logit contributions
Run-0.039
aw-0.038
oc-0.035
 horror-0.033
Is-0.031
Token.
Token ID13
Feature activation+2.51e-01

Pos logit contributions
aw+0.035
Run+0.035
oc+0.032
 horror+0.031
Is+0.029
Neg logit contributions
nam-0.029
ooter-0.027
anna-0.027
ilda-0.026
lee-0.025
Token Sam
Token ID3409
Feature activation-5.60e-01

Pos logit contributions
nam+0.013
ooter+0.012
anna+0.012
lee+0.012
ilda+0.012
Neg logit contributions
aw-0.014
Run-0.014
oc-0.013
 horror-0.012
Is-0.011
Token watched
Token ID7342
Feature activation+1.86e-01

Pos logit contributions
aw+0.030
Run+0.029
oc+0.026
 horror+0.026
Is+0.024
Neg logit contributions
nam-0.032
ooter-0.029
anna-0.029
ilda-0.028
lee-0.028
Token in
Token ID287
Feature activation+1.70e+00

Pos logit contributions
nam+0.010
anna+0.009
lee+0.009
ooter+0.009
 Jackie+0.009
Neg logit contributions
aw-0.011
Run-0.010
oc-0.010
 horror-0.009
Is-0.009
Token horror
Token ID9961
Feature activation-7.49e+00

Pos logit contributions
nam+0.090
 blank+0.082
 smile+0.082
lee+0.082
 Jackie+0.081
Neg logit contributions
aw-0.095
Run-0.088
oc-0.083
Is-0.074
Too-0.073
Token as
Token ID355
Feature activation+7.53e-01

Pos logit contributions
aw+0.437
Run+0.432
oc+0.392
 horror+0.384
Is+0.365
Neg logit contributions
nam-0.381
anna-0.353
ooter-0.348
lee-0.340
ilda-0.338
Token R
Token ID371
Feature activation+3.40e-01

Pos logit contributions
nam+0.043
ooter+0.039
anna+0.039
ilda+0.039
lee+0.038
Neg logit contributions
aw-0.040
Run-0.039
oc-0.035
 horror-0.034
Is-0.032
Tokenoo
Token ID2238
Feature activation+1.28e+00

Pos logit contributions
nam+0.020
ooter+0.018
anna+0.018
ilda+0.018
lee+0.018
Neg logit contributions
aw-0.018
Run-0.017
oc-0.015
 horror-0.015
Is-0.014
Token landed
Token ID11406
Feature activation+2.97e-01

Pos logit contributions
nam+0.072
anna+0.067
ooter+0.067
ilda+0.065
lee+0.065
Neg logit contributions
aw-0.067
Run-0.067
 horror-0.060
oc-0.060
Is-0.055
Token on
Token ID319
Feature activation+9.29e-01

Pos logit contributions
nam+0.011
ooter+0.011
lee+0.011
anna+0.010
ail+0.010
Neg logit contributions
oc-0.019
Run-0.019
aw-0.018
 horror-0.018
Is-0.017
Token,
Token ID11
Feature activation+3.09e-02

Pos logit contributions
Run+0.128
aw+0.122
oc+0.117
 horror+0.113
Bad+0.113
Neg logit contributions
 Jackie-0.079
lee-0.075
 blank-0.073
nam-0.072
anna-0.071
Token reluctantly
Token ID35462
Feature activation-8.40e-02

Pos logit contributions
nam+0.002
ooter+0.002
anna+0.002
ilda+0.002
ooters+0.002
Neg logit contributions
aw-0.002
Run-0.002
 horror-0.001
oc-0.001
Is-0.001
Token.
Token ID13
Feature activation+5.12e-02

Pos logit contributions
aw+0.005
Run+0.005
oc+0.005
 horror+0.005
Is+0.004
Neg logit contributions
nam-0.004
ooter-0.004
anna-0.004
ilda-0.004
lee-0.004
Token To
Token ID1675
Feature activation+3.95e-01

Pos logit contributions
nam+0.003
ooter+0.003
anna+0.003
ilda+0.003
lee+0.003
Neg logit contributions
aw-0.003
Run-0.003
oc-0.002
 horror-0.002
Is-0.002
Token his
Token ID465
Feature activation-2.88e-01

Pos logit contributions
nam+0.019
anna+0.017
ilda+0.017
 Jackie+0.017
ooter+0.017
Neg logit contributions
aw-0.024
Run-0.024
 horror-0.021
oc-0.021
Is-0.020
Token horror
Token ID9961
Feature activation-7.39e+00

Pos logit contributions
aw+0.016
Run+0.016
oc+0.014
Is+0.013
 horror+0.013
Neg logit contributions
nam-0.015
anna-0.014
ooter-0.014
 Jackie-0.014
lee-0.014
Token,
Token ID11
Feature activation+1.93e-01

Pos logit contributions
aw+0.388
Run+0.378
 horror+0.338
oc+0.331
Is+0.302
Neg logit contributions
nam-0.433
ooter-0.397
anna-0.387
ilda-0.380
lee-0.370
Token it
Token ID340
Feature activation-3.01e-01

Pos logit contributions
nam+0.010
ilda+0.009
 Jackie+0.009
ooter+0.009
anna+0.009
Neg logit contributions
aw-0.011
Run-0.011
oc-0.010
 horror-0.010
Is-0.009
Token was
Token ID373
Feature activation-1.89e+00

Pos logit contributions
aw+0.016
Run+0.016
 horror+0.014
oc+0.014
Is+0.013
Neg logit contributions
nam-0.016
anna-0.015
 Jackie-0.015
ilda-0.015
lee-0.015
Token bitter
Token ID12922
Feature activation-1.22e+00

Pos logit contributions
aw+0.103
Run+0.101
 horror+0.094
 disaster+0.086
oc+0.084
Neg logit contributions
ooter-0.103
nam-0.102
anna-0.099
ooters-0.096
ilda-0.094
Token and
Token ID290
Feature activation-8.87e-02

Pos logit contributions
Run+0.069
aw+0.069
oc+0.063
 horror+0.062
Is+0.058
Neg logit contributions
nam-0.062
anna-0.059
ooter-0.058
ilda-0.057
lee-0.057
Token times
Token ID1661
Feature activation+2.59e-01

Pos logit contributions
aw+0.179
Run+0.175
 horror+0.158
oc+0.156
Is+0.140
Neg logit contributions
nam-0.189
ooter-0.170
anna-0.168
ilda-0.167
lee-0.163
Token,
Token ID11
Feature activation-1.63e-01

Pos logit contributions
nam+0.015
anna+0.014
ooter+0.013
ilda+0.013
lee+0.013
Neg logit contributions
aw-0.014
Run-0.013
 horror-0.012
oc-0.012
Is-0.011
Token but
Token ID475
Feature activation-1.45e+00

Pos logit contributions
aw+0.011
Run+0.011
oc+0.010
 horror+0.010
Is+0.009
Neg logit contributions
nam-0.007
ooter-0.006
anna-0.006
ilda-0.006
lee-0.006
Token to
Token ID284
Feature activation+3.42e-01

Pos logit contributions
aw+0.086
Run+0.082
oc+0.080
 horror+0.070
Is+0.067
Neg logit contributions
nam-0.081
 Jackie-0.069
ilda-0.067
ooter-0.067
anna-0.066
Token no
Token ID645
Feature activation-4.91e+00

Pos logit contributions
nam+0.017
anna+0.016
ooter+0.016
lee+0.015
ilda+0.015
Neg logit contributions
aw-0.020
Run-0.020
 horror-0.018
oc-0.017
Is-0.017
Token avail
Token ID29107
Feature activation-7.21e+00

Pos logit contributions
aw+0.298
Run+0.289
oc+0.267
 horror+0.255
Is+0.244
Neg logit contributions
nam-0.249
anna-0.226
ooter-0.223
ilda-0.221
 Jackie-0.218
Token.
Token ID13
Feature activation-3.93e-01

Pos logit contributions
aw+0.404
Run+0.390
oc+0.360
 horror+0.355
Is+0.328
Neg logit contributions
nam-0.389
ooter-0.358
anna-0.353
ilda-0.346
lee-0.340
Token
Token ID220
Feature activation+4.63e+00

Pos logit contributions
aw+0.023
Run+0.022
 horror+0.021
oc+0.020
Is+0.019
Neg logit contributions
nam-0.020
ooter-0.019
ilda-0.019
anna-0.018
ppa-0.018
Token
Token ID628
Feature activation+6.65e-01

Pos logit contributions
nam+0.342
anna+0.301
 handsome+0.299
ooter+0.299
inations+0.295
Neg logit contributions
aw-0.186
Run-0.154
 horror-0.140
Is-0.140
oc-0.134
Token Jane
Token ID12091
Feature activation+1.27e+00

Pos logit contributions
nam+0.033
anna+0.030
ooter+0.030
ilda+0.029
 Jackie+0.029
Neg logit contributions
aw-0.040
Run-0.039
oc-0.035
 horror-0.035
Is-0.032
Token's
Token ID338
Feature activation-2.58e+00

Pos logit contributions
anna+0.064
nam+0.064
ilda+0.062
lee+0.061
ooter+0.060
Neg logit contributions
Run-0.071
aw-0.068
 horror-0.062
oc-0.062
Is-0.058
Token out
Token ID503
Feature activation-3.43e-01

Pos logit contributions
aw+0.086
Run+0.083
 horror+0.077
oc+0.073
Is+0.067
Neg logit contributions
nam-0.087
anna-0.080
ilda-0.077
ooter-0.076
aj-0.076
Token,
Token ID11
Feature activation-1.84e-01

Pos logit contributions
aw+0.017
Run+0.017
 horror+0.015
oc+0.015
Is+0.013
Neg logit contributions
nam-0.021
anna-0.019
ooter-0.019
ilda-0.019
aj-0.018
Token but
Token ID475
Feature activation-1.36e+00

Pos logit contributions
aw+0.012
Run+0.012
oc+0.011
 horror+0.011
Is+0.010
Neg logit contributions
nam-0.008
ooter-0.008
anna-0.007
ilda-0.007
lee-0.007
Token to
Token ID284
Feature activation+5.00e-01

Pos logit contributions
aw+0.077
Run+0.074
oc+0.068
 horror+0.064
Is+0.060
Neg logit contributions
nam-0.077
ooter-0.067
 Jackie-0.066
anna-0.065
ilda-0.065
Token no
Token ID645
Feature activation-4.75e+00

Pos logit contributions
nam+0.025
ooter+0.023
anna+0.023
ilda+0.022
lee+0.022
Neg logit contributions
aw-0.030
Run-0.029
oc-0.026
 horror-0.026
Is-0.024
Token avail
Token ID29107
Feature activation-7.15e+00

Pos logit contributions
aw+0.271
Run+0.256
oc+0.251
Is+0.227
 horror+0.226
Neg logit contributions
nam-0.252
 Jackie-0.233
anna-0.226
ooter-0.222
 Emmy-0.222
Token.
Token ID13
Feature activation-1.80e-01

Pos logit contributions
aw+0.395
Run+0.380
oc+0.357
 horror+0.348
Is+0.319
Neg logit contributions
nam-0.392
ooter-0.359
anna-0.354
ilda-0.348
lee-0.341
Token He
Token ID679
Feature activation-9.17e-01

Pos logit contributions
aw+0.010
Run+0.010
oc+0.009
 horror+0.009
Is+0.008
Neg logit contributions
nam-0.009
ooter-0.009
anna-0.009
ilda-0.008
lee-0.008
Token felt
Token ID2936
Feature activation+1.30e+00

Pos logit contributions
aw+0.053
Run+0.052
 horror+0.047
oc+0.047
Is+0.044
Neg logit contributions
nam-0.044
anna-0.043
lee-0.041
ooter-0.041
ilda-0.040
Token sad
Token ID6507
Feature activation+1.50e+00

Pos logit contributions
nam+0.052
ooter+0.045
anna+0.045
lee+0.044
 Jackie+0.043
Neg logit contributions
aw-0.090
Run-0.089
oc-0.083
 horror-0.080
Is-0.077
Token and
Token ID290
Feature activation-3.06e-01

Pos logit contributions
nam+0.078
ooter+0.074
anna+0.073
ilda+0.072
lee+0.071
Neg logit contributions
Run-0.085
aw-0.084
oc-0.075
 horror-0.073
Is-0.069
Token him
Token ID683
Feature activation+5.36e-01

Pos logit contributions
aw+0.053
Run+0.050
 horror+0.046
oc+0.045
Is+0.040
Neg logit contributions
nam-0.062
ooter-0.059
anna-0.059
ilda-0.057
aj-0.054
Token.
Token ID13
Feature activation-9.36e-02

Pos logit contributions
nam+0.033
ooter+0.031
anna+0.031
ilda+0.030
lee+0.029
Neg logit contributions
aw-0.026
Run-0.024
oc-0.023
 horror-0.022
Is-0.018
Token But
Token ID887
Feature activation-3.34e+00

Pos logit contributions
aw+0.005
Run+0.005
oc+0.005
 horror+0.004
Is+0.004
Neg logit contributions
nam-0.005
ooter-0.005
anna-0.005
ilda-0.005
lee-0.005
Token to
Token ID284
Feature activation+5.28e-01

Pos logit contributions
aw+0.195
Run+0.184
oc+0.161
 horror+0.159
Is+0.153
Neg logit contributions
nam-0.183
 Jackie-0.163
ooter-0.158
anna-0.156
ilda-0.155
Token no
Token ID645
Feature activation-4.72e+00

Pos logit contributions
nam+0.027
ooter+0.024
anna+0.024
ilda+0.024
lee+0.023
Neg logit contributions
aw-0.032
Run-0.031
oc-0.028
 horror-0.027
Is-0.025
Token avail
Token ID29107
Feature activation-7.12e+00

Pos logit contributions
aw+0.310
Run+0.301
oc+0.277
 horror+0.271
Is+0.264
Neg logit contributions
nam-0.211
anna-0.191
ooter-0.189
 Jackie-0.184
ilda-0.180
Token,
Token ID11
Feature activation+6.43e-02

Pos logit contributions
aw+0.378
Run+0.362
oc+0.345
 horror+0.331
Is+0.303
Neg logit contributions
nam-0.406
ooter-0.371
anna-0.365
ilda-0.361
lee-0.354
Token they
Token ID484
Feature activation-1.40e+00

Pos logit contributions
nam+0.003
 Jackie+0.003
anna+0.003
ooter+0.003
ilda+0.003
Neg logit contributions
aw-0.004
Run-0.004
oc-0.003
 horror-0.003
Is-0.003
Token were
Token ID547
Feature activation-1.26e+00

Pos logit contributions
aw+0.081
Run+0.080
 horror+0.071
oc+0.071
Is+0.063
Neg logit contributions
nam-0.075
ooter-0.069
anna-0.067
aj-0.067
ilda-0.066
Token too
Token ID1165
Feature activation+1.89e+00

Pos logit contributions
aw+0.075
Run+0.071
 horror+0.067
oc+0.060
Bad+0.057
Neg logit contributions
nam-0.065
ooter-0.062
anna-0.060
ilda-0.060
aj-0.057
Token scared
Token ID12008
Feature activation+8.64e-01

Pos logit contributions
nam+0.092
ooter+0.092
anna+0.086
ilda+0.085
ooters+0.081
Neg logit contributions
aw-0.115
Run-0.115
 horror-0.101
oc-0.099
 disaster-0.092
Token deep
Token ID2769
Feature activation-2.79e+00

Pos logit contributions
 horror+0.012
Run+0.011
aw+0.011
oc+0.010
 disaster+0.010
Neg logit contributions
anna-0.017
nam-0.016
any-0.016
ppa-0.016
ilda-0.015
Token paws
Token ID49193
Feature activation-3.69e-01

Pos logit contributions
 horror+0.136
aw+0.131
Run+0.129
oc+0.126
 disaster+0.107
Neg logit contributions
nam-0.166
ilda-0.153
inations-0.147
ppa-0.147
 handsome-0.144
Token,
Token ID11
Feature activation-4.32e-02

Pos logit contributions
aw+0.018
Run+0.017
 horror+0.015
oc+0.015
Is+0.013
Neg logit contributions
nam-0.022
anna-0.021
ooter-0.020
ilda-0.020
lee-0.020
Token to
Token ID284
Feature activation+6.14e-01

Pos logit contributions
aw+0.003
Run+0.003
oc+0.003
 horror+0.002
Is+0.002
Neg logit contributions
nam-0.002
ooter-0.002
anna-0.002
ilda-0.002
lee-0.002
Token no
Token ID645
Feature activation-4.72e+00

Pos logit contributions
nam+0.030
anna+0.029
ooter+0.028
ilda+0.027
lee+0.027
Neg logit contributions
aw-0.037
Run-0.037
 horror-0.033
oc-0.033
Is-0.031
Token avail
Token ID29107
Feature activation-7.03e+00

Pos logit contributions
aw+0.290
Run+0.283
oc+0.256
 horror+0.251
Is+0.238
Neg logit contributions
nam-0.235
ooter-0.215
anna-0.212
ilda-0.206
lee-0.202
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
aw+0.370
Run+0.351
oc+0.339
 horror+0.326
Is+0.295
Neg logit contributions
nam-0.403
ooter-0.367
anna-0.360
ilda-0.357
 handsome-0.352
Token He
Token ID679
Feature activation-8.10e-01

Pos logit contributions
aw+0.006
Run+0.006
oc+0.005
 horror+0.005
Is+0.005
Neg logit contributions
nam-0.005
ooter-0.005
anna-0.005
ilda-0.005
lee-0.005
Token finally
Token ID3443
Feature activation+5.03e-01

Pos logit contributions
aw+0.047
Run+0.047
 horror+0.042
oc+0.041
Is+0.039
Neg logit contributions
nam-0.041
anna-0.038
ooter-0.037
ilda-0.036
lee-0.036
Token thought
Token ID1807
Feature activation+3.58e+00

Pos logit contributions
nam+0.022
ooter+0.020
anna+0.020
ilda+0.019
lee+0.019
Neg logit contributions
aw-0.033
Run-0.033
oc-0.030
 horror-0.030
Is-0.028
Token of
Token ID286
Feature activation-7.40e-01

Pos logit contributions
nam+0.226
ooter+0.207
anna+0.205
ilda+0.198
lee+0.196
Neg logit contributions
aw-0.173
Run-0.166
 horror-0.150
oc-0.144
Is-0.132
Token eat
Token ID4483
Feature activation-5.77e+00

Pos logit contributions
aw+0.165
Run+0.161
oc+0.147
 horror+0.143
Is+0.135
Neg logit contributions
nam-0.148
anna-0.130
ooter-0.129
ilda-0.128
 Jackie-0.127
Token his
Token ID465
Feature activation-2.96e+00

Pos logit contributions
aw+0.312
Run+0.304
oc+0.271
 horror+0.268
Is+0.247
Neg logit contributions
nam-0.325
ooter-0.302
anna-0.299
ilda-0.292
lee-0.287
Token treat
Token ID2190
Feature activation-2.83e+00

Pos logit contributions
aw+0.143
Run+0.138
oc+0.125
 horror+0.122
 disaster+0.108
Neg logit contributions
nam-0.172
ilda-0.169
anna-0.168
lee-0.161
ooter-0.161
Token.
Token ID13
Feature activation-1.39e+00

Pos logit contributions
aw+0.160
Run+0.155
oc+0.141
 horror+0.137
Is+0.127
Neg logit contributions
nam-0.152
ooter-0.141
anna-0.139
ilda-0.135
lee-0.134
Token The
Token ID383
Feature activation-7.69e-01

Pos logit contributions
aw+0.073
Run+0.072
oc+0.066
 horror+0.063
Is+0.059
Neg logit contributions
nam-0.080
ooter-0.073
ilda-0.072
anna-0.072
lee-0.070
Token end
Token ID886
Feature activation-6.93e+00

Pos logit contributions
aw+0.039
Run+0.038
oc+0.033
 horror+0.033
Is+0.030
Neg logit contributions
nam-0.046
anna-0.044
ooter-0.043
ilda-0.042
lee-0.042
Token.
Token ID13
Feature activation-7.10e-01

Pos logit contributions
aw+0.390
Run+0.381
oc+0.350
 horror+0.338
Is+0.309
Neg logit contributions
nam-0.395
ooter-0.353
anna-0.345
ilda-0.339
lee-0.333
Token<|endoftext|>
Token ID50256
Feature activation-1.88e+00

Pos logit contributions
aw+0.042
Run+0.041
oc+0.036
 horror+0.036
Is+0.034
Neg logit contributions
nam-0.036
ooter-0.034
anna-0.033
ilda-0.032
lee-0.032
TokenOnce
Token ID7454
Feature activation+2.51e+00

Pos logit contributions
aw+0.102
Run+0.099
oc+0.089
 horror+0.087
Is+0.081
Neg logit contributions
nam-0.108
ooter-0.099
anna-0.098
ilda-0.095
lee-0.094
Token there
Token ID612
Feature activation+2.10e+00

Pos logit contributions
nam+0.103
ooter+0.088
anna+0.086
any+0.085
inations+0.083
Neg logit contributions
aw-0.167
Run-0.152
 horror-0.150
oc-0.146
ara-0.140
Token was
Token ID373
Feature activation-2.00e+00

Pos logit contributions
nam+0.124
ooter+0.117
anna+0.116
 Jackie+0.116
ilda+0.114
Neg logit contributions
aw-0.103
Run-0.103
oc-0.086
 horror-0.086
Is-0.077
Token restored
Token ID15032
Feature activation-2.07e+00

Pos logit contributions
nam+0.003
anna+0.003
ooter+0.003
ilda+0.003
lee+0.003
Neg logit contributions
aw-0.002
Run-0.002
oc-0.002
 horror-0.002
Is-0.002
Token.
Token ID13
Feature activation-2.53e+00

Pos logit contributions
aw+0.109
Run+0.101
oc+0.094
 horror+0.092
Is+0.080
Neg logit contributions
nam-0.119
ooter-0.113
anna-0.111
ilda-0.107
ooters-0.104
Token
Token ID198
Feature activation-1.91e+00

Pos logit contributions
aw+0.130
Run+0.127
oc+0.116
 horror+0.110
Is+0.105
Neg logit contributions
nam-0.150
ooter-0.138
ilda-0.133
anna-0.132
inations-0.131
Token
Token ID198
Feature activation-1.64e+00

Pos logit contributions
aw+0.098
Run+0.093
oc+0.085
 horror+0.079
Is+0.076
Neg logit contributions
nam-0.122
ooter-0.111
ilda-0.104
anna-0.103
 handsome-0.101
TokenThe
Token ID464
Feature activation-1.93e+00

Pos logit contributions
aw+0.072
Run+0.070
 horror+0.060
oc+0.060
Is+0.053
Neg logit contributions
nam-0.108
ooter-0.102
anna-0.102
ilda-0.099
lee-0.098
Token end
Token ID886
Feature activation-6.84e+00

Pos logit contributions
aw+0.097
Run+0.095
 horror+0.083
oc+0.083
Is+0.075
Neg logit contributions
nam-0.116
anna-0.110
ooter-0.109
ilda-0.106
lee-0.104
Token.
Token ID13
Feature activation-4.88e-01

Pos logit contributions
aw+0.375
Run+0.363
oc+0.329
 horror+0.325
Is+0.290
Neg logit contributions
nam-0.410
ooter-0.361
anna-0.352
ilda-0.345
lee-0.338
Token<|endoftext|>
Token ID50256
Feature activation-2.08e+00

Pos logit contributions
aw+0.028
Run+0.027
oc+0.025
 horror+0.025
Is+0.023
Neg logit contributions
nam-0.026
ooter-0.024
anna-0.024
ilda-0.023
lee-0.022
TokenJohn
Token ID7554
Feature activation+1.29e-03

Pos logit contributions
aw+0.100
Run+0.097
oc+0.085
 horror+0.084
Is+0.077
Neg logit contributions
nam-0.131
ooter-0.121
anna-0.121
ilda-0.118
lee-0.116
Token was
Token ID373
Feature activation-1.98e+00

Pos logit contributions
nam+0.000
ooter+0.000
ooters+0.000
inations+0.000
ilda+0.000
Neg logit contributions
aw-0.000
Run-0.000
oc-0.000
 horror-0.000
Is-0.000
Token walking
Token ID6155
Feature activation+4.57e+00

Pos logit contributions
aw+0.129
Run+0.119
 horror+0.113
oc+0.104
 disaster+0.099
Neg logit contributions
nam-0.094
ooter-0.085
anna-0.082
ilda-0.081
ooters-0.081
Token cozy
Token ID37438
Feature activation-2.14e+00

Pos logit contributions
aw+0.079
Run+0.075
oc+0.070
 horror+0.066
Is+0.062
Neg logit contributions
nam-0.074
ooter-0.069
anna-0.068
ilda-0.066
lee-0.066
Token and
Token ID290
Feature activation-1.69e+00

Pos logit contributions
aw+0.114
Run+0.109
oc+0.101
 horror+0.097
 disaster+0.085
Neg logit contributions
nam-0.120
ooter-0.110
ilda-0.108
anna-0.106
lee-0.106
Token content
Token ID2695
Feature activation-2.33e+00

Pos logit contributions
Run+0.106
aw+0.106
oc+0.097
 horror+0.096
Is+0.086
Neg logit contributions
ooter-0.075
nam-0.071
ilda-0.070
anna-0.069
ooters-0.067
Token.
Token ID13
Feature activation-1.41e+00

Pos logit contributions
aw+0.132
Run+0.127
oc+0.115
 horror+0.113
Is+0.104
Neg logit contributions
nam-0.127
ooter-0.118
anna-0.115
ilda-0.113
lee-0.111
Token The
Token ID383
Feature activation-6.64e-01

Pos logit contributions
aw+0.075
Run+0.073
oc+0.067
 horror+0.064
Is+0.060
Neg logit contributions
nam-0.082
ooter-0.076
ilda-0.073
anna-0.072
inations-0.071
Token end
Token ID886
Feature activation-6.83e+00

Pos logit contributions
aw+0.035
Run+0.035
 horror+0.031
oc+0.031
Is+0.028
Neg logit contributions
nam-0.038
ooter-0.035
anna-0.035
ilda-0.034
lee-0.034
Token.
Token ID13
Feature activation-6.47e-01

Pos logit contributions
aw+0.397
Run+0.385
oc+0.349
 horror+0.347
Is+0.317
Neg logit contributions
nam-0.373
ooter-0.335
anna-0.330
ilda-0.321
lee-0.315
Token<|endoftext|>
Token ID50256
Feature activation-1.87e+00

Pos logit contributions
aw+0.036
Run+0.035
oc+0.032
 horror+0.032
Is+0.029
Neg logit contributions
nam-0.035
ooter-0.033
anna-0.032
ilda-0.031
lee-0.031
TokenOnce
Token ID7454
Feature activation+2.51e+00

Pos logit contributions
aw+0.092
Run+0.089
oc+0.079
 horror+0.075
Is+0.071
Neg logit contributions
nam-0.121
ooter-0.110
anna-0.109
ilda-0.105
lee-0.104
Token upon
Token ID2402
Feature activation+1.34e+00

Pos logit contributions
nam+0.102
ooter+0.089
anna+0.087
any+0.087
inations+0.085
Neg logit contributions
aw-0.163
 horror-0.150
Run-0.149
oc-0.142
 disaster-0.140
Token a
Token ID257
Feature activation-4.70e-02

Pos logit contributions
nam+0.075
ooter+0.070
anna+0.069
ilda+0.067
lee+0.066
Neg logit contributions
aw-0.073
Run-0.072
oc-0.064
 horror-0.063
Is-0.058
Token peacefully
Token ID30996
Feature activation-5.70e+00

Pos logit contributions
nam+0.066
anna+0.065
ilda+0.063
ooter+0.062
ppa+0.062
Neg logit contributions
aw-0.082
Run-0.079
oc-0.070
 horror-0.068
Go-0.065
Token and
Token ID290
Feature activation-2.05e+00

Pos logit contributions
aw+0.309
Run+0.298
oc+0.266
 horror+0.265
Bad+0.232
Neg logit contributions
nam-0.324
ooter-0.306
ilda-0.291
ooters-0.281
anna-0.278
Token happily
Token ID18177
Feature activation-1.15e+00

Pos logit contributions
aw+0.119
Run+0.116
 horror+0.104
oc+0.104
Is+0.095
Neg logit contributions
nam-0.107
ooter-0.100
anna-0.098
ilda-0.096
lee-0.094
Token.
Token ID13
Feature activation-1.60e+00

Pos logit contributions
aw+0.064
Run+0.059
oc+0.053
 horror+0.050
Is+0.045
Neg logit contributions
nam-0.068
ooter-0.060
ilda-0.060
anna-0.057
 Jackie-0.057
Token The
Token ID383
Feature activation-8.69e-01

Pos logit contributions
aw+0.087
Run+0.085
oc+0.077
 horror+0.075
Is+0.070
Neg logit contributions
nam-0.091
ooter-0.083
anna-0.081
ilda-0.081
lee-0.078
Token end
Token ID886
Feature activation-6.76e+00

Pos logit contributions
aw+0.045
Run+0.044
 horror+0.038
oc+0.038
Is+0.035
Neg logit contributions
nam-0.051
anna-0.048
ooter-0.048
ilda-0.047
lee-0.046
Token.
Token ID13
Feature activation-6.95e-01

Pos logit contributions
aw+0.392
Run+0.381
oc+0.344
 horror+0.342
Is+0.312
Neg logit contributions
nam-0.371
ooter-0.334
anna-0.327
ilda-0.320
lee-0.314
Token<|endoftext|>
Token ID50256
Feature activation-1.93e+00

Pos logit contributions
aw+0.040
Run+0.039
oc+0.035
 horror+0.035
Is+0.032
Neg logit contributions
nam-0.037
ooter-0.034
anna-0.034
ilda-0.033
lee-0.032
TokenOnce
Token ID7454
Feature activation+2.42e+00

Pos logit contributions
aw+0.099
Run+0.095
oc+0.085
 horror+0.083
Is+0.077
Neg logit contributions
nam-0.118
ooter-0.108
anna-0.107
ilda-0.104
lee-0.102
Token upon
Token ID2402
Feature activation+1.28e+00

Pos logit contributions
nam+0.097
ooter+0.086
anna+0.084
any+0.083
inations+0.080
Neg logit contributions
aw-0.157
 horror-0.147
Run-0.145
oc-0.138
 disaster-0.137
Token a
Token ID257
Feature activation-8.21e-02

Pos logit contributions
nam+0.071
ooter+0.066
anna+0.065
ilda+0.064
lee+0.063
Neg logit contributions
aw-0.070
Run-0.069
oc-0.061
 horror-0.061
Is-0.056
Token it
Token ID340
Feature activation-4.27e+00

Pos logit contributions
nam+0.014
anna+0.012
ooter+0.012
ilda+0.012
lee+0.012
Neg logit contributions
aw-0.015
Run-0.015
oc-0.014
 horror-0.013
Is-0.012
Token flew
Token ID13112
Feature activation-1.37e+00

Pos logit contributions
aw+0.215
Run+0.200
oc+0.172
 horror+0.169
 disaster+0.160
Neg logit contributions
nam-0.261
ilda-0.234
anna-0.233
ooter-0.231
lee-0.229
Token away
Token ID1497
Feature activation-1.73e+00

Pos logit contributions
aw+0.075
Run+0.069
oc+0.056
 horror+0.055
Bad+0.052
Neg logit contributions
nam-0.083
ilda-0.076
anna-0.075
ooter-0.074
inations-0.073
Token.
Token ID13
Feature activation-1.27e+00

Pos logit contributions
aw+0.082
Run+0.079
 horror+0.070
oc+0.069
 disaster+0.061
Neg logit contributions
nam-0.107
ooter-0.103
ilda-0.101
anna-0.099
lee-0.095
Token The
Token ID383
Feature activation-7.11e-01

Pos logit contributions
aw+0.066
Run+0.065
oc+0.058
 horror+0.057
Is+0.053
Neg logit contributions
nam-0.074
ooter-0.068
ilda-0.067
anna-0.066
inations-0.065
Token end
Token ID886
Feature activation-6.74e+00

Pos logit contributions
aw+0.038
Run+0.037
oc+0.033
 horror+0.032
Is+0.030
Neg logit contributions
nam-0.040
anna-0.038
ooter-0.038
ilda-0.037
lee-0.036
Token.
Token ID13
Feature activation-6.09e-01

Pos logit contributions
aw+0.359
Run+0.353
oc+0.318
 horror+0.309
Is+0.277
Neg logit contributions
nam-0.420
ooter-0.363
ilda-0.354
anna-0.354
ppa-0.349
Token<|endoftext|>
Token ID50256
Feature activation-1.89e+00

Pos logit contributions
aw+0.034
Run+0.034
oc+0.030
 horror+0.030
Is+0.028
Neg logit contributions
nam-0.033
ooter-0.030
anna-0.030
ilda-0.029
lee-0.029
TokenOnce
Token ID7454
Feature activation+2.44e+00

Pos logit contributions
aw+0.098
Run+0.095
oc+0.085
 horror+0.083
Is+0.077
Neg logit contributions
nam-0.114
ooter-0.104
anna-0.103
ilda-0.100
lee-0.099
Token upon
Token ID2402
Feature activation+1.31e+00

Pos logit contributions
nam+0.099
ooter+0.087
anna+0.084
any+0.083
inations+0.081
Neg logit contributions
aw-0.159
 horror-0.146
Run-0.145
oc-0.139
 disaster-0.135
Token a
Token ID257
Feature activation-1.40e-01

Pos logit contributions
nam+0.074
ooter+0.069
anna+0.069
ilda+0.067
lee+0.066
Neg logit contributions
aw-0.071
Run-0.069
oc-0.061
 horror-0.061
Is-0.056
Token and
Token ID290
Feature activation-3.40e-01

Pos logit contributions
aw+0.148
Run+0.145
oc+0.129
 horror+0.128
Is+0.118
Neg logit contributions
nam-0.150
ooter-0.138
anna-0.137
ilda-0.134
lee-0.132
Token he
Token ID339
Feature activation-1.36e+00

Pos logit contributions
aw+0.020
Run+0.019
 horror+0.017
oc+0.017
Is+0.016
Neg logit contributions
nam-0.017
anna-0.016
ooter-0.016
ilda-0.016
lee-0.015
Token didn
Token ID1422
Feature activation+2.55e+00

Pos logit contributions
aw+0.076
Run+0.074
oc+0.067
 horror+0.066
Is+0.060
Neg logit contributions
nam-0.075
ooter-0.068
anna-0.067
ilda-0.065
lee-0.065
Token't
Token ID470
Feature activation+1.48e+00

Pos logit contributions
nam+0.088
ooter+0.084
anna+0.081
ilda+0.080
lee+0.074
Neg logit contributions
aw-0.189
Run-0.184
oc-0.172
 horror-0.169
Is-0.157
Token know
Token ID760
Feature activation+2.79e+00

Pos logit contributions
nam+0.082
aj+0.077
lee+0.073
ilda+0.071
anna+0.069
Neg logit contributions
Run-0.082
aw-0.081
oc-0.074
 horror-0.073
Is-0.064
Token how
Token ID703
Feature activation+6.22e+00

Pos logit contributions
nam+0.150
anna+0.142
ooter+0.141
ilda+0.138
lee+0.137
Neg logit contributions
aw-0.158
Run-0.145
 horror-0.134
oc-0.130
Is-0.124
Token he
Token ID339
Feature activation-1.38e+00

Pos logit contributions
nam+0.347
ppa+0.330
enna+0.317
ilda+0.313
anna+0.310
Neg logit contributions
aw-0.334
Run-0.327
 disaster-0.277
 horror-0.266
oc-0.265
Token could
Token ID714
Feature activation+1.65e+00

Pos logit contributions
aw+0.065
Run+0.063
oc+0.057
 horror+0.052
Is+0.048
Neg logit contributions
nam-0.090
ooter-0.081
anna-0.080
lee-0.079
 Jackie-0.079
Token do
Token ID466
Feature activation-3.20e+00

Pos logit contributions
nam+0.084
ooter+0.077
anna+0.076
ilda+0.074
lee+0.073
Neg logit contributions
aw-0.098
Run-0.097
oc-0.087
 horror-0.087
Is-0.080
Token it
Token ID340
Feature activation-6.45e-01

Pos logit contributions
aw+0.153
Run+0.145
oc+0.129
 horror+0.128
Is+0.116
Neg logit contributions
nam-0.202
ooter-0.186
anna-0.185
lee-0.179
ilda-0.179
Token.
Token ID13
Feature activation-4.13e-01

Pos logit contributions
aw+0.030
Run+0.029
oc+0.026
 horror+0.024
 disaster+0.023
Neg logit contributions
nam-0.041
anna-0.038
lee-0.037
aj-0.036
ppa-0.036
Token hopped
Token ID45230
Feature activation-6.83e-01

Pos logit contributions
nam+0.143
ooter+0.134
anna+0.129
ilda+0.128
ooters+0.124
Neg logit contributions
aw-0.148
Run-0.146
oc-0.127
 horror-0.124
Is-0.113
Token away
Token ID1497
Feature activation-5.38e-01

Pos logit contributions
aw+0.038
Run+0.037
oc+0.033
 horror+0.033
Is+0.030
Neg logit contributions
nam-0.038
ooter-0.035
anna-0.035
ilda-0.034
lee-0.033
Token,
Token ID11
Feature activation-2.78e-02

Pos logit contributions
aw+0.028
Run+0.028
 horror+0.025
oc+0.024
Is+0.022
Neg logit contributions
nam-0.031
ooter-0.029
anna-0.029
ilda-0.028
lee-0.027
Token no
Token ID645
Feature activation-4.89e+00

Pos logit contributions
aw+0.002
Run+0.002
 horror+0.001
oc+0.001
Is+0.001
Neg logit contributions
nam-0.001
ooter-0.001
anna-0.001
ilda-0.001
lee-0.001
Token matter
Token ID2300
Feature activation-2.85e+00

Pos logit contributions
aw+0.300
Run+0.293
oc+0.264
 horror+0.262
Is+0.248
Neg logit contributions
nam-0.240
anna-0.223
ooter-0.221
ilda-0.213
lee-0.209
Token how
Token ID703
Feature activation+6.27e+00

Pos logit contributions
aw+0.151
Run+0.145
 horror+0.131
oc+0.126
Is+0.116
Neg logit contributions
nam-0.158
ooter-0.156
anna-0.151
ilda-0.146
 handsome-0.146
Token the
Token ID262
Feature activation+6.92e-01

Pos logit contributions
nam+0.359
ooter+0.358
anna+0.325
ilda+0.321
ppa+0.317
Neg logit contributions
Run-0.348
aw-0.332
oc-0.281
 horror-0.280
 disaster-0.272
Token monster
Token ID9234
Feature activation-3.20e+00

Pos logit contributions
nam+0.040
ooter+0.037
anna+0.037
ilda+0.036
lee+0.035
Neg logit contributions
aw-0.037
Run-0.037
oc-0.033
 horror-0.032
Is-0.030
Token yelled
Token ID22760
Feature activation+3.36e-01

Pos logit contributions
aw+0.184
Run+0.180
oc+0.162
 horror+0.159
Is+0.146
Neg logit contributions
nam-0.171
ooter-0.156
anna-0.153
ilda-0.150
lee-0.149
Token.
Token ID13
Feature activation+6.80e-02

Pos logit contributions
nam+0.019
ooter+0.018
anna+0.017
ilda+0.017
inations+0.016
Neg logit contributions
aw-0.019
Run-0.018
 horror-0.016
oc-0.016
Is-0.014
Token
Token ID198
Feature activation-2.24e-01

Pos logit contributions
nam+0.004
ooter+0.004
inations+0.004
anna+0.004
ilda+0.004
Neg logit contributions
aw-0.003
Run-0.003
oc-0.003
 horror-0.003
Is-0.003
Token
Token ID198
Feature activation-3.43e-01

Pos logit contributions
aw+0.014
oc+0.013
Run+0.013
Is+0.011
 horror+0.010
Neg logit contributions
nam-0.026
ooter-0.022
lee-0.022
anna-0.021
ilda-0.021
TokenL
Token ID43
Feature activation+5.96e-01

Pos logit contributions
aw+0.016
Run+0.016
 horror+0.014
oc+0.014
Is+0.012
Neg logit contributions
nam-0.022
ooter-0.020
anna-0.020
ilda-0.020
lee-0.019
Tokenily
Token ID813
Feature activation+2.87e-01

Pos logit contributions
nam+0.034
ooter+0.031
anna+0.031
ilda+0.030
lee+0.030
Neg logit contributions
aw-0.032
Run-0.032
oc-0.028
 horror-0.028
Is-0.026
Token showed
Token ID3751
Feature activation+6.35e-01

Pos logit contributions
nam+0.015
ooter+0.013
anna+0.013
ilda+0.013
lee+0.013
Neg logit contributions
aw-0.017
Run-0.017
oc-0.015
 horror-0.015
Is-0.014
Token Max
Token ID5436
Feature activation-3.72e-01

Pos logit contributions
nam+0.035
ooter+0.032
anna+0.032
ilda+0.032
lee+0.031
Neg logit contributions
aw-0.035
Run-0.034
oc-0.031
 horror-0.030
Is-0.028
Token how
Token ID703
Feature activation+6.17e+00

Pos logit contributions
aw+0.020
Run+0.019
 horror+0.017
oc+0.017
Is+0.015
Neg logit contributions
nam-0.021
ooter-0.020
anna-0.020
ilda-0.019
aj-0.018
Token to
Token ID284
Feature activation+3.71e-01

Pos logit contributions
nam+0.310
aj+0.301
anna+0.298
ilda+0.293
ooter+0.290
Neg logit contributions
aw-0.358
Run-0.333
oc-0.287
Bad-0.285
 horror-0.281
Token pretend
Token ID16614
Feature activation-7.86e-01

Pos logit contributions
nam+0.017
anna+0.015
ooter+0.015
ilda+0.015
lee+0.014
Neg logit contributions
aw-0.024
Run-0.024
oc-0.022
 horror-0.022
Is-0.020
Token to
Token ID284
Feature activation+3.79e-01

Pos logit contributions
aw+0.040
Run+0.040
oc+0.035
 horror+0.035
Is+0.032
Neg logit contributions
nam-0.046
ooter-0.043
anna-0.042
ilda-0.042
lee-0.041
Token be
Token ID307
Feature activation-1.21e+00

Pos logit contributions
nam+0.017
ooter+0.015
anna+0.015
ilda+0.015
lee+0.014
Neg logit contributions
aw-0.025
Run-0.025
 horror-0.022
oc-0.022
Is-0.021
Token a
Token ID257
Feature activation-1.07e-01

Pos logit contributions
aw+0.062
Run+0.054
oc+0.053
 horror+0.048
Bad+0.045
Neg logit contributions
nam-0.073
anna-0.071
ooter-0.069
ilda-0.068
ail-0.065
Token girl
Token ID2576
Feature activation-9.42e-01

Pos logit contributions
nam+0.075
ooter+0.073
anna+0.073
ilda+0.070
lee+0.069
Neg logit contributions
aw-0.058
Run-0.058
 horror-0.050
oc-0.048
Is-0.045
Token was
Token ID373
Feature activation-1.91e+00

Pos logit contributions
aw+0.045
Run+0.041
oc+0.039
 horror+0.038
Is+0.034
Neg logit contributions
nam-0.061
ooter-0.056
ooters-0.053
ilda-0.053
anna-0.053
Token very
Token ID845
Feature activation+3.22e+00

Pos logit contributions
aw+0.114
 horror+0.107
Run+0.098
Is+0.091
oc+0.090
Neg logit contributions
nam-0.094
ooter-0.093
ooters-0.091
anna-0.087
ilda-0.085
Token happy
Token ID3772
Feature activation+1.47e+00

Pos logit contributions
ooter+0.157
ooters+0.148
ilda+0.148
anna+0.143
nam+0.142
Neg logit contributions
aw-0.184
 horror-0.181
Run-0.170
oc-0.161
Is-0.156
Token with
Token ID351
Feature activation-1.14e+00

Pos logit contributions
nam+0.081
ooter+0.075
anna+0.074
ilda+0.072
lee+0.071
Neg logit contributions
aw-0.082
Run-0.080
oc-0.072
 horror-0.072
Is-0.066
Token how
Token ID703
Feature activation+6.39e+00

Pos logit contributions
aw+0.066
 horror+0.064
Run+0.062
oc+0.054
Is+0.054
Neg logit contributions
ooter-0.059
anna-0.057
nam-0.055
aj-0.054
ooters-0.053
Token it
Token ID340
Feature activation-4.87e-01

Pos logit contributions
ooter+0.408
ooters+0.367
aj+0.343
ppa+0.339
anna+0.339
Neg logit contributions
aw-0.324
Run-0.250
 disaster-0.249
 another-0.236
 horror-0.235
Token looked
Token ID3114
Feature activation+3.32e+00

Pos logit contributions
aw+0.022
Run+0.021
oc+0.019
 horror+0.018
Is+0.018
Neg logit contributions
nam-0.031
ooter-0.030
ooters-0.029
anna-0.028
aj-0.027
Token.
Token ID13
Feature activation-9.83e-02

Pos logit contributions
nam+0.201
ooter+0.198
anna+0.190
ooters+0.188
ilda+0.186
Neg logit contributions
aw-0.168
Run-0.139
oc-0.131
 horror-0.128
 disaster-0.120
Token<|endoftext|>
Token ID50256
Feature activation-1.85e+00

Pos logit contributions
aw+0.005
Run+0.004
oc+0.004
 horror+0.004
Is+0.004
Neg logit contributions
nam-0.006
ooter-0.006
inations-0.006
 handsome-0.006
anna-0.006
TokenOnce
Token ID7454
Feature activation+2.75e+00

Pos logit contributions
aw+0.091
Run+0.088
oc+0.078
 horror+0.076
Is+0.070
Neg logit contributions
nam-0.115
ooter-0.107
anna-0.106
ilda-0.103
lee-0.102
Token with
Token ID351
Feature activation-9.38e-01

Pos logit contributions
nam+0.077
ooter+0.071
anna+0.071
ilda+0.069
lee+0.069
Neg logit contributions
aw-0.070
Run-0.069
oc-0.061
 horror-0.061
Is-0.056
Token joy
Token ID8716
Feature activation+7.32e-01

Pos logit contributions
aw+0.061
Run+0.061
oc+0.055
 horror+0.053
Is+0.051
Neg logit contributions
nam-0.043
lee-0.037
ooter-0.037
anna-0.036
 Jackie-0.036
Token when
Token ID618
Feature activation-1.53e+00

Pos logit contributions
nam+0.047
ooter+0.045
anna+0.042
ooters+0.042
inations+0.040
Neg logit contributions
aw-0.035
Run-0.031
oc-0.028
 horror-0.028
Is-0.025
Token he
Token ID339
Feature activation-1.17e+00

Pos logit contributions
aw+0.081
Run+0.079
oc+0.071
 horror+0.069
Is+0.063
Neg logit contributions
nam-0.089
ooter-0.081
anna-0.080
ilda-0.079
lee-0.078
Token saw
Token ID2497
Feature activation-7.39e-02

Pos logit contributions
aw+0.072
Run+0.072
 horror+0.065
oc+0.065
Is+0.060
Neg logit contributions
nam-0.055
anna-0.050
ooter-0.050
ilda-0.049
lee-0.049
Token how
Token ID703
Feature activation+6.48e+00

Pos logit contributions
aw+0.004
Run+0.004
 horror+0.003
oc+0.003
Is+0.003
Neg logit contributions
nam-0.004
ooter-0.004
anna-0.004
ilda-0.004
lee-0.004
Token beautiful
Token ID4950
Feature activation+7.17e-01

Pos logit contributions
ooter+0.330
anna+0.312
aj+0.296
ppa+0.291
nam+0.289
Neg logit contributions
aw-0.419
Run-0.363
 horror-0.320
 disaster-0.318
oc-0.312
Token it
Token ID340
Feature activation-3.57e-01

Pos logit contributions
nam+0.041
anna+0.037
ooter+0.037
lee+0.037
ilda+0.036
Neg logit contributions
Run-0.037
aw-0.037
 horror-0.033
oc-0.033
Is-0.030
Token looked
Token ID3114
Feature activation+3.51e+00

Pos logit contributions
aw+0.016
Run+0.016
oc+0.013
 horror+0.013
Is+0.012
Neg logit contributions
nam-0.024
ooter-0.022
anna-0.022
ilda-0.021
lee-0.021
Token.
Token ID13
Feature activation+3.59e-01

Pos logit contributions
nam+0.215
ooter+0.199
anna+0.198
ilda+0.190
lee+0.186
Neg logit contributions
aw-0.182
Run-0.160
oc-0.150
 horror-0.146
Is-0.131
Token
Token ID198
Feature activation+1.16e-02

Pos logit contributions
nam+0.023
ooter+0.021
anna+0.021
ilda+0.020
ppa+0.020
Neg logit contributions
aw-0.017
Run-0.016
oc-0.015
 horror-0.015
Is-0.014
Token favorite
Token ID4004
Feature activation-2.73e+00

Pos logit contributions
aw+0.140
Run+0.132
 horror+0.126
oc+0.124
Bad+0.108
Neg logit contributions
nam-0.130
anna-0.126
ilda-0.124
lee-0.119
ooter-0.118
Token drink
Token ID4144
Feature activation-2.74e+00

Pos logit contributions
aw+0.142
Run+0.136
oc+0.129
 horror+0.123
Is+0.111
Neg logit contributions
nam-0.157
ooter-0.146
anna-0.145
ilda-0.144
lee-0.142
Token.
Token ID13
Feature activation-8.43e-01

Pos logit contributions
aw+0.159
Run+0.158
oc+0.142
 horror+0.142
Is+0.131
Neg logit contributions
nam-0.140
ooter-0.130
anna-0.128
ilda-0.124
lee-0.122
Token He
Token ID679
Feature activation-1.28e+00

Pos logit contributions
aw+0.043
Run+0.042
oc+0.039
 horror+0.037
Is+0.035
Neg logit contributions
nam-0.049
ooter-0.046
ilda-0.045
anna-0.044
inations-0.043
Token proudly
Token ID23017
Feature activation+3.03e-01

Pos logit contributions
aw+0.075
Run+0.073
oc+0.065
 horror+0.065
Is+0.060
Neg logit contributions
nam-0.067
ooter-0.062
anna-0.060
ilda-0.059
lee-0.057
Token took
Token ID1718
Feature activation+9.72e-01

Pos logit contributions
nam+0.016
ooter+0.015
ooters+0.013
ilda+0.013
anna+0.013
Neg logit contributions
aw-0.018
Run-0.018
oc-0.016
 horror-0.016
Is-0.015
Token it
Token ID340
Feature activation-5.97e-01

Pos logit contributions
nam+0.057
ooter+0.053
anna+0.053
ilda+0.051
lee+0.050
Neg logit contributions
aw-0.051
Run-0.049
oc-0.044
 horror-0.043
Is-0.040
Token and
Token ID290
Feature activation+6.69e-02

Pos logit contributions
aw+0.034
Run+0.032
oc+0.030
 horror+0.029
Is+0.026
Neg logit contributions
nam-0.032
anna-0.029
lee-0.028
ooter-0.028
ilda-0.028
Token marched
Token ID23558
Feature activation+2.06e+00

Pos logit contributions
nam+0.003
anna+0.003
ooter+0.003
ilda+0.003
lee+0.003
Neg logit contributions
aw-0.004
Run-0.004
oc-0.004
 horror-0.004
Is-0.003
Token back
Token ID736
Feature activation-8.54e-01

Pos logit contributions
nam+0.116
ooter+0.103
anna+0.103
ilda+0.100
aj+0.099
Neg logit contributions
aw-0.113
Run-0.107
 horror-0.096
oc-0.096
Is-0.088
Token to
Token ID284
Feature activation+5.84e-01

Pos logit contributions
aw+0.042
oc+0.040
Run+0.038
 horror+0.036
cer+0.035
Neg logit contributions
nam-0.047
inations-0.043
ppa-0.042
lee-0.042
anna-0.041
Token a
Token ID257
Feature activation+1.27e-01

Pos logit contributions
Run+0.014
aw+0.014
oc+0.013
 horror+0.012
Is+0.012
Neg logit contributions
nam-0.013
anna-0.012
ilda-0.012
ooter-0.011
 Jackie-0.011
Token microphone
Token ID21822
Feature activation+1.48e+00

Pos logit contributions
nam+0.006
ooter+0.005
ilda+0.005
anna+0.005
 handsome+0.005
Neg logit contributions
aw-0.008
Run-0.008
oc-0.008
 horror-0.008
Is-0.007
Token and
Token ID290
Feature activation+3.31e-03

Pos logit contributions
nam+0.081
ooter+0.074
anna+0.074
ilda+0.071
lee+0.071
Neg logit contributions
aw-0.083
Run-0.081
oc-0.072
 horror-0.071
Is-0.065
Token wanted
Token ID2227
Feature activation+1.43e+00

Pos logit contributions
nam+0.000
ooter+0.000
anna+0.000
ilda+0.000
lee+0.000
Neg logit contributions
aw-0.000
Run-0.000
 horror-0.000
oc-0.000
Is-0.000
Token to
Token ID284
Feature activation+5.70e-01

Pos logit contributions
nam+0.055
ooter+0.050
anna+0.049
ilda+0.047
lee+0.046
Neg logit contributions
aw-0.103
Run-0.100
 horror-0.092
oc-0.090
Is-0.086
Token play
Token ID711
Feature activation+1.81e+00

Pos logit contributions
nam+0.030
anna+0.028
ooter+0.027
ilda+0.027
aj+0.027
Neg logit contributions
Run-0.033
aw-0.031
 horror-0.029
oc-0.028
Is-0.027
Token.
Token ID13
Feature activation+5.25e-01

Pos logit contributions
nam+0.093
anna+0.084
 handsome+0.082
ooter+0.081
ilda+0.081
Neg logit contributions
Run-0.105
aw-0.105
 horror-0.096
oc-0.092
Is-0.086
Token But
Token ID887
Feature activation-3.21e+00

Pos logit contributions
nam+0.027
anna+0.022
 Emmy+0.022
 handsome+0.022
ooter+0.022
Neg logit contributions
aw-0.031
Run-0.028
oc-0.025
 horror-0.025
 course-0.025
Token a
Token ID257
Feature activation+8.27e-02

Pos logit contributions
aw+0.183
Run+0.174
oc+0.161
 horror+0.153
Is+0.140
Neg logit contributions
nam-0.180
ooter-0.158
anna-0.157
 Jackie-0.156
ilda-0.155
Token man
Token ID582
Feature activation-2.10e+00

Pos logit contributions
nam+0.004
ooter+0.003
anna+0.003
ilda+0.003
lee+0.003
Neg logit contributions
aw-0.005
Run-0.005
oc-0.005
 horror-0.005
Is-0.004
Token yelled
Token ID22760
Feature activation+6.60e-01

Pos logit contributions
aw+0.112
Run+0.110
 horror+0.098
oc+0.097
Is+0.090
Neg logit contributions
nam-0.118
ooter-0.110
anna-0.110
ilda-0.106
lee-0.104
Token raining
Token ID43079
Feature activation+8.85e-01

Pos logit contributions
aw+0.125
Run+0.122
 horror+0.112
 disaster+0.105
Bad+0.101
Neg logit contributions
nam-0.113
ooter-0.106
anna-0.105
ilda-0.104
ouses-0.100
Token!"
Token ID2474
Feature activation-2.08e+00

Pos logit contributions
nam+0.047
lee+0.042
anna+0.042
ooter+0.042
ilda+0.040
Neg logit contributions
aw-0.052
Run-0.051
oc-0.044
 horror-0.043
 disaster-0.041
Token Lily
Token ID20037
Feature activation+3.31e-01

Pos logit contributions
aw+0.124
Run+0.122
oc+0.109
 horror+0.108
Is+0.100
Neg logit contributions
nam-0.105
ooter-0.097
anna-0.096
ilda-0.093
lee-0.092
Token exclaimed
Token ID33552
Feature activation-4.68e-01

Pos logit contributions
nam+0.018
ooter+0.016
anna+0.015
ilda+0.015
lee+0.015
Neg logit contributions
aw-0.019
Run-0.019
oc-0.017
 horror-0.017
Is-0.015
Token.
Token ID13
Feature activation+2.99e-01

Pos logit contributions
aw+0.023
Run+0.023
 horror+0.021
oc+0.019
 disaster+0.018
Neg logit contributions
nam-0.027
ooter-0.027
anna-0.025
ooters-0.025
ilda-0.025
Token
Token ID220
Feature activation+4.92e+00

Pos logit contributions
nam+0.017
inations+0.016
ooter+0.016
ilda+0.015
anna+0.015
Neg logit contributions
aw-0.016
Run-0.016
 horror-0.014
Is-0.013
oc-0.013
Token
Token ID198
Feature activation-1.41e-01

Pos logit contributions
nam+0.347
ooter+0.307
anna+0.304
 handsome+0.303
inations+0.298
Neg logit contributions
aw-0.214
Run-0.195
 horror-0.168
oc-0.164
Is-0.151
Token
Token ID198
Feature activation-1.87e-01

Pos logit contributions
aw+0.006
Run+0.006
oc+0.005
Is+0.005
 horror+0.005
Neg logit contributions
nam-0.010
ooter-0.009
ilda-0.008
 handsome-0.008
inations-0.008
Token"
Token ID1
Feature activation+5.62e-02

Pos logit contributions
aw+0.009
Run+0.008
 horror+0.008
oc+0.007
Is+0.007
Neg logit contributions
nam-0.012
anna-0.011
ooter-0.011
ilda-0.011
lee-0.011
TokenIt
Token ID1026
Feature activation+5.21e-01

Pos logit contributions
nam+0.004
 Emmy+0.003
 Jackie+0.003
anna+0.003
any+0.003
Neg logit contributions
aw-0.003
oc-0.002
 horror-0.002
Run-0.002
 beast-0.002
Token's
Token ID338
Feature activation-2.17e+00

Pos logit contributions
nam+0.039
ooter+0.036
anna+0.035
ilda+0.034
lee+0.034
Neg logit contributions
aw-0.020
Run-0.019
oc-0.016
 horror-0.016
Is-0.014
Token realised
Token ID19169
Feature activation-4.28e+00

Pos logit contributions
nam+0.114
anna+0.106
ooter+0.106
ilda+0.101
aj+0.099
Neg logit contributions
aw-0.102
Run-0.093
 horror-0.091
oc-0.084
Is-0.080
Token that
Token ID326
Feature activation-1.61e+00

Pos logit contributions
aw+0.192
Run+0.174
 horror+0.147
oc+0.145
 disaster+0.131
Neg logit contributions
nam-0.286
ooter-0.277
anna-0.263
ooters-0.261
aj-0.255
Token its
Token ID663
Feature activation-3.60e+00

Pos logit contributions
aw+0.083
Run+0.081
 horror+0.072
oc+0.071
Is+0.065
Neg logit contributions
nam-0.093
ooter-0.090
anna-0.088
ilda-0.086
lee-0.084
Token friend
Token ID1545
Feature activation-1.69e+00

Pos logit contributions
aw+0.204
Run+0.191
 horror+0.184
oc+0.181
 disaster+0.163
Neg logit contributions
nam-0.189
ilda-0.172
anna-0.169
ooter-0.166
lee-0.162
Token had
Token ID550
Feature activation+1.41e+00

Pos logit contributions
aw+0.089
Run+0.083
oc+0.076
 horror+0.074
Is+0.065
Neg logit contributions
nam-0.104
ooter-0.093
ooters-0.089
anna-0.089
aj-0.087
Token been
Token ID587
Feature activation+1.02e+00

Pos logit contributions
nam+0.081
anna+0.076
ooter+0.075
ilda+0.071
ooters+0.070
Neg logit contributions
aw-0.080
Run-0.073
 horror-0.065
 disaster-0.061
Bad-0.060
Token trying
Token ID2111
Feature activation+1.95e+00

Pos logit contributions
nam+0.052
ooter+0.052
anna+0.049
ooters+0.049
ilda+0.048
Neg logit contributions
aw-0.060
Run-0.055
 horror-0.049
 disaster-0.049
Bad-0.048
Token to
Token ID284
Feature activation+3.38e-01

Pos logit contributions
nam+0.085
ooter+0.081
anna+0.080
ilda+0.076
aj+0.072
Neg logit contributions
aw-0.126
Run-0.121
 horror-0.114
oc-0.110
 disaster-0.106
Token help
Token ID1037
Feature activation-3.19e-02

Pos logit contributions
nam+0.017
anna+0.016
ooter+0.015
ilda+0.015
lee+0.015
Neg logit contributions
Run-0.020
aw-0.020
 horror-0.018
oc-0.018
Is-0.017
Token it
Token ID340
Feature activation-8.73e-01

Pos logit contributions
aw+0.002
Run+0.002
oc+0.002
 horror+0.002
Is+0.001
Neg logit contributions
nam-0.002
ooter-0.002
anna-0.002
aj-0.002
ilda-0.002
Token and
Token ID290
Feature activation+5.46e-03

Pos logit contributions
aw+0.044
Run+0.044
oc+0.042
 horror+0.040
Is+0.036
Neg logit contributions
nam-0.052
anna-0.046
ooter-0.045
ilda-0.045
lee-0.044
Token reached
Token ID4251
Feature activation-8.96e-01

Pos logit contributions
nam+0.014
anna+0.014
ooter+0.014
lee+0.013
ilda+0.013
Neg logit contributions
aw-0.022
Run-0.021
 horror-0.020
oc-0.019
Bad-0.018
Token the
Token ID262
Feature activation+6.18e-01

Pos logit contributions
aw+0.044
Run+0.042
 horror+0.039
oc+0.036
Is+0.034
Neg logit contributions
nam-0.055
anna-0.051
ooter-0.051
ilda-0.049
lee-0.048
Token temple
Token ID12505
Feature activation+4.31e-01

Pos logit contributions
nam+0.035
ooter+0.033
anna+0.031
ilda+0.031
 handsome+0.030
Neg logit contributions
Run-0.033
aw-0.032
oc-0.029
 horror-0.028
Is-0.026
Token,
Token ID11
Feature activation-1.40e-01

Pos logit contributions
nam+0.022
ooter+0.021
anna+0.020
ilda+0.020
lee+0.020
Neg logit contributions
aw-0.025
Run-0.025
oc-0.022
 horror-0.022
Is-0.020
Token the
Token ID262
Feature activation+6.50e-01

Pos logit contributions
Run+0.008
aw+0.008
 horror+0.007
oc+0.007
Is+0.007
Neg logit contributions
ooter-0.007
nam-0.007
anna-0.007
lee-0.007
ooters-0.006
Token little
Token ID1310
Feature activation+1.06e+00

Pos logit contributions
nam+0.039
anna+0.038
ooter+0.037
ilda+0.037
aj+0.036
Neg logit contributions
aw-0.033
Run-0.031
 horror-0.027
oc-0.027
Is-0.025
Token girl
Token ID2576
Feature activation-1.12e+00

Pos logit contributions
nam+0.061
ooter+0.056
anna+0.056
ilda+0.054
lee+0.054
Neg logit contributions
aw-0.056
Run-0.055
oc-0.049
 horror-0.048
Is-0.044
Token gazed
Token ID50255
Feature activation+1.48e+00

Pos logit contributions
aw+0.067
Run+0.066
oc+0.059
 horror+0.059
Is+0.055
Neg logit contributions
nam-0.056
ooter-0.051
anna-0.051
ilda-0.050
lee-0.049
Token in
Token ID287
Feature activation+1.38e+00

Pos logit contributions
nam+0.091
ooter+0.087
anna+0.086
ilda+0.086
inations+0.083
Neg logit contributions
aw-0.074
Run-0.068
 horror-0.060
oc-0.055
Is-0.052
Token wonder
Token ID4240
Feature activation-5.62e-01

Pos logit contributions
nam+0.079
 Jackie+0.071
lee+0.071
 blank+0.069
 pretty+0.069
Neg logit contributions
aw-0.073
Run-0.070
oc-0.067
Is-0.057
Too-0.056
Token.
Token ID13
Feature activation-3.29e-01

Pos logit contributions
aw+0.030
Run+0.026
 horror+0.025
oc+0.023
Is+0.021
Neg logit contributions
nam-0.034
ooter-0.032
anna-0.031
ilda-0.030
 Jackie-0.030
Token yellow
Token ID7872
Feature activation+6.32e-01

Pos logit contributions
aw+0.008
Run+0.008
oc+0.007
 horror+0.007
Is+0.007
Neg logit contributions
anna-0.005
nam-0.005
lee-0.004
ilda-0.004
ooter-0.004
Token flower
Token ID15061
Feature activation-2.00e+00

Pos logit contributions
nam+0.030
ooter+0.029
anna+0.026
 Jackie+0.026
 Emmy+0.025
Neg logit contributions
aw-0.038
Run-0.038
 horror-0.036
oc-0.034
Is-0.032
Token in
Token ID287
Feature activation+1.31e+00

Pos logit contributions
Run+0.123
aw+0.121
 horror+0.111
oc+0.110
Is+0.101
Neg logit contributions
nam-0.097
ooter-0.090
anna-0.084
ilda-0.083
lee-0.082
Token the
Token ID262
Feature activation+5.89e-01

Pos logit contributions
nam+0.054
 Jackie+0.043
 Emmy+0.042
ilda+0.042
lee+0.041
Neg logit contributions
aw-0.095
Run-0.092
oc-0.087
 horror-0.084
Is-0.077
Token grass
Token ID8701
Feature activation-1.78e+00

Pos logit contributions
nam+0.032
ooter+0.029
anna+0.029
ilda+0.028
lee+0.028
Neg logit contributions
aw-0.033
Run-0.033
oc-0.029
 horror-0.029
Is-0.027
Token.
Token ID13
Feature activation-3.53e-01

Pos logit contributions
Run+0.124
aw+0.117
 horror+0.113
oc+0.112
Bad+0.103
Neg logit contributions
nam-0.069
ooter-0.064
anna-0.060
lee-0.059
ilda-0.059
Token It
Token ID632
Feature activation-2.20e-01

Pos logit contributions
aw+0.015
Run+0.014
Is+0.013
oc+0.013
 horror+0.013
Neg logit contributions
inations-0.024
nam-0.024
ooter-0.022
anna-0.022
ilda-0.022
Token made
Token ID925
Feature activation-1.35e+00

Pos logit contributions
aw+0.009
Run+0.009
oc+0.008
 horror+0.007
Is+0.007
Neg logit contributions
nam-0.015
ooter-0.014
anna-0.014
ilda-0.014
lee-0.014
Token her
Token ID607
Feature activation+1.97e+00

Pos logit contributions
aw+0.081
Run+0.077
 horror+0.069
oc+0.064
Is+0.063
Neg logit contributions
nam-0.069
ooter-0.069
anna-0.066
ooters-0.062
ilda-0.062
Token heart
Token ID2612
Feature activation-8.81e-01

Pos logit contributions
ilda+0.078
anna+0.077
nam+0.076
ooter+0.074
ppa+0.070
Neg logit contributions
aw-0.131
 horror-0.126
Run-0.125
oc-0.116
Is-0.107
Token happy
Token ID3772
Feature activation+1.34e+00

Pos logit contributions
aw+0.050
 horror+0.043
oc+0.042
Run+0.041
 disaster+0.040
Neg logit contributions
nam-0.042
ooter-0.040
anna-0.040
ooters-0.039
ilda-0.039
Token Tim
Token ID5045
Feature activation-2.09e-01

Pos logit contributions
nam+0.002
anna+0.001
ooter+0.001
ilda+0.001
inations+0.001
Neg logit contributions
aw-0.001
Run-0.001
oc-0.001
 horror-0.001
Is-0.001
Tokenmy
Token ID1820
Feature activation+4.84e+00

Pos logit contributions
aw+0.015
oc+0.014
Run+0.014
 horror+0.013
Bad+0.012
Neg logit contributions
nam-0.009
ooter-0.007
anna-0.007
ouses-0.007
ooters-0.007
Token!"
Token ID2474
Feature activation-2.28e+00

Pos logit contributions
nam+0.301
ooter+0.274
anna+0.268
ooters+0.256
ilda+0.255
Neg logit contributions
aw-0.245
Run-0.234
oc-0.226
 horror-0.207
Bad-0.175
Token Lily
Token ID20037
Feature activation+9.98e-02

Pos logit contributions
Run+0.127
aw+0.124
oc+0.111
 horror+0.109
Is+0.102
Neg logit contributions
nam-0.123
anna-0.118
ooter-0.117
ilda-0.111
inations-0.109
Token said
Token ID531
Feature activation+2.61e-01

Pos logit contributions
nam+0.006
ooter+0.006
inations+0.006
ooters+0.006
anna+0.006
Neg logit contributions
aw-0.004
Run-0.004
oc-0.004
 horror-0.004
 Ha-0.003
Token.
Token ID13
Feature activation-1.01e-01

Pos logit contributions
nam+0.016
ooter+0.015
inations+0.015
anna+0.015
aj+0.015
Neg logit contributions
Run-0.011
aw-0.011
 horror-0.011
oc-0.010
 disaster-0.009
Token
Token ID198
Feature activation-2.57e-01

Pos logit contributions
Run+0.005
aw+0.004
Is+0.004
 horror+0.004
oc+0.004
Neg logit contributions
nam-0.006
anna-0.006
inations-0.006
ppa-0.006
ooter-0.006
Token
Token ID198
Feature activation-2.83e-01

Pos logit contributions
aw+0.011
Run+0.011
oc+0.010
Is+0.009
 horror+0.009
Neg logit contributions
nam-0.018
ooter-0.016
anna-0.016
ilda-0.015
inations-0.015
Token"
Token ID1
Feature activation-2.07e-01

Pos logit contributions
aw+0.014
Run+0.013
 horror+0.012
oc+0.012
Is+0.010
Neg logit contributions
nam-0.018
ooter-0.016
anna-0.016
ilda-0.016
lee-0.016
TokenHi
Token ID17250
Feature activation+5.51e-02

Pos logit contributions
aw+0.010
Run+0.010
oc+0.009
 horror+0.009
Is+0.008
Neg logit contributions
nam-0.013
ooter-0.012
anna-0.012
ilda-0.012
lee-0.011
Token Lily
Token ID20037
Feature activation+1.45e-01

Pos logit contributions
nam+0.004
anna+0.003
ooter+0.003
ilda+0.003
inations+0.003
Neg logit contributions
aw-0.003
Run-0.002
oc-0.002
 horror-0.002
Is-0.002
Token do
Token ID466
Feature activation-3.07e+00

Pos logit contributions
nam+0.004
anna+0.003
ooter+0.003
lee+0.003
ilda+0.003
Neg logit contributions
aw-0.005
Run-0.005
oc-0.004
 horror-0.004
Is-0.004
Token it
Token ID340
Feature activation-4.59e-01

Pos logit contributions
aw+0.109
Run+0.100
 horror+0.086
oc+0.085
Bad+0.075
Neg logit contributions
nam-0.221
ooter-0.219
anna-0.217
aj-0.209
any-0.208
Token,
Token ID11
Feature activation+9.93e-02

Pos logit contributions
aw+0.020
Run+0.018
oc+0.017
 disaster+0.015
 horror+0.014
Neg logit contributions
nam-0.032
lee-0.029
anna-0.028
ooter-0.028
aj-0.027
Token Tim
Token ID5045
Feature activation+4.10e-02

Pos logit contributions
nam+0.005
ooter+0.005
anna+0.005
ilda+0.005
lee+0.005
Neg logit contributions
aw-0.006
Run-0.006
oc-0.005
 horror-0.005
Is-0.005
Tokenmy
Token ID1820
Feature activation+5.17e+00

Pos logit contributions
nam+0.002
rolling+0.002
ooter+0.001
anna+0.001
ooters+0.001
Neg logit contributions
aw-0.003
oc-0.003
Run-0.003
 horror-0.002
cer-0.002
Token!
Token ID0
Feature activation-4.81e-01

Pos logit contributions
nam+0.302
ooter+0.280
anna+0.263
lee+0.263
ooters+0.258
Neg logit contributions
aw-0.276
oc-0.265
Run-0.264
 horror-0.231
Bad-0.206
Token Keep
Token ID9175
Feature activation-6.53e-01

Pos logit contributions
aw+0.024
Run+0.024
oc+0.021
 horror+0.021
Is+0.019
Neg logit contributions
nam-0.029
ooter-0.027
anna-0.027
ilda-0.026
lee-0.026
Token trying
Token ID2111
Feature activation+2.17e+00

Pos logit contributions
aw+0.039
Run+0.039
 horror+0.035
oc+0.034
Is+0.032
Neg logit contributions
nam-0.032
ooter-0.030
anna-0.029
ilda-0.028
ooters-0.027
Token and
Token ID290
Feature activation-6.16e-02

Pos logit contributions
nam+0.144
ooter+0.134
anna+0.133
lee+0.133
ilda+0.132
Neg logit contributions
aw-0.090
Run-0.082
oc-0.078
 horror-0.076
 disaster-0.067
Token don
Token ID836
Feature activation+1.37e+00

Pos logit contributions
Run+0.003
aw+0.003
 horror+0.003
oc+0.003
Is+0.003
Neg logit contributions
nam-0.003
anna-0.003
ooter-0.003
ilda-0.003
lee-0.003
Token't
Token ID470
Feature activation+1.59e+00

Pos logit contributions
nam+0.048
ooter+0.043
ilda+0.043
anna+0.042
lee+0.039
Neg logit contributions
aw-0.102
Run-0.098
 horror-0.093
oc-0.092
Is-0.085
Token€
Token ID26391
Feature activation+1.67e-01

Pos logit contributions
aw+0.037
Run+0.035
oc+0.032
 horror+0.030
Is+0.029
Neg logit contributions
nam-0.032
ooter-0.027
anna-0.027
lee-0.026
 handsome-0.026
Token
Token ID198
Feature activation-4.24e-01

Pos logit contributions
nam+0.009
ooter+0.009
anna+0.009
ilda+0.008
lee+0.008
Neg logit contributions
aw-0.009
Run-0.009
oc-0.008
 horror-0.008
Is-0.007
Token
Token ID198
Feature activation-4.48e-01

Pos logit contributions
aw+0.017
Run+0.017
oc+0.015
Is+0.014
 horror+0.013
Neg logit contributions
nam-0.032
ooter-0.028
anna-0.027
ppa-0.026
ilda-0.026
TokenMax
Token ID11518
Feature activation-1.00e+00

Pos logit contributions
aw+0.020
Run+0.020
oc+0.017
 horror+0.017
Is+0.015
Neg logit contributions
nam-0.029
ooter-0.027
anna-0.027
ilda-0.026
lee-0.026
Token opened
Token ID4721
Feature activation+1.18e+00

Pos logit contributions
aw+0.049
Run+0.048
oc+0.043
 horror+0.040
Is+0.036
Neg logit contributions
nam-0.065
ooter-0.058
anna-0.056
ilda-0.054
inations-0.054
Token the
Token ID262
Feature activation+6.25e-01

Pos logit contributions
nam+0.074
ooter+0.071
anna+0.070
ilda+0.067
inations+0.065
Neg logit contributions
aw-0.057
Run-0.054
 horror-0.048
oc-0.048
Is-0.043
Token box
Token ID3091
Feature activation+9.77e-02

Pos logit contributions
anna+0.041
nam+0.041
ppa+0.038
lee+0.038
ooter+0.038
Neg logit contributions
aw-0.027
Run-0.026
 horror-0.024
oc-0.023
Is-0.021
Token,
Token ID11
Feature activation-1.76e-01

Pos logit contributions
nam+0.005
ooter+0.005
anna+0.005
ilda+0.005
lee+0.005
Neg logit contributions
Run-0.005
aw-0.005
oc-0.005
 horror-0.004
Is-0.004
Token and
Token ID290
Feature activation-3.33e-01

Pos logit contributions
aw+0.009
Run+0.009
 horror+0.008
oc+0.008
Is+0.007
Neg logit contributions
nam-0.010
ooter-0.010
anna-0.010
ilda-0.009
lee-0.009
Token to
Token ID284
Feature activation+3.06e-01

Pos logit contributions
aw+0.019
Run+0.018
oc+0.016
 horror+0.016
Is+0.015
Neg logit contributions
nam-0.018
ooter-0.017
anna-0.017
ilda-0.016
lee-0.016
Token the
Token ID262
Feature activation+6.11e-01

Pos logit contributions
nam+0.017
ooter+0.015
anna+0.015
ilda+0.015
lee+0.015
Neg logit contributions
aw-0.017
Run-0.017
 horror-0.015
oc-0.015
Is-0.014
Token Sammy
Token ID44067
Feature activation+2.59e+00

Pos logit contributions
aw+0.022
Run+0.020
oc+0.018
 horror+0.018
Is+0.017
Neg logit contributions
nam-0.023
anna-0.020
ooter-0.020
inations-0.020
ilda-0.020
Token wanted
Token ID2227
Feature activation+1.15e+00

Pos logit contributions
nam+0.155
ooter+0.143
ooters+0.132
lee+0.129
ilda+0.129
Neg logit contributions
aw-0.141
Run-0.138
oc-0.121
 horror-0.114
Is-0.106
Token to
Token ID284
Feature activation+3.11e-01

Pos logit contributions
nam+0.045
ooter+0.040
anna+0.040
ilda+0.038
lee+0.037
Neg logit contributions
aw-0.083
Run-0.080
 horror-0.075
oc-0.072
Is-0.069
Token arrive
Token ID9240
Feature activation-3.18e-02

Pos logit contributions
nam+0.017
ooter+0.015
anna+0.015
ilda+0.015
lee+0.015
Neg logit contributions
aw-0.017
Run-0.017
 horror-0.016
oc-0.016
Is-0.014
Token at
Token ID379
Feature activation-2.09e+00

Pos logit contributions
aw+0.002
Run+0.002
oc+0.001
 horror+0.001
Is+0.001
Neg logit contributions
nam-0.002
ooter-0.002
anna-0.002
ilda-0.002
lee-0.002
Token the
Token ID262
Feature activation+5.92e-01

Pos logit contributions
aw+0.104
Run+0.100
 horror+0.094
oc+0.090
Is+0.079
Neg logit contributions
nam-0.122
ooter-0.119
anna-0.119
lee-0.112
aj-0.111
Token truth
Token ID3872
Feature activation-7.87e-01

Pos logit contributions
nam+0.032
ooter+0.029
anna+0.028
ilda+0.028
lee+0.027
Neg logit contributions
aw-0.034
Run-0.033
oc-0.030
 horror-0.030
Is-0.027
Token and
Token ID290
Feature activation-2.27e-01

Pos logit contributions
aw+0.038
Run+0.035
oc+0.032
 horror+0.031
Is+0.028
Neg logit contributions
nam-0.049
ooter-0.045
anna-0.044
lee-0.044
ilda-0.043
Token understand
Token ID1833
Feature activation-5.30e-01

Pos logit contributions
Run+0.014
aw+0.014
 horror+0.013
oc+0.012
Is+0.011
Neg logit contributions
nam-0.011
ooter-0.010
anna-0.010
ilda-0.010
lee-0.010
Token it
Token ID340
Feature activation-6.18e-01

Pos logit contributions
aw+0.032
Run+0.031
oc+0.028
 horror+0.028
Is+0.026
Neg logit contributions
nam-0.027
ooter-0.025
anna-0.025
ilda-0.024
lee-0.024
Token,
Token ID11
Feature activation-1.11e-01

Pos logit contributions
aw+0.030
Run+0.029
 horror+0.026
oc+0.026
Is+0.023
Neg logit contributions
nam-0.039
ooter-0.036
anna-0.035
lee-0.034
ilda-0.033
TokenHer
Token ID9360
Feature activation-7.40e-02

Pos logit contributions
aw+0.015
Run+0.014
oc+0.013
 horror+0.013
Is+0.012
Neg logit contributions
nam-0.017
ooter-0.015
anna-0.015
ilda-0.015
lee-0.015
Token mom
Token ID1995
Feature activation-4.85e-01

Pos logit contributions
aw+0.003
 horror+0.003
Run+0.003
oc+0.003
Is+0.003
Neg logit contributions
nam-0.005
anna-0.005
ooter-0.004
ilda-0.004
 Jackie-0.004
Token replied
Token ID8712
Feature activation-1.73e-02

Pos logit contributions
aw+0.028
Run+0.027
oc+0.025
 horror+0.024
Is+0.022
Neg logit contributions
nam-0.027
ooter-0.024
anna-0.024
ilda-0.022
ooters-0.022
Token,
Token ID11
Feature activation-3.05e-01

Pos logit contributions
aw+0.001
Run+0.001
oc+0.001
 horror+0.001
Is+0.001
Neg logit contributions
nam-0.001
ooter-0.001
anna-0.001
ilda-0.001
ooters-0.001
Token "
Token ID366
Feature activation+4.68e-01

Pos logit contributions
Run+0.011
aw+0.011
Is+0.010
oc+0.008
 horror+0.008
Neg logit contributions
inations-0.022
ooter-0.022
ooters-0.021
nam-0.021
ouses-0.020
TokenNo
Token ID2949
Feature activation-4.87e+00

Pos logit contributions
nam+0.026
ooter+0.023
anna+0.022
ilda+0.022
 Jackie+0.022
Neg logit contributions
aw-0.026
 horror-0.025
Run-0.025
oc-0.023
 beast-0.020
Token,
Token ID11
Feature activation-2.41e-01

Pos logit contributions
aw+0.246
Run+0.240
 horror+0.218
oc+0.211
Is+0.185
Neg logit contributions
nam-0.300
ooter-0.271
anna-0.266
ilda-0.258
lee-0.256
Token we
Token ID356
Feature activation-1.37e+00

Pos logit contributions
aw+0.014
Run+0.013
 horror+0.012
oc+0.012
Is+0.011
Neg logit contributions
nam-0.013
ooter-0.012
anna-0.012
ilda-0.012
lee-0.011
Token can
Token ID460
Feature activation-9.42e-03

Pos logit contributions
Run+0.063
aw+0.061
oc+0.058
 horror+0.056
 disaster+0.047
Neg logit contributions
nam-0.085
anna-0.079
lee-0.078
aj-0.078
ilda-0.077
Token't
Token ID470
Feature activation+1.55e+00

Pos logit contributions
aw+0.001
Run+0.001
oc+0.000
 horror+0.000
Is+0.000
Neg logit contributions
nam-0.000
anna-0.000
ooter-0.000
lee-0.000
ilda-0.000
Token go
Token ID467
Feature activation-2.17e+00

Pos logit contributions
nam+0.084
ooter+0.073
anna+0.073
lee+0.071
ilda+0.071
Neg logit contributions
aw-0.090
Run-0.089
oc-0.081
 horror-0.078
Is-0.072
Token loved
Token ID6151
Feature activation+1.41e+00

Pos logit contributions
nam+0.020
ooter+0.019
anna+0.018
ilda+0.017
lee+0.017
Neg logit contributions
aw-0.022
Run-0.021
oc-0.020
 horror-0.019
Is-0.018
Token.
Token ID13
Feature activation-1.24e-01

Pos logit contributions
nam+0.080
ooter+0.075
anna+0.074
aj+0.070
ilda+0.070
Neg logit contributions
aw-0.077
Run-0.068
oc-0.065
 horror-0.063
Is-0.057
Token
Token ID198
Feature activation-4.49e-01

Pos logit contributions
aw+0.007
Run+0.006
oc+0.006
 horror+0.006
Is+0.005
Neg logit contributions
nam-0.007
ooter-0.007
anna-0.007
ilda-0.006
lee-0.006
Token
Token ID198
Feature activation-4.46e-01

Pos logit contributions
aw+0.023
Run+0.021
oc+0.020
 horror+0.018
Is+0.018
Neg logit contributions
nam-0.029
ooter-0.026
anna-0.025
ilda-0.025
lee-0.024
TokenThe
Token ID464
Feature activation-1.01e+00

Pos logit contributions
aw+0.020
Run+0.019
 horror+0.018
oc+0.016
Is+0.014
Neg logit contributions
nam-0.028
anna-0.027
ooter-0.027
ilda-0.026
lee-0.026
Token end
Token ID886
Feature activation-6.39e+00

Pos logit contributions
Run+0.040
aw+0.038
oc+0.036
 horror+0.033
Is+0.030
Neg logit contributions
nam-0.073
anna-0.070
ooter-0.069
ilda-0.067
aj-0.066
Token.
Token ID13
Feature activation-1.51e-01

Pos logit contributions
aw+0.366
Run+0.353
oc+0.327
 horror+0.319
Is+0.292
Neg logit contributions
nam-0.356
ooter-0.319
anna-0.315
ilda-0.306
lee-0.301
Token
Token ID220
Feature activation+4.75e+00

Pos logit contributions
Run+0.010
aw+0.010
 horror+0.009
oc+0.009
Bad+0.008
Neg logit contributions
nam-0.006
anna-0.005
 Jackie-0.005
ilda-0.005
 Emmy-0.005
Token
Token ID198
Feature activation-4.68e-01

Pos logit contributions
nam+0.356
anna+0.301
 fashionable+0.301
 blank+0.299
 handsome+0.299
Neg logit contributions
aw-0.208
Run-0.180
oc-0.167
 horror-0.150
Is-0.147
Token
Token ID198
Feature activation-4.71e-01

Pos logit contributions
Run+0.031
aw+0.031
 horror+0.029
oc+0.027
Is+0.025
Neg logit contributions
nam-0.018
anna-0.017
ooter-0.017
ilda-0.017
lee-0.016
TokenM
Token ID44
Feature activation-2.00e+00

Pos logit contributions
Run+0.025
 horror+0.025
aw+0.025
oc+0.021
cer+0.020
Neg logit contributions
nam-0.022
ilda-0.022
anna-0.021
ail-0.021
inations-0.021
Token crawl
Token ID27318
Feature activation-4.26e-01

Pos logit contributions
Run+0.076
aw+0.076
 horror+0.069
oc+0.068
Go+0.056
Neg logit contributions
nam-0.080
anna-0.075
ooter-0.074
ilda-0.073
lee-0.070
Token into
Token ID656
Feature activation-5.12e-01

Pos logit contributions
aw+0.030
Run+0.030
oc+0.027
 horror+0.027
Is+0.026
Neg logit contributions
nam-0.017
ooter-0.015
anna-0.015
ilda-0.014
lee-0.014
Token the
Token ID262
Feature activation+5.31e-01

Pos logit contributions
aw+0.032
Run+0.031
oc+0.028
 horror+0.026
Is+0.026
Neg logit contributions
nam-0.026
 Jackie-0.022
lee-0.021
ilda-0.021
 Emmy-0.021
Token hay
Token ID27678
Feature activation-2.44e+00

Pos logit contributions
nam+0.029
ooter+0.027
anna+0.026
aj+0.026
lee+0.026
Neg logit contributions
aw-0.028
Run-0.028
 horror-0.024
oc-0.024
Is-0.023
Token and
Token ID290
Feature activation-2.54e-01

Pos logit contributions
Run+0.159
aw+0.153
Is+0.136
Too+0.135
Bad+0.134
Neg logit contributions
nam-0.109
ooter-0.103
ilda-0.093
anna-0.093
any-0.092
Token start
Token ID923
Feature activation-4.67e+00

Pos logit contributions
aw+0.017
Run+0.016
oc+0.015
 horror+0.015
Is+0.014
Neg logit contributions
nam-0.012
ooter-0.010
anna-0.010
lee-0.009
ilda-0.009
Token to
Token ID284
Feature activation+4.04e-01

Pos logit contributions
aw+0.310
Run+0.299
 horror+0.277
oc+0.273
Is+0.259
Neg logit contributions
nam-0.202
ooter-0.194
anna-0.188
ilda-0.182
 Emmy-0.171
Token dig
Token ID3100
Feature activation-1.55e-01

Pos logit contributions
ooter+0.021
anna+0.021
nam+0.020
ilda+0.020
lee+0.019
Neg logit contributions
Run-0.023
 horror-0.022
oc-0.022
aw-0.021
Is-0.019
Token and
Token ID290
Feature activation-2.54e-01

Pos logit contributions
Run+0.011
aw+0.010
 horror+0.010
Is+0.010
oc+0.010
Neg logit contributions
 pretty-0.005
nam-0.005
 neat-0.005
 Jackie-0.005
 soft-0.005
Token pile
Token ID14540
Feature activation-6.38e-01

Pos logit contributions
aw+0.017
Run+0.017
oc+0.015
 horror+0.015
Is+0.014
Neg logit contributions
nam-0.011
ooter-0.010
anna-0.010
ilda-0.010
lee-0.009
Token and
Token ID290
Feature activation-2.82e-01

Pos logit contributions
Run+0.038
aw+0.037
oc+0.035
 horror+0.033
Too+0.032
Neg logit contributions
nam-0.030
lee-0.028
ail-0.028
 Jackie-0.027
anna-0.027
Token toys
Token ID14958
Feature activation+1.49e+00

Pos logit contributions
aw+0.296
Run+0.288
 horror+0.267
oc+0.259
Is+0.238
Neg logit contributions
nam-0.224
anna-0.211
ilda-0.204
ooter-0.203
lee-0.198
Token and
Token ID290
Feature activation-1.90e-01

Pos logit contributions
nam+0.086
anna+0.081
lee+0.080
ooter+0.078
 Jackie+0.077
Neg logit contributions
aw-0.079
Run-0.073
 horror-0.065
oc-0.064
Is-0.059
Token no
Token ID645
Feature activation-4.74e+00

Pos logit contributions
aw+0.011
Run+0.010
 horror+0.009
oc+0.009
Is+0.008
Neg logit contributions
nam-0.010
anna-0.010
ooter-0.009
ilda-0.009
lee-0.009
Token TV
Token ID3195
Feature activation-7.84e-01

Pos logit contributions
aw+0.293
Run+0.288
 horror+0.268
oc+0.253
Is+0.238
Neg logit contributions
nam-0.214
anna-0.212
ilda-0.205
ooter-0.203
lee-0.198
Token and
Token ID290
Feature activation-2.18e-01

Pos logit contributions
aw+0.045
Run+0.044
oc+0.040
 horror+0.040
Is+0.037
Neg logit contributions
nam-0.041
ooter-0.038
anna-0.037
ilda-0.036
lee-0.036
Token no
Token ID645
Feature activation-4.74e+00

Pos logit contributions
aw+0.011
Run+0.011
 horror+0.010
oc+0.009
Is+0.009
Neg logit contributions
nam-0.012
anna-0.012
ooter-0.012
ilda-0.012
lee-0.011
Token dessert
Token ID23084
Feature activation-1.98e+00

Pos logit contributions
aw+0.289
Run+0.284
 horror+0.263
oc+0.249
Is+0.234
Neg logit contributions
nam-0.222
anna-0.216
ooter-0.210
ilda-0.210
lee-0.204
Token.
Token ID13
Feature activation+3.89e-01

Pos logit contributions
aw+0.117
Run+0.114
oc+0.103
 horror+0.102
Is+0.095
Neg logit contributions
nam-0.102
ooter-0.093
anna-0.093
ilda-0.090
lee-0.089
Token
Token ID198
Feature activation+1.44e-01

Pos logit contributions
nam+0.020
anna+0.019
ooter+0.019
ilda+0.018
lee+0.018
Neg logit contributions
aw-0.023
Run-0.022
 horror-0.020
oc-0.020
Is-0.019
Token
Token ID198
Feature activation+1.02e-01

Pos logit contributions
nam+0.009
ooter+0.009
anna+0.008
ilda+0.008
nie+0.008
Neg logit contributions
aw-0.007
Run-0.007
oc-0.006
 horror-0.006
Is-0.005
TokenL
Token ID43
Feature activation+9.05e-01

Pos logit contributions
nam+0.005
ooter+0.005
ilda+0.005
 tidy+0.005
aj+0.005
Neg logit contributions
Run-0.006
aw-0.005
 horror-0.005
oc-0.005
 beast-0.005
Token he
Token ID339
Feature activation-1.34e+00

Pos logit contributions
aw+0.054
Run+0.052
oc+0.046
 horror+0.045
Is+0.041
Neg logit contributions
nam-0.073
ooter-0.068
anna-0.068
ilda-0.066
lee-0.065
Token dropped
Token ID5710
Feature activation-9.46e-01

Pos logit contributions
aw+0.082
Run+0.081
 horror+0.073
oc+0.073
Is+0.068
Neg logit contributions
nam-0.065
ooter-0.059
anna-0.059
ilda-0.057
lee-0.056
Token something
Token ID1223
Feature activation-1.47e+00

Pos logit contributions
aw+0.051
Run+0.050
oc+0.045
 horror+0.044
Is+0.042
Neg logit contributions
nam-0.053
ooter-0.049
anna-0.048
ilda-0.047
lee-0.047
Token.
Token ID13
Feature activation+6.55e-03

Pos logit contributions
aw+0.092
Run+0.089
 horror+0.081
oc+0.081
Is+0.074
Neg logit contributions
nam-0.070
ooter-0.065
anna-0.064
ilda-0.062
lee-0.061
Token The
Token ID383
Feature activation+2.01e-01

Pos logit contributions
nam+0.000
ooter+0.000
anna+0.000
lee+0.000
ilda+0.000
Neg logit contributions
aw-0.000
Run-0.000
 horror-0.000
oc-0.000
Is-0.000
Token end
Token ID886
Feature activation-6.25e+00

Pos logit contributions
nam+0.012
ooter+0.011
anna+0.011
ilda+0.011
lee+0.011
Neg logit contributions
aw-0.010
Run-0.010
oc-0.009
 horror-0.009
Is-0.008
Token.
Token ID13
Feature activation-4.41e-02

Pos logit contributions
aw+0.403
Run+0.401
 horror+0.359
oc+0.352
Is+0.341
Neg logit contributions
nam-0.269
ooter-0.258
anna-0.256
ilda-0.247
lee-0.243
Token<|endoftext|>
Token ID50256
Feature activation-1.76e+00

Pos logit contributions
aw+0.003
Run+0.003
 horror+0.003
Is+0.003
oc+0.003
Neg logit contributions
nam-0.002
 Jackie-0.002
 Emmy-0.002
ilda-0.002
anna-0.001
TokenOnce
Token ID7454
Feature activation+2.82e+00

Pos logit contributions
aw+0.101
Run+0.099
oc+0.089
 horror+0.088
Is+0.082
Neg logit contributions
nam-0.093
ooter-0.086
anna-0.085
ilda-0.083
lee-0.081
Token upon
Token ID2402
Feature activation+1.42e+00

Pos logit contributions
nam+0.108
ooter+0.090
anna+0.087
ppa+0.084
any+0.083
Neg logit contributions
aw-0.195
 horror-0.186
Run-0.185
oc-0.178
 disaster-0.165
Token a
Token ID257
Feature activation-1.26e-02

Pos logit contributions
nam+0.075
ooter+0.069
anna+0.069
ilda+0.067
lee+0.065
Neg logit contributions
aw-0.081
Run-0.079
oc-0.071
 horror-0.071
Is-0.065