TOP ACTIVATIONS
MAX = 10.136

checking that she had everything she needed . She even missed
L ily felt ashamed because she didn 't take good care
pillow and all the things she used to cover it .
. Lily was ashamed because she thought her friend might make
she had all the things she needed from the store .
inside that barn . If she did , the owners would
ever before . If only she had been this stubborn all
they needed . Even though she was away , the family
more careful with the things she played with . She learned
taken and all the things she had discovered .
adventure and the green things she found . <|endoftext|> Jim was
ended . But still , she was happy to have experienced
happy â she had so much fun carrying
a special plant . If she took good care of it
can happen . But if she was smart and quick ,
to have the pencil that she hugged it tight and smiled
." Spot felt guilty because he knew Fl uffy was right
. Lily was ashamed that she got lost , but her
, she had two things she called her own , and
S ue felt guilty because she made the calendar messy .

MIN ACTIVATIONS
MIN = -11.598

, it kept on flying err atically with inexplicable speed .
sometimes her drawings would get sm ud ged because the paper
you . It is too sm elly for us . We
Max thought it was too sm elly and didn 't want
should be compassionate . Comp assion ate means you care about
he thought it was too sm elly . Jane said ,
sign that said " RE VERS E ". L ila and
! That flower is too sm elly . Please take it
, but it smelled very sm elly . He quickly backed
I can find something gl immer ing ?"
mother . We love g aj ar ka hal wa .
, even if it tasted y ucky . <|endoftext|> Once upon
he tried to take deep breaths to calm down . Tim
her cr ay ons to scrib ble on the wall .
, " That tower looks sm elly . Let 's go
. It is called g aj ar ka hal wa .
so it wouldn 't get sm elly again . The end
the room and started to scrib ble all over her pictures
and put on your p aj amas . Then we can
No , it smells too sm elly . I don 't

INTERVAL 4.702 - 10.136
CONTAINS 11.471%

time . Nick carefully hopped off his bike
. She is flexible . She likes to play with you
boy was so scared . He quickly stood up and ran
B enny 's mom my was very proud of him
says . " He is a lawyer too .

INTERVAL -0.731 - 4.702
CONTAINS 41.681%

was important to stay away from danger . He stayed away
, Lily 's brother tried to say sorry and fix the
hear anything . " Can we borrow the dog
. Tim my was sad , but his mom promised they
Mom said . " We have to eat lunch first .

INTERVAL -6.165 - -0.731
CONTAINS 45.603%

" Help ! Help !" Lily and Tom shout
there was a little robot . He was a very persistent
. " We did not know . We just wanted to
" It 's not polite to lend things without asking
noisy wind . <|endoftext|> Once upon a time there was a

INTERVAL -11.598 - -6.165
CONTAINS 1.244%

tops spin and spin and spin . They cheer for their
but he took a deep breath and began to dance .
oppy decided to take a nap next to the squash .
bad ending for him . <|endoftext|> Max was very tired .
because she was going to drive for the first time .
Token checking
Token ID10627
Feature activation-3.64e+00

Pos logit contributions
 forgot+0.044
 stayed+0.038
 forget+0.034
 waited+0.034
 hoped+0.033
Neg logit contributions
 This-0.029
elly-0.026
 Today-0.026
ore-0.025
ires-0.024
Token that
Token ID326
Feature activation+1.03e+00

Pos logit contributions
 This+0.060
 Today+0.058
elly+0.055
ummy+0.054
ires+0.052
Neg logit contributions
 forgot-0.087
 stayed-0.075
 waited-0.068
 hoped-0.067
 forget-0.065
Token she
Token ID673
Feature activation+8.91e+00

Pos logit contributions
 forgot+0.024
 stayed+0.021
 waited+0.019
 hoped+0.019
 learned+0.018
Neg logit contributions
 This-0.017
 Today-0.017
elly-0.015
ummy-0.015
ore-0.015
Token had
Token ID550
Feature activation+4.12e+00

Pos logit contributions
 forgot+0.115
ode+0.112
 scar+0.108
 captain+0.097
 passengers+0.095
Neg logit contributions
 This-0.159
ore-0.149
-0.149
elly-0.144
time-0.137
Token everything
Token ID2279
Feature activation-7.26e-01

Pos logit contributions
 forgot+0.062
ode+0.052
 forget+0.048
 promise+0.046
 stayed+0.046
Neg logit contributions
 This-0.085
 late-0.074
time-0.071
uttering-0.071
elly-0.070
Token she
Token ID673
Feature activation+1.01e+01

Pos logit contributions
 This+0.009
 Today+0.008
ummy+0.008
elly+0.008
ore+0.008
Neg logit contributions
 forgot-0.020
 stayed-0.017
 waited-0.016
 hoped-0.016
 learned-0.015
Token needed
Token ID2622
Feature activation-4.18e-01

Pos logit contributions
 forgot+0.122
ode+0.107
 scar+0.105
 stayed+0.098
 forget+0.094
Neg logit contributions
 This-0.218
-0.202
elly-0.199
ore-0.196
 Today-0.191
Token.
Token ID13
Feature activation-3.27e+00

Pos logit contributions
 This+0.005
 Today+0.005
elly+0.004
ummy+0.004
ires+0.004
Neg logit contributions
 forgot-0.012
 stayed-0.011
 waited-0.010
 hoped-0.010
 learned-0.009
Token She
Token ID1375
Feature activation+8.54e+00

Pos logit contributions
 This+0.033
 Today+0.032
elly+0.032
uttering+0.031
ummy+0.031
Neg logit contributions
 forgot-0.094
 stayed-0.082
 hoped-0.078
 waited-0.077
 learned-0.076
Token even
Token ID772
Feature activation+8.24e+00

Pos logit contributions
ode+0.143
ologist+0.114
 plank+0.111
ppers+0.109
 mate+0.107
Neg logit contributions
:-0.117
-0.115
 This-0.112
.-0.110
 with-0.109
Token missed
Token ID6825
Feature activation-2.66e+00

Pos logit contributions
ode+0.110
 forgot+0.095
 forget+0.083
 promise+0.080
 stayed+0.080
Neg logit contributions
 late-0.159
elly-0.148
 This-0.146
ore-0.138
looking-0.137
TokenL
Token ID43
Feature activation+2.31e-01

Pos logit contributions
 This+0.068
 Today+0.065
elly+0.062
ummy+0.062
ires+0.059
Neg logit contributions
 forgot-0.095
 stayed-0.082
 waited-0.075
 hoped-0.073
 learned-0.071
Tokenily
Token ID813
Feature activation+6.43e+00

Pos logit contributions
 forgot+0.006
 stayed+0.005
 waited+0.004
 hoped+0.004
 forget+0.004
Neg logit contributions
 This-0.004
 Today-0.004
elly-0.004
ummy-0.003
ires-0.003
Token felt
Token ID2936
Feature activation+1.83e+00

Pos logit contributions
 forgot+0.117
ode+0.106
 forget+0.104
 passengers+0.100
 scar+0.099
Neg logit contributions
 This-0.094
-0.084
 Today-0.083
elly-0.081
 The-0.076
Token ashamed
Token ID22461
Feature activation-4.06e+00

Pos logit contributions
 forgot+0.039
 stayed+0.032
 waited+0.029
 hoped+0.029
 forget+0.028
Neg logit contributions
 This-0.035
 Today-0.034
elly-0.032
ummy-0.032
ore-0.031
Token because
Token ID780
Feature activation+1.48e+00

Pos logit contributions
 This+0.068
 Today+0.065
elly+0.059
uttering+0.059
ires+0.059
Neg logit contributions
 forgot-0.096
 stayed-0.082
 waited-0.074
 hoped-0.073
 forget-0.072
Token she
Token ID673
Feature activation+1.01e+01

Pos logit contributions
 forgot+0.038
 stayed+0.033
 waited+0.030
 hoped+0.030
 forget+0.029
Neg logit contributions
 This-0.022
 Today-0.021
ummy-0.019
elly-0.019
ires-0.019
Token didn
Token ID1422
Feature activation-1.70e+00

Pos logit contributions
ode+0.134
 scar+0.131
 forgot+0.126
 passengers+0.125
 forget+0.121
Neg logit contributions
 This-0.189
elly-0.173
-0.173
looking-0.172
 late-0.167
Token't
Token ID470
Feature activation+4.70e+00

Pos logit contributions
elly+0.032
uttering+0.031
ires+0.029
joy+0.029
 Today+0.029
Neg logit contributions
 forgot-0.031
 never-0.028
 stayed-0.028
 forget-0.025
 waited-0.024
Token take
Token ID1011
Feature activation-1.38e+00

Pos logit contributions
 forgot+0.092
 stayed+0.079
 waited+0.071
 hoped+0.070
 sighed+0.067
Neg logit contributions
 This-0.096
 Today-0.093
elly-0.087
ore-0.082
ummy-0.081
Token good
Token ID922
Feature activation-6.45e-01

Pos logit contributions
 This+0.023
 Today+0.020
elly+0.019
ummy+0.019
ore+0.018
Neg logit contributions
 forgot-0.035
 stayed-0.029
 waited-0.027
 hoped-0.027
 forget-0.026
Token care
Token ID1337
Feature activation-5.10e+00

Pos logit contributions
 This+0.017
 Today+0.016
elly+0.016
ummy+0.016
ires+0.016
Neg logit contributions
 forgot-0.009
 stayed-0.007
 waited-0.006
 hoped-0.006
 learned-0.005
Token pillow
Token ID28774
Feature activation-2.10e+00

Pos logit contributions
 forgot+0.061
 stayed+0.050
 waited+0.043
 hoped+0.043
 forget+0.041
Neg logit contributions
 This-0.074
 Today-0.072
elly-0.069
ummy-0.068
ires-0.066
Token and
Token ID290
Feature activation+4.96e+00

Pos logit contributions
 This+0.026
 Today+0.023
ummy+0.023
ore+0.020
elly+0.019
Neg logit contributions
 forgot-0.057
 stayed-0.049
 waited-0.047
 hoped-0.046
 forget-0.045
Token all
Token ID477
Feature activation+3.88e+00

Pos logit contributions
ode+0.086
 forgot+0.081
 promise+0.071
ppy+0.069
 argued+0.066
Neg logit contributions
 This-0.077
ummy-0.071
 with-0.067
 She-0.065
 late-0.064
Token the
Token ID262
Feature activation+3.18e+00

Pos logit contributions
 forgot+0.108
 stayed+0.093
 waited+0.089
 hoped+0.087
ode+0.086
Neg logit contributions
 This-0.049
 Today-0.043
ummy-0.039
ore-0.038
elly-0.037
Token things
Token ID1243
Feature activation+3.42e-01

Pos logit contributions
 forgot+0.075
 stayed+0.065
 hoped+0.060
 managed+0.060
 waited+0.057
Neg logit contributions
 Today-0.047
ummy-0.045
 This-0.044
 outdoors-0.041
ires-0.040
Token she
Token ID673
Feature activation+1.01e+01

Pos logit contributions
 forgot+0.009
 stayed+0.008
 waited+0.007
 hoped+0.007
ode+0.007
Neg logit contributions
 This-0.004
ore-0.004
ummy-0.004
 Today-0.003
elly-0.003
Token used
Token ID973
Feature activation-1.02e-01

Pos logit contributions
 forgot+0.128
 promise+0.123
ode+0.123
 forget+0.115
 scar+0.110
Neg logit contributions
 This-0.193
elly-0.179
-0.177
ore-0.176
 late-0.174
Token to
Token ID284
Feature activation+4.72e+00

Pos logit contributions
 This+0.001
 Today+0.001
ummy+0.001
elly+0.001
ore+0.001
Neg logit contributions
 forgot-0.003
 stayed-0.002
 waited-0.002
 hoped-0.002
 forget-0.002
Token cover
Token ID3002
Feature activation-6.97e+00

Pos logit contributions
 forgot+0.089
 stayed+0.070
 hoped+0.063
 waited+0.062
 regretted+0.059
Neg logit contributions
 This-0.101
 Today-0.096
ore-0.089
ummy-0.088
ires-0.086
Token it
Token ID340
Feature activation+1.59e+00

Pos logit contributions
 This+0.117
 Today+0.114
elly+0.108
ummy+0.104
ore+0.101
Neg logit contributions
 forgot-0.162
 stayed-0.141
 waited-0.126
 hoped-0.126
 learned-0.121
Token.
Token ID13
Feature activation-3.52e+00

Pos logit contributions
 forgot+0.043
 stayed+0.038
 waited+0.034
 hoped+0.034
 forget+0.033
Neg logit contributions
 This-0.021
 Today-0.020
elly-0.019
ummy-0.019
ires-0.018
Token.
Token ID13
Feature activation-3.70e+00

Pos logit contributions
 forgot+0.044
 stayed+0.040
 forget+0.037
 waited+0.035
 learned+0.035
Neg logit contributions
elly-0.029
 This-0.028
 Today-0.027
ummy-0.027
ires-0.026
Token Lily
Token ID20037
Feature activation+6.93e+00

Pos logit contributions
uttering+0.047
elly+0.047
ires+0.046
 Today+0.045
 This+0.045
Neg logit contributions
 forgot-0.096
 stayed-0.083
 waited-0.076
 hoped-0.076
 learned-0.075
Token was
Token ID373
Feature activation+3.34e+00

Pos logit contributions
ode+0.100
 forgot+0.096
 promise+0.090
 wait+0.087
 passengers+0.086
Neg logit contributions
 This-0.123
-0.110
-0.109
 Today-0.106
 That-0.104
Token ashamed
Token ID22461
Feature activation-4.21e+00

Pos logit contributions
 forgot+0.071
 stayed+0.059
 waited+0.053
 hoped+0.053
 forget+0.051
Neg logit contributions
 This-0.063
 Today-0.061
elly-0.057
ummy-0.057
uttering-0.055
Token because
Token ID780
Feature activation+9.32e-01

Pos logit contributions
 This+0.066
 Today+0.063
elly+0.059
ummy+0.059
ires+0.056
Neg logit contributions
 forgot-0.105
 stayed-0.091
 waited-0.083
 hoped-0.082
 forget-0.079
Token she
Token ID673
Feature activation+1.01e+01

Pos logit contributions
 forgot+0.022
 stayed+0.019
 waited+0.018
 hoped+0.017
 forget+0.017
Neg logit contributions
 This-0.015
 Today-0.015
elly-0.014
ummy-0.014
ore-0.013
Token thought
Token ID1807
Feature activation-1.68e+00

Pos logit contributions
ode+0.147
 scar+0.135
 promise+0.127
 passengers+0.126
 forgot+0.125
Neg logit contributions
 This-0.182
looking-0.158
elly-0.154
-0.152
 late-0.152
Token her
Token ID607
Feature activation+2.57e+00

Pos logit contributions
 This+0.028
 Today+0.026
ummy+0.025
elly+0.024
ore+0.023
Neg logit contributions
 forgot-0.040
 stayed-0.034
 waited-0.032
 hoped-0.031
 forget-0.030
Token friend
Token ID1545
Feature activation+2.24e+00

Pos logit contributions
 forgot+0.052
 stayed+0.042
 waited+0.037
 hoped+0.036
 managed+0.036
Neg logit contributions
 This-0.052
 Today-0.051
ummy-0.048
elly-0.045
ires-0.045
Token might
Token ID1244
Feature activation+2.41e+00

Pos logit contributions
 forgot+0.040
 stayed+0.031
 waited+0.030
 forget+0.028
ode+0.028
Neg logit contributions
 This-0.049
 Today-0.045
ummy-0.041
elly-0.041
ore-0.040
Token make
Token ID787
Feature activation-2.99e+00

Pos logit contributions
 forgot+0.043
 stayed+0.035
 waited+0.032
 hoped+0.031
 sighed+0.030
Neg logit contributions
 This-0.053
 Today-0.051
elly-0.047
ore-0.047
ummy-0.046
Token she
Token ID673
Feature activation+8.75e+00

Pos logit contributions
 This+0.043
 Today+0.042
elly+0.039
ummy+0.037
ires+0.037
Neg logit contributions
 forgot-0.074
 stayed-0.065
 waited-0.059
 hoped-0.058
 forget-0.056
Token had
Token ID550
Feature activation+3.03e+00

Pos logit contributions
 forgot+0.108
ode+0.094
 scar+0.090
 forget+0.086
 promise+0.086
Neg logit contributions
 This-0.195
ore-0.170
-0.163
ach-0.162
looking-0.162
Token all
Token ID477
Feature activation+3.58e+00

Pos logit contributions
 forgot+0.049
 forget+0.037
 stayed+0.036
 promise+0.036
ode+0.035
Neg logit contributions
 This-0.067
-0.056
 late-0.056
 Today-0.055
time-0.053
Token the
Token ID262
Feature activation+3.03e+00

Pos logit contributions
 forgot+0.088
 stayed+0.074
 waited+0.068
 hoped+0.068
 forget+0.067
Neg logit contributions
 This-0.057
 Today-0.052
elly-0.048
ummy-0.048
ore-0.048
Token things
Token ID1243
Feature activation-8.21e-01

Pos logit contributions
 forgot+0.071
 stayed+0.060
 hoped+0.054
 waited+0.053
 managed+0.052
Neg logit contributions
 This-0.050
 Today-0.049
ummy-0.047
elly-0.044
ires-0.044
Token she
Token ID673
Feature activation+1.01e+01

Pos logit contributions
 This+0.012
 Today+0.011
ummy+0.011
elly+0.010
ore+0.010
Neg logit contributions
 forgot-0.021
 stayed-0.018
 waited-0.017
 hoped-0.017
 forget-0.016
Token needed
Token ID2622
Feature activation-7.00e-01

Pos logit contributions
 forgot+0.127
ode+0.104
 scar+0.103
 stayed+0.100
 forget+0.098
Neg logit contributions
 This-0.222
-0.201
ore-0.194
elly-0.192
 late-0.188
Token from
Token ID422
Feature activation+9.88e-01

Pos logit contributions
 This+0.008
 Today+0.008
elly+0.007
ummy+0.007
ires+0.007
Neg logit contributions
 forgot-0.020
 stayed-0.018
 waited-0.016
 hoped-0.016
 learned-0.016
Token the
Token ID262
Feature activation+2.76e+00

Pos logit contributions
 forgot+0.023
 stayed+0.020
 waited+0.018
 hoped+0.017
 forget+0.017
Neg logit contributions
 This-0.017
 Today-0.017
elly-0.016
ummy-0.015
ore-0.015
Token store
Token ID3650
Feature activation-2.27e+00

Pos logit contributions
 forgot+0.062
 stayed+0.053
 hoped+0.047
 waited+0.047
 managed+0.045
Neg logit contributions
 This-0.050
 Today-0.048
ummy-0.045
elly-0.045
ore-0.043
Token.
Token ID13
Feature activation-3.19e+00

Pos logit contributions
 This+0.023
 Today+0.021
ummy+0.019
elly+0.019
ore+0.017
Neg logit contributions
 forgot-0.069
 stayed-0.061
 waited-0.057
 hoped-0.056
 forget-0.055
Token inside
Token ID2641
Feature activation-3.71e+00

Pos logit contributions
 This+0.017
 Today+0.016
elly+0.016
ummy+0.015
ires+0.015
Neg logit contributions
 forgot-0.026
 stayed-0.023
 waited-0.021
 hoped-0.020
 forget-0.020
Token that
Token ID326
Feature activation+1.28e+00

Pos logit contributions
 This+0.060
 Today+0.059
elly+0.056
ummy+0.054
ires+0.053
Neg logit contributions
 forgot-0.087
 stayed-0.077
 hoped-0.069
 waited-0.069
 learned-0.067
Token barn
Token ID25203
Feature activation-2.13e+00

Pos logit contributions
 forgot+0.029
 stayed+0.024
 waited+0.022
 hoped+0.021
 forget+0.021
Neg logit contributions
 This-0.023
 Today-0.022
elly-0.021
ummy-0.020
ore-0.020
Token.
Token ID13
Feature activation-3.22e+00

Pos logit contributions
 This+0.029
 Today+0.027
ummy+0.025
elly+0.024
ore+0.024
Neg logit contributions
 forgot-0.057
 stayed-0.049
 waited-0.045
 hoped-0.045
 forget-0.044
Token If
Token ID1002
Feature activation-3.56e-01

Pos logit contributions
uttering+0.038
elly+0.038
 This+0.036
ore+0.035
 Today+0.035
Neg logit contributions
 forgot-0.085
 stayed-0.075
 hoped-0.071
 waited-0.070
 learned-0.069
Token she
Token ID673
Feature activation+1.00e+01

Pos logit contributions
 This+0.005
 Today+0.005
ummy+0.005
ires+0.004
elly+0.004
Neg logit contributions
 forgot-0.009
 stayed-0.008
 hoped-0.007
 waited-0.007
 learned-0.007
Token did
Token ID750
Feature activation+6.48e-01

Pos logit contributions
 forgot+0.125
 scar+0.107
ode+0.105
 passengers+0.090
 forget+0.088
Neg logit contributions
 This-0.216
 Today-0.207
elly-0.205
ore-0.199
-0.190
Token,
Token ID11
Feature activation+6.44e-01

Pos logit contributions
 forgot+0.017
 stayed+0.014
 hoped+0.013
 waited+0.013
 forget+0.013
Neg logit contributions
 This-0.010
 Today-0.009
ummy-0.008
ore-0.008
elly-0.007
Token the
Token ID262
Feature activation+3.92e+00

Pos logit contributions
 forgot+0.017
 stayed+0.015
 hoped+0.014
 waited+0.014
ode+0.014
Neg logit contributions
 This-0.009
 Today-0.008
ummy-0.007
ires-0.006
ore-0.006
Token owners
Token ID4393
Feature activation+5.64e+00

Pos logit contributions
 forgot+0.091
 stayed+0.073
 forget+0.067
 managed+0.067
 laughed+0.066
Neg logit contributions
 Today-0.070
 This-0.067
ummy-0.059
elly-0.059
-0.058
Token would
Token ID561
Feature activation+2.53e+00

Pos logit contributions
 forgot+0.082
 scar+0.065
ode+0.063
 forget+0.056
 stayed+0.054
Neg logit contributions
 This-0.116
ore-0.110
 Today-0.106
time-0.099
elly-0.099
Token ever
Token ID1683
Feature activation+3.76e+00

Pos logit contributions
 forgot+0.054
 stayed+0.047
 hoped+0.043
 waited+0.042
 learned+0.040
Neg logit contributions
 This-0.036
 Today-0.033
ummy-0.032
elly-0.032
ires-0.031
Token before
Token ID878
Feature activation-1.02e+00

Pos logit contributions
 forgot+0.089
 stayed+0.075
 waited+0.068
 hoped+0.066
 forget+0.066
Neg logit contributions
 This-0.066
 Today-0.064
elly-0.060
ummy-0.059
ires-0.058
Token.
Token ID13
Feature activation-3.26e+00

Pos logit contributions
 This+0.016
elly+0.015
ires+0.015
 Today+0.014
ore+0.014
Neg logit contributions
 forgot-0.025
 stayed-0.021
 waited-0.020
 never-0.019
 learned-0.019
Token If
Token ID1002
Feature activation+1.12e-01

Pos logit contributions
elly+0.044
uttering+0.043
 This+0.042
 Today+0.042
ach+0.041
Neg logit contributions
 forgot-0.082
 stayed-0.070
 learned-0.065
 hoped-0.065
 waited-0.064
Token only
Token ID691
Feature activation+4.40e+00

Pos logit contributions
 forgot+0.003
 stayed+0.003
 hoped+0.002
 waited+0.002
 learned+0.002
Neg logit contributions
 This-0.002
 Today-0.001
ummy-0.001
elly-0.001
ore-0.001
Token she
Token ID673
Feature activation+1.00e+01

Pos logit contributions
 forgot+0.106
 stayed+0.091
 hoped+0.083
 waited+0.083
 learned+0.079
Neg logit contributions
 This-0.072
 Today-0.068
ummy-0.063
elly-0.061
ires-0.058
Token had
Token ID550
Feature activation+4.86e+00

Pos logit contributions
 forgot+0.122
 scar+0.097
 stayed+0.094
ode+0.084
 passengers+0.084
Neg logit contributions
 This-0.242
 Today-0.219
elly-0.215
ummy-0.211
ore-0.209
Token been
Token ID587
Feature activation+3.81e+00

Pos logit contributions
 forgot+0.080
 stayed+0.066
 hoped+0.061
ode+0.058
 waited+0.057
Neg logit contributions
 This-0.105
 Today-0.090
elly-0.088
ummy-0.088
 late-0.086
Token this
Token ID428
Feature activation+3.10e+00

Pos logit contributions
 forgot+0.075
 stayed+0.064
 waited+0.056
 hoped+0.056
 forget+0.054
Neg logit contributions
 This-0.077
 Today-0.073
elly-0.071
ummy-0.070
ore-0.067
Token stubborn
Token ID24444
Feature activation-2.43e+00

Pos logit contributions
 forgot+0.077
 stayed+0.067
 waited+0.061
 hoped+0.061
 forget+0.059
Neg logit contributions
 This-0.048
 Today-0.046
elly-0.043
ummy-0.042
ore-0.040
Token all
Token ID477
Feature activation+3.53e+00

Pos logit contributions
 This+0.040
 Today+0.038
ummy+0.036
elly+0.036
ore+0.033
Neg logit contributions
 forgot-0.058
 stayed-0.050
 waited-0.046
 hoped-0.046
 learned-0.043
Token they
Token ID484
Feature activation+9.26e+00

Pos logit contributions
 This+0.026
 Today+0.024
ummy+0.023
elly+0.022
ore+0.022
Neg logit contributions
 forgot-0.047
 stayed-0.040
 waited-0.037
 hoped-0.037
 forget-0.036
Token needed
Token ID2622
Feature activation-5.54e-01

Pos logit contributions
 forgot+0.123
ode+0.104
 scar+0.100
 stayed+0.098
 sighed+0.085
Neg logit contributions
 This-0.197
 Today-0.172
-0.168
 late-0.165
ore-0.161
Token.
Token ID13
Feature activation-3.06e+00

Pos logit contributions
 This+0.006
 Today+0.006
elly+0.006
ummy+0.005
ires+0.005
Neg logit contributions
 forgot-0.016
 stayed-0.014
 waited-0.013
 hoped-0.013
 learned-0.013
Token Even
Token ID3412
Feature activation+2.98e+00

Pos logit contributions
 This+0.032
 Today+0.031
elly+0.030
ummy+0.029
ires+0.028
Neg logit contributions
 forgot-0.087
 stayed-0.078
 waited-0.072
 hoped-0.072
 learned-0.070
Token though
Token ID996
Feature activation-6.02e-02

Pos logit contributions
 forgot+0.074
 stayed+0.064
 waited+0.059
 hoped+0.058
 forget+0.056
Neg logit contributions
 This-0.045
 Today-0.043
elly-0.041
ummy-0.040
ires-0.039
Token she
Token ID673
Feature activation+1.00e+01

Pos logit contributions
 This+0.001
 Today+0.001
ummy+0.001
elly+0.001
ires+0.001
Neg logit contributions
 forgot-0.001
 stayed-0.001
 waited-0.001
 hoped-0.001
 forget-0.001
Token was
Token ID373
Feature activation+4.72e+00

Pos logit contributions
 forgot+0.145
 scar+0.128
ode+0.122
 passengers+0.117
 stayed+0.115
Neg logit contributions
 This-0.193
elly-0.179
ore-0.179
-0.178
 Today-0.176
Token away
Token ID1497
Feature activation-1.28e+00

Pos logit contributions
 forgot+0.099
 stayed+0.083
 hoped+0.075
 waited+0.074
 forget+0.073
Neg logit contributions
 This-0.087
 Today-0.081
elly-0.077
ummy-0.077
uttering-0.075
Token,
Token ID11
Feature activation-1.72e-01

Pos logit contributions
 This+0.018
 Today+0.017
elly+0.016
ummy+0.016
ires+0.015
Neg logit contributions
 forgot-0.034
 stayed-0.029
 waited-0.027
 hoped-0.027
 forget-0.026
Token the
Token ID262
Feature activation+3.89e+00

Pos logit contributions
 This+0.002
 Today+0.002
ummy+0.002
ires+0.002
ore+0.002
Neg logit contributions
 forgot-0.005
 stayed-0.004
 waited-0.004
 hoped-0.004
ode-0.003
Token family
Token ID1641
Feature activation+5.58e+00

Pos logit contributions
 forgot+0.077
 stayed+0.062
 managed+0.057
 hoped+0.055
 waited+0.052
Neg logit contributions
ummy-0.077
 Today-0.076
 This-0.071
elly-0.067
uttering-0.064
Token more
Token ID517
Feature activation+1.26e+00

Pos logit contributions
 forgot+0.084
 stayed+0.065
 forget+0.061
 waited+0.060
ode+0.059
Neg logit contributions
 This-0.082
 Today-0.076
 late-0.071
uttering-0.071
ore-0.069
Token careful
Token ID8161
Feature activation-3.81e+00

Pos logit contributions
 forgot+0.020
 stayed+0.016
 waited+0.014
 hoped+0.013
 forget+0.013
Neg logit contributions
 This-0.029
 Today-0.029
elly-0.028
ummy-0.028
uttering-0.027
Token with
Token ID351
Feature activation+4.89e-01

Pos logit contributions
 This+0.059
 Today+0.058
elly+0.056
ummy+0.053
ires+0.051
Neg logit contributions
 forgot-0.093
 stayed-0.083
 waited-0.074
 hoped-0.073
 never-0.073
Token the
Token ID262
Feature activation+3.63e+00

Pos logit contributions
 forgot+0.012
 stayed+0.010
 waited+0.010
 hoped+0.009
 forget+0.009
Neg logit contributions
 This-0.008
 Today-0.007
elly-0.007
ummy-0.007
ires-0.006
Token things
Token ID1243
Feature activation-1.80e+00

Pos logit contributions
 forgot+0.077
 stayed+0.060
 hoped+0.057
 waited+0.056
 argued+0.054
Neg logit contributions
 Today-0.066
 This-0.064
ummy-0.060
elly-0.059
-0.058
Token she
Token ID673
Feature activation+1.00e+01

Pos logit contributions
 This+0.025
 Today+0.022
ummy+0.021
elly+0.021
ore+0.021
Neg logit contributions
 forgot-0.048
 stayed-0.041
 waited-0.038
 hoped-0.038
 forget-0.036
Token played
Token ID2826
Feature activation-4.88e+00

Pos logit contributions
 forgot+0.117
 scar+0.102
 promise+0.096
ode+0.093
 forget+0.093
Neg logit contributions
 This-0.200
-0.199
elly-0.187
ore-0.184
ires-0.174
Token with
Token ID351
Feature activation-2.89e-01

Pos logit contributions
 Today+0.069
 This+0.068
elly+0.066
ummy+0.064
ires+0.060
Neg logit contributions
 forgot-0.122
 stayed-0.112
 waited-0.100
 hoped-0.099
 never-0.097
Token.
Token ID13
Feature activation-3.14e+00

Pos logit contributions
 This+0.004
 Today+0.004
elly+0.003
ummy+0.003
ires+0.003
Neg logit contributions
 forgot-0.008
 stayed-0.007
 waited-0.006
 hoped-0.006
 forget-0.006
Token She
Token ID1375
Feature activation+8.58e+00

Pos logit contributions
elly+0.034
 Today+0.034
uttering+0.033
 This+0.033
ummy+0.033
Neg logit contributions
 forgot-0.086
 stayed-0.077
 hoped-0.072
 learned-0.070
 waited-0.070
Token learned
Token ID4499
Feature activation-6.12e-01

Pos logit contributions
ode+0.129
 forgot+0.122
 heads+0.120
 forehead+0.119
 nurses+0.116
Neg logit contributions
-0.123
-0.112
 with-0.112
 This-0.108
:-0.106
Token taken
Token ID2077
Feature activation-1.88e+00

Pos logit contributions
 forgot+0.052
 stayed+0.039
 forget+0.036
 promise+0.034
 scar+0.034
Neg logit contributions
 This-0.083
 Today-0.075
-0.073
elly-0.073
uttering-0.073
Token and
Token ID290
Feature activation+4.88e+00

Pos logit contributions
 This+0.028
 Today+0.026
ummy+0.024
elly+0.024
ore+0.023
Neg logit contributions
 forgot-0.048
 stayed-0.042
 waited-0.038
 hoped-0.038
 forget-0.037
Token all
Token ID477
Feature activation+3.60e+00

Pos logit contributions
 forgot+0.084
ode+0.072
 stayed+0.065
 scar+0.063
ppy+0.063
Neg logit contributions
 This-0.093
ummy-0.077
 Today-0.077
 late-0.076
ore-0.075
Token the
Token ID262
Feature activation+3.47e+00

Pos logit contributions
 forgot+0.095
 stayed+0.081
 waited+0.076
 hoped+0.075
 forget+0.073
Neg logit contributions
 This-0.051
 Today-0.046
ore-0.041
ummy-0.041
elly-0.041
Token things
Token ID1243
Feature activation+4.75e-01

Pos logit contributions
 forgot+0.083
 stayed+0.071
 hoped+0.065
 waited+0.062
 managed+0.060
Neg logit contributions
 This-0.057
 Today-0.054
ummy-0.051
ires-0.048
elly-0.047
Token she
Token ID673
Feature activation+1.00e+01

Pos logit contributions
 forgot+0.012
 stayed+0.010
 waited+0.010
 hoped+0.010
ode+0.010
Neg logit contributions
 This-0.006
ore-0.005
ummy-0.005
 Today-0.005
uttering-0.005
Token had
Token ID550
Feature activation+3.83e+00

Pos logit contributions
 forgot+0.127
 scar+0.104
 stayed+0.101
ode+0.095
 forget+0.093
Neg logit contributions
 This-0.230
-0.207
elly-0.205
 Today-0.200
ore-0.200
Token discovered
Token ID5071
Feature activation-9.93e-01

Pos logit contributions
 forgot+0.057
 stayed+0.044
 forget+0.040
 scar+0.039
 promise+0.039
Neg logit contributions
 This-0.089
 Today-0.079
elly-0.079
uttering-0.078
-0.077
Token.
Token ID13
Feature activation-3.53e+00

Pos logit contributions
 This+0.013
 Today+0.013
elly+0.012
ummy+0.012
ires+0.011
Neg logit contributions
 forgot-0.027
 stayed-0.023
 waited-0.021
 hoped-0.021
 learned-0.021
Token
Token ID220
Feature activation-4.52e+00

Pos logit contributions
elly+0.037
 This+0.036
uttering+0.036
 Today+0.035
ummy+0.035
Neg logit contributions
 forgot-0.097
 stayed-0.085
 hoped-0.081
 learned-0.080
 waited-0.079
Token
Token ID198
Feature activation-4.45e+00

Pos logit contributions
elly+0.058
 Today+0.055
ummy+0.053
uttering+0.051
ires+0.050
Neg logit contributions
 forgot-0.112
 stayed-0.098
 hoped-0.091
 learned-0.091
 waited-0.090
Token adventure
Token ID8855
Feature activation-4.04e+00

Pos logit contributions
 forgot+0.053
 stayed+0.045
 waited+0.040
 hoped+0.040
 forget+0.038
Neg logit contributions
 This-0.047
 Today-0.046
ummy-0.043
elly-0.042
ore-0.041
Token and
Token ID290
Feature activation+4.97e+00

Pos logit contributions
 This+0.050
 Today+0.045
ummy+0.043
elly+0.041
ore+0.040
Neg logit contributions
 forgot-0.114
 stayed-0.098
 waited-0.092
 hoped-0.092
 forget-0.090
Token the
Token ID262
Feature activation+3.20e+00

Pos logit contributions
ode+0.073
 forgot+0.073
 stayed+0.059
 promise+0.058
 waited+0.054
Neg logit contributions
 This-0.102
 Today-0.088
ummy-0.087
 late-0.084
 Of-0.082
Token green
Token ID4077
Feature activation+2.36e+00

Pos logit contributions
 forgot+0.070
 stayed+0.058
 hoped+0.054
 waited+0.052
 managed+0.051
Neg logit contributions
 Today-0.056
 This-0.056
ummy-0.054
elly-0.051
ore-0.049
Token things
Token ID1243
Feature activation+6.10e-01

Pos logit contributions
 forgot+0.049
 stayed+0.040
 hoped+0.036
 waited+0.036
 forget+0.034
Neg logit contributions
 This-0.047
 Today-0.046
ummy-0.043
elly-0.043
ore-0.041
Token she
Token ID673
Feature activation+9.98e+00

Pos logit contributions
 forgot+0.015
 stayed+0.012
 waited+0.012
 hoped+0.011
 forget+0.011
Neg logit contributions
 This-0.009
ore-0.008
 Today-0.008
ummy-0.007
elly-0.007
Token found
Token ID1043
Feature activation-6.71e-01

Pos logit contributions
 forgot+0.127
ode+0.126
 promise+0.111
 scar+0.110
 forget+0.104
Neg logit contributions
 This-0.199
-0.180
elly-0.180
ore-0.177
 late-0.170
Token.
Token ID13
Feature activation-2.80e+00

Pos logit contributions
 This+0.009
 Today+0.008
elly+0.008
ummy+0.007
ires+0.007
Neg logit contributions
 forgot-0.018
 stayed-0.016
 waited-0.015
 hoped-0.015
 learned-0.014
Token<|endoftext|>
Token ID50256
Feature activation-7.12e+00

Pos logit contributions
uttering+0.037
elly+0.035
ach+0.035
ires+0.034
 This+0.033
Neg logit contributions
 forgot-0.070
 stayed-0.060
 hoped-0.057
 learned-0.056
 waited-0.055
TokenJim
Token ID18050
Feature activation+2.99e+00

Pos logit contributions
ires+0.114
uttering+0.114
ummy+0.107
elly+0.103
ocol+0.102
Neg logit contributions
 forgot-0.151
 stayed-0.137
 learned-0.135
 felt-0.130
 waited-0.128
Token was
Token ID373
Feature activation+1.93e+00

Pos logit contributions
 forgot+0.058
 stayed+0.048
 waited+0.043
 hoped+0.042
 forget+0.041
Neg logit contributions
 This-0.061
 Today-0.059
elly-0.056
ummy-0.055
ore-0.054
Token ended
Token ID4444
Feature activation-3.36e+00

Pos logit contributions
 forgot+0.050
ode+0.038
 promise+0.037
 stayed+0.037
 forget+0.036
Neg logit contributions
 This-0.054
 Today-0.047
elly-0.045
uttering-0.045
time-0.044
Token.
Token ID13
Feature activation-3.85e+00

Pos logit contributions
 This+0.051
 Today+0.049
elly+0.047
ummy+0.045
ore+0.044
Neg logit contributions
 forgot-0.084
 stayed-0.075
 hoped-0.068
 waited-0.068
 never-0.067
Token But
Token ID887
Feature activation+1.63e+00

Pos logit contributions
ach+0.042
uttering+0.042
elly+0.041
ires+0.039
 This+0.039
Neg logit contributions
 forgot-0.103
 stayed-0.089
 hoped-0.085
 learned-0.084
 waited-0.084
Token still
Token ID991
Feature activation+3.61e+00

Pos logit contributions
 forgot+0.038
 stayed+0.032
 hoped+0.029
 waited+0.029
 forget+0.028
Neg logit contributions
 This-0.027
 Today-0.026
ummy-0.024
ore-0.023
elly-0.023
Token,
Token ID11
Feature activation-6.56e-01

Pos logit contributions
 forgot+0.083
 stayed+0.071
 waited+0.065
 hoped+0.063
 forget+0.061
Neg logit contributions
 This-0.062
 Today-0.059
ummy-0.054
elly-0.054
ore-0.052
Tokenshe
Token ID7091
Feature activation+9.97e+00

Pos logit contributions
 This+0.009
 Today+0.008
ummy+0.008
ore+0.008
elly+0.007
Neg logit contributions
 forgot-0.017
 stayed-0.015
 waited-0.013
 hoped-0.013
ode-0.013
Token was
Token ID373
Feature activation+3.17e+00

Pos logit contributions
ode+0.126
 scar+0.117
 forgot+0.115
 heads+0.114
 nurses+0.111
Neg logit contributions
-0.155
ore-0.150
 This-0.146
?-0.145
-0.142
Token happy
Token ID3772
Feature activation-1.64e+00

Pos logit contributions
 forgot+0.066
 stayed+0.054
 waited+0.049
 forget+0.048
 hoped+0.048
Neg logit contributions
 This-0.058
 Today-0.055
uttering-0.050
ore-0.050
ummy-0.050
Token to
Token ID284
Feature activation+1.51e+00

Pos logit contributions
 This+0.024
 Today+0.023
elly+0.021
ummy+0.021
ires+0.020
Neg logit contributions
 forgot-0.043
 stayed-0.037
 waited-0.034
 hoped-0.034
 forget-0.033
Token have
Token ID423
Feature activation+2.16e+00

Pos logit contributions
 forgot+0.025
 stayed+0.020
 waited+0.017
 hoped+0.017
 sighed+0.016
Neg logit contributions
 This-0.036
 Today-0.035
ummy-0.032
ore-0.032
elly-0.032
Token experienced
Token ID5924
Feature activation-2.10e+00

Pos logit contributions
 forgot+0.053
 stayed+0.044
 promise+0.043
 forget+0.043
ode+0.041
Neg logit contributions
 This-0.031
 Today-0.026
-0.025
elly-0.024
uttering-0.023
Token happy
Token ID3772
Feature activation-2.29e+00

Pos logit contributions
 forgot+0.073
 stayed+0.061
 waited+0.055
 hoped+0.054
 forget+0.052
Neg logit contributions
 This-0.069
 Today-0.067
elly-0.063
ummy-0.063
ires-0.061
Tokenâ
Token ID22940
Feature activation-1.57e-01

Pos logit contributions
 This+0.034
 Today+0.033
elly+0.031
ummy+0.030
ires+0.029
Neg logit contributions
 forgot-0.058
 stayed-0.051
 waited-0.046
 hoped-0.046
 forget-0.044
Token
Token ID26391
Feature activation-3.37e+00

Pos logit contributions
 This+0.003
 Today+0.003
elly+0.003
ummy+0.003
ore+0.002
Neg logit contributions
 forgot-0.003
 stayed-0.003
 waited-0.003
 hoped-0.003
 forget-0.003
Token
Token ID447
Feature activation-3.02e+00

Pos logit contributions
 This+0.049
 Today+0.048
elly+0.046
ummy+0.044
ires+0.043
Neg logit contributions
 forgot-0.087
 stayed-0.075
 waited-0.069
 hoped-0.068
 learned-0.066
Token
Token ID251
Feature activation-2.09e+00

Pos logit contributions
 This+0.028
 Today+0.028
elly+0.026
ummy+0.023
ires+0.023
Neg logit contributions
 forgot-0.093
 stayed-0.084
 waited-0.078
 hoped-0.077
 learned-0.075
Tokenshe
Token ID7091
Feature activation+9.96e+00

Pos logit contributions
 This+0.028
 Today+0.027
elly+0.026
ummy+0.025
ires+0.024
Neg logit contributions
 forgot-0.055
 stayed-0.049
 waited-0.045
 hoped-0.045
 learned-0.044
Token had
Token ID550
Feature activation+3.64e+00

Pos logit contributions
 forgot+0.125
ode+0.100
 stayed+0.098
 drowned+0.095
 passengers+0.094
Neg logit contributions
 This-0.201
-0.187
 Today-0.177
 A-0.174
ummy-0.173
Token so
Token ID523
Feature activation+1.95e+00

Pos logit contributions
 forgot+0.069
ode+0.057
 stayed+0.057
 promise+0.056
 forget+0.054
Neg logit contributions
 This-0.069
 late-0.056
 Today-0.055
-0.055
 A-0.053
Token much
Token ID881
Feature activation+1.15e+00

Pos logit contributions
 forgot+0.050
 stayed+0.044
 waited+0.040
 hoped+0.040
 learned+0.039
Neg logit contributions
 This-0.029
 Today-0.028
elly-0.026
ummy-0.025
ires-0.025
Token fun
Token ID1257
Feature activation-2.20e+00

Pos logit contributions
 forgot+0.022
 stayed+0.019
 waited+0.017
 hoped+0.016
 learned+0.016
Neg logit contributions
 This-0.024
 Today-0.023
elly-0.022
ummy-0.022
ires-0.022
Token carrying
Token ID6872
Feature activation-2.30e+00

Pos logit contributions
 This+0.033
 Today+0.032
elly+0.030
ummy+0.029
ires+0.028
Neg logit contributions
 forgot-0.055
 stayed-0.049
 waited-0.044
 hoped-0.043
 learned-0.042
Token a
Token ID257
Feature activation+2.31e+00

Pos logit contributions
 forgot+0.066
 stayed+0.057
 waited+0.052
 hoped+0.052
 forget+0.050
Neg logit contributions
 This-0.042
 Today-0.040
elly-0.038
ummy-0.038
ires-0.036
Token special
Token ID2041
Feature activation+8.11e-01

Pos logit contributions
 forgot+0.053
 stayed+0.045
 hoped+0.041
 waited+0.041
 learned+0.038
Neg logit contributions
 This-0.040
 Today-0.038
ummy-0.037
elly-0.036
ore-0.036
Token plant
Token ID4618
Feature activation-1.86e+00

Pos logit contributions
 forgot+0.018
 stayed+0.015
 hoped+0.013
 waited+0.013
 forget+0.013
Neg logit contributions
 This-0.015
 Today-0.015
ummy-0.014
elly-0.014
ore-0.013
Token.
Token ID13
Feature activation-3.51e+00

Pos logit contributions
 This+0.026
 Today+0.024
elly+0.023
ummy+0.023
ore+0.022
Neg logit contributions
 forgot-0.049
 stayed-0.042
 waited-0.039
 hoped-0.039
 forget-0.038
Token If
Token ID1002
Feature activation-2.01e-01

Pos logit contributions
uttering+0.059
elly+0.058
ore+0.058
ires+0.058
 Today+0.056
Neg logit contributions
 forgot-0.074
 stayed-0.059
 hoped-0.058
 learned-0.057
 waited-0.057
Token she
Token ID673
Feature activation+9.95e+00

Pos logit contributions
 This+0.003
 Today+0.003
ummy+0.003
elly+0.003
ires+0.003
Neg logit contributions
 forgot-0.005
 stayed-0.004
 hoped-0.004
 waited-0.004
ode-0.004
Token took
Token ID1718
Feature activation-1.12e+00

Pos logit contributions
 forgot+0.125
 scar+0.104
 passengers+0.097
ode+0.097
 forget+0.087
Neg logit contributions
 This-0.217
 Today-0.204
elly-0.203
ore-0.199
 On-0.193
Token good
Token ID922
Feature activation-1.02e+00

Pos logit contributions
 This+0.017
 Today+0.015
ummy+0.014
ires+0.014
elly+0.014
Neg logit contributions
 forgot-0.030
 stayed-0.025
 waited-0.023
 hoped-0.023
 forget-0.023
Token care
Token ID1337
Feature activation-5.31e+00

Pos logit contributions
 This+0.026
 Today+0.025
elly+0.024
ummy+0.024
ires+0.023
Neg logit contributions
 forgot-0.015
 stayed-0.012
 waited-0.010
 hoped-0.010
 forget-0.009
Token of
Token ID286
Feature activation-3.24e-01

Pos logit contributions
 This+0.069
 Today+0.065
elly+0.061
ummy+0.060
ore+0.057
Neg logit contributions
 forgot-0.145
 stayed-0.128
 waited-0.118
 hoped-0.117
 forget-0.114
Token it
Token ID340
Feature activation+8.42e-01

Pos logit contributions
 This+0.005
 Today+0.005
ummy+0.005
elly+0.005
ires+0.005
Neg logit contributions
 forgot-0.008
 stayed-0.007
 waited-0.006
 hoped-0.006
 forget-0.006
Token can
Token ID460
Feature activation+2.12e+00

Pos logit contributions
 forgot+0.024
 stayed+0.019
 hoped+0.018
 waited+0.018
 sighed+0.017
Neg logit contributions
 This-0.026
 Today-0.024
ore-0.023
ires-0.023
ummy-0.022
Token happen
Token ID1645
Feature activation-4.97e+00

Pos logit contributions
 forgot+0.037
 hoped+0.029
 stayed+0.028
 waited+0.027
 sighed+0.027
Neg logit contributions
 This-0.046
 Today-0.043
ummy-0.043
ires-0.039
ore-0.039
Token.
Token ID13
Feature activation-3.04e+00

Pos logit contributions
 This+0.073
 Today+0.073
elly+0.066
ummy+0.063
uttering+0.063
Neg logit contributions
 forgot-0.126
 stayed-0.112
 hoped-0.100
 waited-0.099
 never-0.099
Token But
Token ID887
Feature activation+1.52e+00

Pos logit contributions
 This+0.030
 Today+0.029
elly+0.028
uttering+0.028
ummy+0.027
Neg logit contributions
 forgot-0.088
 stayed-0.078
 hoped-0.073
 waited-0.072
 learned-0.071
Token if
Token ID611
Feature activation+4.27e-01

Pos logit contributions
 forgot+0.038
 stayed+0.032
 waited+0.029
 hoped+0.029
 managed+0.028
Neg logit contributions
 This-0.024
 Today-0.023
ummy-0.021
ires-0.020
ore-0.020
Token she
Token ID673
Feature activation+9.95e+00

Pos logit contributions
 forgot+0.011
 stayed+0.009
 hoped+0.009
 waited+0.009
 learned+0.009
Neg logit contributions
 This-0.006
 Today-0.005
ummy-0.005
ires-0.005
ore-0.005
Token was
Token ID373
Feature activation+5.34e+00

Pos logit contributions
 forgot+0.129
 scar+0.108
 passengers+0.100
ode+0.093
 forget+0.089
Neg logit contributions
 This-0.214
elly-0.209
ore-0.208
 Today-0.206
-0.197
Token smart
Token ID4451
Feature activation-2.70e+00

Pos logit contributions
 forgot+0.112
 stayed+0.094
 waited+0.085
 hoped+0.085
 forget+0.081
Neg logit contributions
 This-0.098
 Today-0.094
elly-0.089
ummy-0.087
ore-0.085
Token and
Token ID290
Feature activation+4.85e+00

Pos logit contributions
 This+0.037
 Today+0.035
elly+0.032
ummy+0.032
ore+0.030
Neg logit contributions
 forgot-0.072
 stayed-0.064
 waited-0.059
 hoped-0.058
 forget-0.056
Token quick
Token ID2068
Feature activation-1.29e+00

Pos logit contributions
 forgot+0.094
 stayed+0.076
ode+0.075
 waited+0.069
 hoped+0.068
Neg logit contributions
 This-0.091
 Today-0.080
ires-0.077
ummy-0.075
 late-0.074
Token,
Token ID11
Feature activation+6.82e-01

Pos logit contributions
 This+0.017
 Today+0.016
elly+0.015
ummy+0.014
ore+0.014
Neg logit contributions
 forgot-0.035
 stayed-0.031
 waited-0.029
 hoped-0.028
 forget-0.028
Token to
Token ID284
Feature activation+1.83e+00

Pos logit contributions
 This+0.040
 Today+0.038
elly+0.036
ummy+0.035
ires+0.034
Neg logit contributions
 forgot-0.063
 stayed-0.055
 waited-0.050
 hoped-0.049
 forget-0.048
Token have
Token ID423
Feature activation+2.57e+00

Pos logit contributions
 forgot+0.033
 stayed+0.027
 waited+0.023
 hoped+0.023
 learned+0.021
Neg logit contributions
 This-0.041
 Today-0.040
ummy-0.037
elly-0.037
ore-0.036
Token the
Token ID262
Feature activation+3.80e+00

Pos logit contributions
 forgot+0.062
 stayed+0.053
 forget+0.050
 promise+0.050
ode+0.049
Neg logit contributions
 This-0.039
 Today-0.032
-0.030
elly-0.030
ummy-0.030
Token pencil
Token ID21613
Feature activation-2.43e+00

Pos logit contributions
 forgot+0.073
 stayed+0.060
 waited+0.053
 hoped+0.052
 forget+0.050
Neg logit contributions
 This-0.081
 Today-0.079
elly-0.075
ummy-0.075
ires-0.072
Token that
Token ID326
Feature activation+3.07e+00

Pos logit contributions
 This+0.036
 Today+0.033
ummy+0.032
elly+0.032
ore+0.030
Neg logit contributions
 forgot-0.062
 stayed-0.053
 waited-0.050
 hoped-0.049
 forget-0.047
Token she
Token ID673
Feature activation+9.94e+00

Pos logit contributions
 forgot+0.070
ode+0.060
 stayed+0.060
 waited+0.055
 scar+0.055
Neg logit contributions
 This-0.050
 Today-0.042
ore-0.040
ummy-0.040
elly-0.039
Token hugged
Token ID41130
Feature activation-3.82e+00

Pos logit contributions
ode+0.116
 passengers+0.102
 scar+0.098
 forgot+0.097
 promise+0.093
Neg logit contributions
 This-0.192
elly-0.174
-0.171
ires-0.169
ore-0.168
Token it
Token ID340
Feature activation-6.96e-01

Pos logit contributions
 This+0.061
 Today+0.059
elly+0.055
ummy+0.055
ore+0.053
Neg logit contributions
 forgot-0.093
 stayed-0.080
 waited-0.073
 hoped-0.072
 forget-0.070
Token tight
Token ID5381
Feature activation-4.79e+00

Pos logit contributions
 This+0.010
 Today+0.009
ummy+0.009
elly+0.009
ore+0.008
Neg logit contributions
 forgot-0.018
 stayed-0.016
 waited-0.015
 hoped-0.014
 forget-0.014
Token and
Token ID290
Feature activation+4.86e+00

Pos logit contributions
 This+0.061
 Today+0.058
elly+0.054
ummy+0.053
ires+0.051
Neg logit contributions
 forgot-0.131
 stayed-0.117
 waited-0.107
 hoped-0.106
 learned-0.103
Token smiled
Token ID13541
Feature activation-3.24e+00

Pos logit contributions
 forgot+0.065
ode+0.062
 stayed+0.050
ppy+0.046
 forget+0.043
Neg logit contributions
 This-0.107
 Today-0.091
 late-0.091
ummy-0.091
ires-0.090
Token."
Token ID526
Feature activation-4.19e+00

Pos logit contributions
 This+0.041
 Today+0.039
elly+0.036
ummy+0.036
ore+0.034
Neg logit contributions
 forgot-0.093
 stayed-0.082
 waited-0.076
 hoped-0.075
 forget-0.073
Token Spot
Token ID15899
Feature activation+5.82e+00

Pos logit contributions
 This+0.065
 Today+0.065
elly+0.063
uttering+0.062
ummy+0.061
Neg logit contributions
 forgot-0.100
 stayed-0.088
 waited-0.080
 hoped-0.078
 learned-0.076
Token felt
Token ID2936
Feature activation+1.36e+00

Pos logit contributions
 forgot+0.090
ode+0.079
 forget+0.079
 passengers+0.077
 least+0.075
Neg logit contributions
 This-0.118
-0.101
 Today-0.099
 A-0.096
elly-0.095
Token guilty
Token ID6717
Feature activation-3.41e+00

Pos logit contributions
 forgot+0.028
 stayed+0.023
 waited+0.020
 hoped+0.020
 learned+0.020
Neg logit contributions
 This-0.027
 Today-0.027
elly-0.026
ummy-0.025
ires-0.024
Token because
Token ID780
Feature activation+1.59e+00

Pos logit contributions
 This+0.059
 Today+0.057
elly+0.054
ires+0.053
ummy+0.053
Neg logit contributions
 forgot-0.078
 stayed-0.067
 waited-0.059
 hoped-0.059
 learned-0.058
Token he
Token ID339
Feature activation+9.94e+00

Pos logit contributions
 forgot+0.038
 stayed+0.033
 waited+0.030
 hoped+0.030
 forget+0.029
Neg logit contributions
 This-0.026
 Today-0.025
ummy-0.023
elly-0.023
ore-0.022
Token knew
Token ID2993
Feature activation+2.38e-01

Pos logit contributions
 forgot+0.134
 forget+0.122
 passengers+0.121
ode+0.120
 stayed+0.117
Neg logit contributions
 This-0.198
elly-0.185
-0.181
 Today-0.174
looking-0.173
Token Fl
Token ID1610
Feature activation-1.77e+00

Pos logit contributions
 forgot+0.006
 stayed+0.005
 waited+0.005
 forget+0.005
 hoped+0.005
Neg logit contributions
 This-0.004
 Today-0.003
ummy-0.003
elly-0.003
ires-0.003
Tokenuffy
Token ID15352
Feature activation+3.29e+00

Pos logit contributions
 This+0.038
 Today+0.036
 These+0.031
looking+0.031
ires+0.030
Neg logit contributions
 forgot-0.034
 stayed-0.028
 promise-0.023
 waited-0.023
 hoped-0.022
Token was
Token ID373
Feature activation+3.71e+00

Pos logit contributions
 forgot+0.057
 stayed+0.046
 waited+0.043
 forget+0.042
 hoped+0.041
Neg logit contributions
 This-0.072
 Today-0.065
elly-0.063
ummy-0.062
ore-0.062
Token right
Token ID826
Feature activation-1.83e+00

Pos logit contributions
 forgot+0.081
 stayed+0.068
 waited+0.061
 hoped+0.061
 forget+0.059
Neg logit contributions
 This-0.069
 Today-0.065
elly-0.062
ummy-0.062
ires-0.060
Token.
Token ID13
Feature activation-3.28e+00

Pos logit contributions
 forgot+0.074
 stayed+0.065
 hoped+0.059
 waited+0.059
 forget+0.059
Neg logit contributions
 This-0.037
 Today-0.035
elly-0.034
ummy-0.032
ires-0.031
Token Lily
Token ID20037
Feature activation+7.09e+00

Pos logit contributions
 This+0.037
 Today+0.037
elly+0.036
uttering+0.036
ummy+0.034
Neg logit contributions
 forgot-0.091
 stayed-0.079
 hoped-0.074
 waited-0.073
 learned-0.072
Token was
Token ID373
Feature activation+3.50e+00

Pos logit contributions
ode+0.104
 stations+0.099
 passengers+0.099
 forgot+0.094
 nurses+0.093
Neg logit contributions
-0.115
 This-0.112
 The-0.108
-0.107
:-0.102
Token ashamed
Token ID22461
Feature activation-4.27e+00

Pos logit contributions
 forgot+0.075
 stayed+0.062
 waited+0.058
 hoped+0.055
 wouldn+0.054
Neg logit contributions
 This-0.064
 Today-0.060
ummy-0.056
elly-0.055
uttering-0.055
Token that
Token ID326
Feature activation+5.31e-01

Pos logit contributions
 This+0.063
 Today+0.060
elly+0.058
ummy+0.057
ore+0.053
Neg logit contributions
 forgot-0.109
 stayed-0.096
 waited-0.088
 hoped-0.087
 forget-0.084
Token she
Token ID673
Feature activation+9.94e+00

Pos logit contributions
 forgot+0.014
 stayed+0.012
 waited+0.011
 hoped+0.011
 managed+0.010
Neg logit contributions
 This-0.008
 Today-0.007
ummy-0.007
elly-0.007
ore-0.006
Token got
Token ID1392
Feature activation-4.62e-01

Pos logit contributions
ode+0.148
 scar+0.132
 passengers+0.126
 promise+0.120
 mast+0.120
Neg logit contributions
 This-0.168
-0.152
ore-0.152
 late-0.151
looking-0.148
Token lost
Token ID2626
Feature activation-3.81e+00

Pos logit contributions
 This+0.006
 Today+0.005
ore+0.005
elly+0.005
ummy+0.005
Neg logit contributions
 forgot-0.012
 stayed-0.010
 waited-0.010
 hoped-0.010
 forget-0.009
Token,
Token ID11
Feature activation+1.93e+00

Pos logit contributions
 This+0.057
 Today+0.055
elly+0.052
ummy+0.051
ore+0.049
Neg logit contributions
 forgot-0.096
 stayed-0.082
 waited-0.076
 hoped-0.074
 forget-0.073
Token but
Token ID475
Feature activation+4.18e+00

Pos logit contributions
 forgot+0.048
 stayed+0.042
ode+0.041
 waited+0.041
 promise+0.039
Neg logit contributions
 This-0.024
 late-0.022
 Today-0.021
elly-0.017
 She-0.017
Token her
Token ID607
Feature activation+4.27e+00

Pos logit contributions
 forgot+0.110
ode+0.101
 stayed+0.094
 scar+0.092
 argued+0.091
Neg logit contributions
 This-0.042
 late-0.036
 Today-0.035
ummy-0.034
ires-0.031
Token,
Token ID11
Feature activation-3.14e-01

Pos logit contributions
 forgot+0.011
 stayed+0.010
 hoped+0.009
 waited+0.009
 learned+0.009
Neg logit contributions
 This-0.006
 Today-0.005
ummy-0.005
ore-0.004
elly-0.004
Token she
Token ID673
Feature activation+8.54e+00

Pos logit contributions
 This+0.005
 Today+0.005
ummy+0.004
ore+0.004
ires+0.004
Neg logit contributions
 forgot-0.008
 stayed-0.007
 waited-0.006
 hoped-0.006
 argued-0.006
Token had
Token ID550
Feature activation+3.28e+00

Pos logit contributions
 forgot+0.126
 argued+0.112
ode+0.109
 stayed+0.100
 punished+0.096
Neg logit contributions
 This-0.157
-0.153
 Today-0.152
ore-0.148
elly-0.140
Token two
Token ID734
Feature activation+2.61e+00

Pos logit contributions
 forgot+0.089
 stayed+0.075
 promise+0.074
 forget+0.074
 hoped+0.072
Neg logit contributions
 This-0.039
 Today-0.030
 late-0.029
ummy-0.026
-0.026
Token things
Token ID1243
Feature activation-7.33e-01

Pos logit contributions
 forgot+0.053
 stayed+0.044
 waited+0.044
 hoped+0.042
 overs+0.040
Neg logit contributions
ummy-0.041
elly-0.039
 Today-0.038
 This-0.038
ay-0.035
Token she
Token ID673
Feature activation+9.93e+00

Pos logit contributions
 This+0.009
 Today+0.008
elly+0.008
ummy+0.008
ore+0.007
Neg logit contributions
 forgot-0.020
 stayed-0.018
 waited-0.017
 hoped-0.016
 forget-0.016
Token called
Token ID1444
Feature activation-5.20e-01

Pos logit contributions
 forgot+0.139
 stayed+0.112
ode+0.103
 forget+0.102
 argued+0.098
Neg logit contributions
 This-0.222
elly-0.205
 Today-0.200
-0.195
ore-0.195
Token her
Token ID607
Feature activation+2.10e+00

Pos logit contributions
 Today+0.008
 This+0.008
elly+0.008
ummy+0.008
ires+0.008
Neg logit contributions
 forgot-0.012
 stayed-0.011
 waited-0.009
 hoped-0.009
 wouldn-0.009
Token own
Token ID898
Feature activation+1.82e+00

Pos logit contributions
 forgot+0.049
 stayed+0.042
 waited+0.038
 hoped+0.037
 forget+0.036
Neg logit contributions
 This-0.036
 Today-0.035
elly-0.033
ummy-0.033
ires-0.031
Token,
Token ID11
Feature activation+1.76e+00

Pos logit contributions
 forgot+0.045
 stayed+0.040
 waited+0.036
 hoped+0.036
 forget+0.035
Neg logit contributions
 This-0.028
 Today-0.027
elly-0.025
ummy-0.025
ires-0.024
Token and
Token ID290
Feature activation+4.01e+00

Pos logit contributions
 forgot+0.042
 stayed+0.035
 waited+0.034
 hoped+0.032
 managed+0.031
Neg logit contributions
 This-0.028
 Today-0.026
elly-0.024
ummy-0.023
ires-0.021
TokenS
Token ID50
Feature activation+1.45e-01

Pos logit contributions
 This+0.072
 Today+0.070
ummy+0.068
elly+0.066
ore+0.065
Neg logit contributions
 forgot-0.125
 stayed-0.109
 waited-0.102
 hoped-0.097
 learned-0.097
Tokenue
Token ID518
Feature activation+6.67e+00

Pos logit contributions
 forgot+0.003
 stayed+0.002
 waited+0.002
 hoped+0.002
 learned+0.002
Neg logit contributions
 This-0.003
 Today-0.003
elly-0.003
ore-0.003
ummy-0.003
Token felt
Token ID2936
Feature activation+1.48e+00

Pos logit contributions
 forgot+0.103
ode+0.096
 forget+0.092
 passengers+0.092
 promise+0.089
Neg logit contributions
 This-0.115
-0.110
elly-0.109
ore-0.106
 Today-0.095
Token guilty
Token ID6717
Feature activation-3.69e+00

Pos logit contributions
 forgot+0.030
 stayed+0.025
 hoped+0.022
 waited+0.022
 learned+0.021
Neg logit contributions
 This-0.031
 Today-0.030
elly-0.029
ummy-0.029
ires-0.027
Token because
Token ID780
Feature activation+1.50e+00

Pos logit contributions
 This+0.062
 Today+0.059
uttering+0.056
ires+0.055
elly+0.055
Neg logit contributions
 forgot-0.082
 stayed-0.072
 hoped-0.063
 waited-0.063
 wouldn-0.063
Token she
Token ID673
Feature activation+9.93e+00

Pos logit contributions
 forgot+0.036
 stayed+0.031
 waited+0.028
 hoped+0.028
 forget+0.027
Neg logit contributions
 This-0.025
 Today-0.024
elly-0.023
ummy-0.022
ore-0.022
Token made
Token ID925
Feature activation-2.53e+00

Pos logit contributions
 forgot+0.121
ode+0.116
 stayed+0.110
 forget+0.109
 scar+0.108
Neg logit contributions
 This-0.201
elly-0.198
-0.187
 late-0.181
looking-0.180
Token the
Token ID262
Feature activation+3.39e+00

Pos logit contributions
 This+0.035
 Today+0.032
ummy+0.030
elly+0.029
ires+0.028
Neg logit contributions
 forgot-0.068
 stayed-0.060
 waited-0.055
 hoped-0.054
 forget-0.053
Token calendar
Token ID11845
Feature activation-2.16e+00

Pos logit contributions
 forgot+0.077
 stayed+0.066
 waited+0.059
 hoped+0.058
 forget+0.056
Neg logit contributions
 This-0.061
 Today-0.059
elly-0.056
ummy-0.055
ires-0.053
Token messy
Token ID24097
Feature activation-4.34e+00

Pos logit contributions
 This+0.038
 Today+0.036
ummy+0.033
ore+0.033
elly+0.032
Neg logit contributions
 forgot-0.046
 stayed-0.039
 waited-0.036
 hoped-0.035
 sighed-0.034
Token.
Token ID13
Feature activation-3.61e+00

Pos logit contributions
 This+0.054
 Today+0.051
elly+0.046
ummy+0.045
uttering+0.044
Neg logit contributions
 forgot-0.122
 stayed-0.109
 waited-0.100
 hoped-0.099
 learned-0.096
Token,
Token ID11
Feature activation-4.76e-01

Pos logit contributions
 This+0.025
 Today+0.023
ummy+0.022
elly+0.020
ore+0.018
Neg logit contributions
 forgot-0.074
 stayed-0.066
 waited-0.063
 hoped-0.062
 forget-0.059
Token it
Token ID340
Feature activation+4.47e+00

Pos logit contributions
 This+0.007
 Today+0.007
ummy+0.006
elly+0.006
ires+0.006
Neg logit contributions
 forgot-0.012
 stayed-0.011
 hoped-0.010
 waited-0.010
 forget-0.009
Token kept
Token ID4030
Feature activation-1.06e+00

Pos logit contributions
 forgot+0.061
ode+0.061
 promise+0.057
 forget+0.054
 least+0.050
Neg logit contributions
 This-0.072
elly-0.071
time-0.070
 late-0.070
-0.070
Token on
Token ID319
Feature activation-1.47e+00

Pos logit contributions
 This+0.017
 Today+0.016
elly+0.015
ummy+0.015
ires+0.014
Neg logit contributions
 forgot-0.026
 stayed-0.023
 waited-0.021
 hoped-0.020
 forget-0.020
Token flying
Token ID7348
Feature activation-4.98e+00

Pos logit contributions
 This+0.025
 Today+0.024
elly+0.023
ummy+0.022
ires+0.021
Neg logit contributions
 forgot-0.035
 stayed-0.030
 waited-0.027
 hoped-0.027
 forget-0.026
Token err
Token ID11454
Feature activation-1.14e+01

Pos logit contributions
 This+0.077
 Today+0.073
elly+0.068
ummy+0.067
ore+0.065
Neg logit contributions
 forgot-0.125
 stayed-0.107
 waited-0.098
 hoped-0.096
 forget-0.095
Tokenatically
Token ID4142
Feature activation-1.40e+00

Pos logit contributions
 This+0.220
 Today+0.216
ummy+0.199
elly+0.199
ires+0.192
Neg logit contributions
 forgot-0.232
 stayed-0.198
 waited-0.178
 hoped-0.174
 learned-0.170
Token with
Token ID351
Feature activation+1.36e+00

Pos logit contributions
 This+0.021
 Today+0.020
elly+0.019
ummy+0.019
ires+0.018
Neg logit contributions
 forgot-0.035
 stayed-0.031
 waited-0.028
 hoped-0.028
 forget-0.027
Token inexplicable
Token ID49602
Feature activation+1.39e+00

Pos logit contributions
 forgot+0.036
 stayed+0.030
 waited+0.028
 hoped+0.027
 forget+0.027
Neg logit contributions
 This-0.020
 Today-0.018
ummy-0.017
elly-0.017
ires-0.016
Token speed
Token ID2866
Feature activation-3.17e+00

Pos logit contributions
 forgot+0.027
 stayed+0.022
 waited+0.020
 hoped+0.019
 learned+0.018
Neg logit contributions
 This-0.029
 Today-0.028
ummy-0.026
elly-0.026
uttering-0.026
Token.
Token ID13
Feature activation-4.57e+00

Pos logit contributions
 This+0.037
 Today+0.034
elly+0.032
ummy+0.031
ore+0.029
Neg logit contributions
 forgot-0.091
 stayed-0.080
 waited-0.075
 hoped-0.074
 forget-0.072
Token sometimes
Token ID3360
Feature activation+1.62e+00

Pos logit contributions
 forgot+0.075
 stayed+0.063
 hoped+0.058
 waited+0.057
 forget+0.056
Neg logit contributions
 This-0.051
 Today-0.048
ummy-0.043
ires-0.043
elly-0.041
Token her
Token ID607
Feature activation+4.37e+00

Pos logit contributions
 forgot+0.041
 stayed+0.037
 waited+0.034
 hoped+0.034
 sighed+0.034
Neg logit contributions
 This-0.021
 Today-0.019
ummy-0.018
ires-0.016
elly-0.016
Token drawings
Token ID23388
Feature activation-4.87e-01

Pos logit contributions
 forgot+0.097
 stayed+0.084
 waited+0.075
 hoped+0.073
 managed+0.072
Neg logit contributions
 This-0.076
 Today-0.071
ummy-0.069
ires-0.067
elly-0.066
Token would
Token ID561
Feature activation+2.62e+00

Pos logit contributions
 This+0.011
 Today+0.010
elly+0.009
ires+0.009
ore+0.009
Neg logit contributions
 forgot-0.007
 stayed-0.005
 waited-0.005
 sighed-0.005
 hoped-0.005
Token get
Token ID651
Feature activation-1.18e+00

Pos logit contributions
 forgot+0.046
 stayed+0.038
 hoped+0.034
 sighed+0.034
 waited+0.033
Neg logit contributions
 This-0.057
 Today-0.054
ummy-0.049
ires-0.047
elly-0.047
Token sm
Token ID895
Feature activation-1.10e+01

Pos logit contributions
 This+0.021
 Today+0.020
elly+0.020
ummy+0.019
ires+0.018
Neg logit contributions
 forgot-0.025
 stayed-0.022
 waited-0.020
 hoped-0.019
 forget-0.019
Tokenud
Token ID463
Feature activation-4.46e+00

Pos logit contributions
 This+0.083
 Today+0.076
+0.042
 These+0.041
ires+0.039
Neg logit contributions
 forgot-0.331
 stayed-0.298
 waited-0.279
 cleaned-0.277
 learned-0.276
Tokenged
Token ID2004
Feature activation-4.63e+00

Pos logit contributions
 This+0.071
 Today+0.070
elly+0.062
ires+0.061
ummy+0.061
Neg logit contributions
 forgot-0.109
 stayed-0.095
 waited-0.085
 hoped-0.083
 wouldn-0.082
Token because
Token ID780
Feature activation+1.27e-01

Pos logit contributions
 This+0.072
 Today+0.068
elly+0.064
ummy+0.064
ires+0.061
Neg logit contributions
 forgot-0.115
 stayed-0.099
 waited-0.091
 hoped-0.090
 forget-0.087
Token the
Token ID262
Feature activation+3.65e+00

Pos logit contributions
 forgot+0.003
 stayed+0.003
 waited+0.002
 hoped+0.002
 forget+0.002
Neg logit contributions
 This-0.002
 Today-0.002
elly-0.002
ummy-0.002
ires-0.002
Token paper
Token ID3348
Feature activation+1.72e+00

Pos logit contributions
 forgot+0.082
 stayed+0.070
 hoped+0.063
 waited+0.062
 managed+0.060
Neg logit contributions
 This-0.064
 Today-0.060
ummy-0.056
elly-0.056
ires-0.052
Token you
Token ID345
Feature activation+1.39e+00

Pos logit contributions
 This+0.083
 Today+0.082
elly+0.079
ummy+0.076
ires+0.074
Neg logit contributions
 forgot-0.096
 stayed-0.082
 waited-0.074
 hoped-0.071
 forget-0.070
Token.
Token ID13
Feature activation-2.54e+00

Pos logit contributions
 forgot+0.038
 stayed+0.033
 waited+0.031
 hoped+0.030
 forget+0.030
Neg logit contributions
 This-0.018
 Today-0.017
elly-0.016
ires-0.016
ummy-0.016
Token It
Token ID632
Feature activation+4.20e+00

Pos logit contributions
 Today+0.027
 This+0.026
elly+0.026
uttering+0.026
ummy+0.026
Neg logit contributions
 forgot-0.072
 stayed-0.065
 waited-0.060
 hoped-0.059
 forget-0.057
Token is
Token ID318
Feature activation+2.62e+00

Pos logit contributions
 forgot+0.107
 stayed+0.086
ppa+0.086
 forget+0.086
ode+0.086
Neg logit contributions
 This-0.057
ore-0.046
 Today-0.045
-0.044
elly-0.042
Token too
Token ID1165
Feature activation+1.13e+00

Pos logit contributions
 forgot+0.059
 stayed+0.050
 hoped+0.046
 waited+0.045
 sighed+0.045
Neg logit contributions
 This-0.044
 Today-0.041
 late-0.038
ires-0.037
elly-0.037
Token sm
Token ID895
Feature activation-1.09e+01

Pos logit contributions
 forgot+0.023
 stayed+0.019
 waited+0.018
 hoped+0.017
 bit+0.016
Neg logit contributions
 This-0.023
 Today-0.022
ires-0.021
ummy-0.020
uttering-0.020
Tokenelly
Token ID6148
Feature activation-5.28e+00

Pos logit contributions
 This+0.090
 Today+0.083
uttering+0.058
ires+0.055
 These+0.052
Neg logit contributions
 forgot-0.309
 stayed-0.285
 waited-0.274
 learned-0.264
 cleaned-0.262
Token for
Token ID329
Feature activation-1.85e+00

Pos logit contributions
 This+0.084
 Today+0.082
uttering+0.077
ires+0.075
ummy+0.074
Neg logit contributions
 forgot-0.123
 stayed-0.111
 waited-0.102
 hoped-0.098
 learned-0.095
Token us
Token ID514
Feature activation+3.77e-01

Pos logit contributions
 This+0.036
 Today+0.035
elly+0.033
ummy+0.033
ore+0.032
Neg logit contributions
 forgot-0.038
 stayed-0.032
 waited-0.029
 hoped-0.028
 forget-0.027
Token.
Token ID13
Feature activation-3.21e+00

Pos logit contributions
 forgot+0.011
 stayed+0.009
 waited+0.009
 hoped+0.009
 forget+0.008
Neg logit contributions
 This-0.005
 Today-0.004
elly-0.004
ummy-0.004
ires-0.004
Token We
Token ID775
Feature activation+6.02e+00

Pos logit contributions
uttering+0.037
ummy+0.035
 Today+0.035
elly+0.034
 This+0.034
Neg logit contributions
 forgot-0.086
 stayed-0.078
 waited-0.072
 hoped-0.072
 learned-0.069
Token Max
Token ID5436
Feature activation+5.75e+00

Pos logit contributions
 forgot+0.066
 stayed+0.057
ode+0.055
 hoped+0.054
 waited+0.053
Neg logit contributions
 This-0.037
 Today-0.034
ummy-0.031
 late-0.029
ires-0.028
Token thought
Token ID1807
Feature activation-2.62e+00

Pos logit contributions
 forgot+0.075
ode+0.060
 forget+0.058
 stayed+0.057
 passengers+0.055
Neg logit contributions
 This-0.131
 Today-0.121
elly-0.116
ore-0.113
ummy-0.112
Token it
Token ID340
Feature activation+2.75e+00

Pos logit contributions
 This+0.045
 Today+0.044
elly+0.042
ummy+0.041
ires+0.039
Neg logit contributions
 forgot-0.061
 stayed-0.052
 waited-0.047
 hoped-0.046
 forget-0.045
Token was
Token ID373
Feature activation+3.03e+00

Pos logit contributions
 forgot+0.048
 stayed+0.038
 forget+0.034
 waited+0.034
 hoped+0.034
Neg logit contributions
 This-0.062
 Today-0.059
elly-0.055
ummy-0.055
ore-0.054
Token too
Token ID1165
Feature activation+8.82e-01

Pos logit contributions
 forgot+0.065
 stayed+0.056
 waited+0.049
 hoped+0.049
 forget+0.047
Neg logit contributions
 This-0.057
 Today-0.056
elly-0.053
ummy-0.052
ore-0.051
Token sm
Token ID895
Feature activation-1.07e+01

Pos logit contributions
 forgot+0.017
 stayed+0.012
 bit+0.012
 waited+0.012
 learned+0.012
Neg logit contributions
 Today-0.019
 This-0.019
uttering-0.018
 Playing-0.017
ore-0.017
Tokenelly
Token ID6148
Feature activation-4.25e+00

Pos logit contributions
 This+0.093
 Today+0.087
 These+0.062
ires+0.061
+0.059
Neg logit contributions
 forgot-0.307
 stayed-0.278
 cleaned-0.255
 promised-0.253
 waited-0.253
Token and
Token ID290
Feature activation+4.43e+00

Pos logit contributions
 This+0.063
 Today+0.063
uttering+0.058
ires+0.056
elly+0.056
Neg logit contributions
 forgot-0.104
 stayed-0.093
 waited-0.084
 wouldn-0.083
 hoped-0.082
Token didn
Token ID1422
Feature activation-2.81e+00

Pos logit contributions
 forgot+0.091
 stayed+0.078
 waited+0.071
 hoped+0.070
 forget+0.069
Neg logit contributions
 This-0.081
 Today-0.074
elly-0.071
ummy-0.071
ires-0.068
Token't
Token ID470
Feature activation+3.75e+00

Pos logit contributions
elly+0.055
uttering+0.054
ires+0.049
 Today+0.049
joy+0.048
Neg logit contributions
 forgot-0.051
 never-0.046
 stayed-0.046
 forget-0.040
 wouldn-0.040
Token want
Token ID765
Feature activation-1.94e+00

Pos logit contributions
 forgot+0.076
 stayed+0.065
 hoped+0.060
 waited+0.059
 sighed+0.057
Neg logit contributions
 This-0.073
 Today-0.070
elly-0.065
ummy-0.063
ore-0.062
Token should
Token ID815
Feature activation+1.86e+00

Pos logit contributions
 forgot+0.107
 sighed+0.097
 stayed+0.090
 vowed+0.090
 hoped+0.090
Neg logit contributions
 This-0.080
ore-0.061
-0.060
 These-0.060
elly-0.060
Token be
Token ID307
Feature activation+2.90e+00

Pos logit contributions
 forgot+0.035
 stayed+0.028
 hoped+0.026
 managed+0.025
 sighed+0.025
Neg logit contributions
 This-0.040
 Today-0.037
ummy-0.035
ires-0.033
elly-0.033
Token compassionate
Token ID32533
Feature activation-4.93e+00

Pos logit contributions
 forgot+0.062
 stayed+0.051
 forget+0.047
 waited+0.047
 wouldn+0.046
Neg logit contributions
 This-0.052
elly-0.045
 Today-0.045
ires-0.043
 late-0.043
Token.
Token ID13
Feature activation-3.18e+00

Pos logit contributions
 This+0.065
 Today+0.063
uttering+0.057
ires+0.056
ummy+0.056
Neg logit contributions
 forgot-0.133
 stayed-0.117
 waited-0.108
 hoped-0.107
 learned-0.105
Token Comp
Token ID3082
Feature activation-6.94e-01

Pos logit contributions
uttering+0.039
ummy+0.034
 Today+0.033
ore+0.033
elly+0.031
Neg logit contributions
 forgot-0.083
 stayed-0.075
 hoped-0.070
 waited-0.068
 learned-0.068
Tokenassion
Token ID11857
Feature activation-1.07e+01

Pos logit contributions
 Today+0.011
 This+0.011
ummy+0.010
elly+0.010
ore+0.010
Neg logit contributions
 forgot-0.017
 stayed-0.014
 hoped-0.013
 waited-0.013
 learned-0.012
Tokenate
Token ID378
Feature activation-2.27e+00

Pos logit contributions
 This+0.175
 Today+0.169
uttering+0.154
ummy+0.149
 These+0.137
Neg logit contributions
 forgot-0.256
 stayed-0.218
 learned-0.207
 hoped-0.204
 waited-0.203
Token means
Token ID1724
Feature activation+2.95e-01

Pos logit contributions
 This+0.038
 Today+0.036
elly+0.034
ummy+0.034
ires+0.033
Neg logit contributions
 forgot-0.054
 stayed-0.046
 waited-0.042
 hoped-0.041
 forget-0.040
Token you
Token ID345
Feature activation+3.65e+00

Pos logit contributions
 forgot+0.007
 stayed+0.006
 hoped+0.005
 waited+0.005
 forget+0.005
Neg logit contributions
 This-0.005
 Today-0.005
ummy-0.005
elly-0.005
ires-0.005
Token care
Token ID1337
Feature activation-2.65e+00

Pos logit contributions
 forgot+0.070
 stayed+0.058
 waited+0.053
 hoped+0.053
 sighed+0.052
Neg logit contributions
 This-0.073
 Today-0.067
elly-0.064
ore-0.063
ummy-0.062
Token about
Token ID546
Feature activation-1.48e+00

Pos logit contributions
 Today+0.043
 This+0.042
uttering+0.041
ummy+0.040
elly+0.040
Neg logit contributions
 forgot-0.061
 stayed-0.053
 learned-0.047
 hoped-0.047
 never-0.046
Token he
Token ID339
Feature activation+7.53e+00

Pos logit contributions
 forgot+0.053
 stayed+0.045
 hoped+0.041
 waited+0.041
 learned+0.040
Neg logit contributions
 This-0.034
 Today-0.032
ummy-0.031
elly-0.029
ires-0.029
Token thought
Token ID1807
Feature activation-3.18e+00

Pos logit contributions
 forgot+0.118
 stayed+0.096
ode+0.094
 forget+0.092
 scar+0.089
Neg logit contributions
 This-0.159
 Today-0.143
-0.140
ore-0.136
elly-0.132
Token it
Token ID340
Feature activation+2.45e+00

Pos logit contributions
 This+0.050
 Today+0.046
ummy+0.044
ore+0.041
elly+0.041
Neg logit contributions
 forgot-0.080
 stayed-0.068
 waited-0.063
 hoped-0.062
 forget-0.062
Token was
Token ID373
Feature activation+3.25e+00

Pos logit contributions
 forgot+0.043
 stayed+0.034
 waited+0.031
 hoped+0.030
 forget+0.030
Neg logit contributions
 This-0.054
 Today-0.052
ummy-0.047
ore-0.046
elly-0.046
Token too
Token ID1165
Feature activation+1.09e+00

Pos logit contributions
 forgot+0.076
 stayed+0.064
 waited+0.059
 hoped+0.058
 forget+0.056
Neg logit contributions
 This-0.054
 Today-0.052
ummy-0.048
elly-0.047
ires-0.046
Token sm
Token ID895
Feature activation-1.06e+01

Pos logit contributions
 forgot+0.023
 stayed+0.018
 waited+0.017
 hoped+0.016
 learned+0.016
Neg logit contributions
 This-0.022
 Today-0.021
uttering-0.020
ummy-0.020
ires-0.020
Tokenelly
Token ID6148
Feature activation-4.51e+00

Pos logit contributions
 This+0.096
 Today+0.093
 These+0.065
 outer+0.063
ires+0.060
Neg logit contributions
 forgot-0.295
 stayed-0.266
 waited-0.248
 cleaned-0.247
 kept-0.244
Token.
Token ID13
Feature activation-3.21e+00

Pos logit contributions
 This+0.065
 Today+0.064
uttering+0.059
ires+0.058
elly+0.058
Neg logit contributions
 forgot-0.113
 stayed-0.101
 waited-0.092
 hoped-0.089
 wouldn-0.089
TokenJane
Token ID41083
Feature activation+6.98e+00

Pos logit contributions
 This+0.039
elly+0.038
uttering+0.038
 Today+0.037
ummy+0.037
Neg logit contributions
 forgot-0.086
 stayed-0.075
 waited-0.070
 hoped-0.070
 learned-0.068
Token said
Token ID531
Feature activation-1.89e+00

Pos logit contributions
 forgot+0.100
 forget+0.086
ode+0.084
 passengers+0.084
 scar+0.078
Neg logit contributions
 This-0.131
 Today-0.122
elly-0.121
-0.119
ore-0.117
Token,
Token ID11
Feature activation-1.79e-01

Pos logit contributions
 Today+0.028
 This+0.028
elly+0.027
ires+0.026
ummy+0.026
Neg logit contributions
 forgot-0.048
 stayed-0.042
 waited-0.038
 hoped-0.038
 learned-0.036
Token sign
Token ID1051
Feature activation-1.89e+00

Pos logit contributions
 forgot+0.064
 stayed+0.057
 hoped+0.051
 waited+0.051
 promised+0.049
Neg logit contributions
 Today-0.041
 This-0.040
ummy-0.033
elly-0.033
ore-0.032
Token that
Token ID326
Feature activation+3.12e+00

Pos logit contributions
 Today+0.031
 This+0.031
elly+0.029
ummy+0.029
ires+0.028
Neg logit contributions
 forgot-0.044
 stayed-0.039
 waited-0.035
 hoped-0.035
 learned-0.033
Token said
Token ID531
Feature activation-2.40e+00

Pos logit contributions
 forgot+0.047
 stayed+0.035
 forget+0.032
ode+0.032
 promise+0.030
Neg logit contributions
 This-0.076
 Today-0.070
ore-0.067
ires-0.067
elly-0.067
Token "
Token ID366
Feature activation-1.30e+00

Pos logit contributions
elly+0.033
 Today+0.032
ummy+0.031
 This+0.030
ires+0.030
Neg logit contributions
 forgot-0.062
 stayed-0.057
 waited-0.050
 hoped-0.050
 never-0.049
TokenRE
Token ID2200
Feature activation-4.79e+00

Pos logit contributions
 This+0.022
 Today+0.022
ummy+0.021
ires+0.020
elly+0.020
Neg logit contributions
 forgot-0.029
 stayed-0.026
 waited-0.024
 hoped-0.022
 forget-0.022
TokenVERS
Token ID28884
Feature activation-1.06e+01

Pos logit contributions
 This+0.078
 Today+0.076
elly+0.072
ummy+0.071
ires+0.069
Neg logit contributions
 forgot-0.113
 stayed-0.096
 waited-0.088
 hoped-0.087
 forget-0.084
TokenE
Token ID36
Feature activation-3.74e+00

Pos logit contributions
 Today+0.168
 This+0.165
ummy+0.149
ires+0.134
elly+0.134
Neg logit contributions
 forgot-0.251
 stayed-0.221
 waited-0.203
 hoped-0.198
 never-0.195
Token".
Token ID1911
Feature activation-4.30e+00

Pos logit contributions
 Today+0.058
 This+0.055
 Nice+0.047
ires+0.045
uttering+0.045
Neg logit contributions
 forgot-0.086
 stayed-0.077
 waited-0.072
 never-0.068
 kept-0.066
Token L
Token ID406
Feature activation-6.17e-02

Pos logit contributions
elly+0.057
 Today+0.057
 This+0.056
uttering+0.056
ummy+0.056
Neg logit contributions
 forgot-0.107
 stayed-0.093
 waited-0.087
 hoped-0.087
 learned-0.084
Tokenila
Token ID10102
Feature activation+5.72e+00

Pos logit contributions
 This+0.001
 Today+0.001
ummy+0.001
elly+0.001
ires+0.001
Neg logit contributions
 forgot-0.001
 stayed-0.001
 waited-0.001
 hoped-0.001
 learned-0.001
Token and
Token ID290
Feature activation+3.92e+00

Pos logit contributions
 forgot+0.151
 forget+0.131
 stayed+0.129
 promise+0.126
 least+0.124
Neg logit contributions
 This-0.064
elly-0.055
 Today-0.051
-0.050
ore-0.050
Token!
Token ID0
Feature activation-1.41e+00

Pos logit contributions
 forgot+0.065
 stayed+0.057
 waited+0.052
 hoped+0.052
 forget+0.050
Neg logit contributions
 This-0.029
 Today-0.028
elly-0.026
ummy-0.025
ires-0.024
Token That
Token ID1320
Feature activation+5.45e+00

Pos logit contributions
uttering+0.016
 Today+0.014
ires+0.014
elly+0.014
ore+0.013
Neg logit contributions
 forgot-0.038
 stayed-0.034
 waited-0.031
 forget-0.030
 hoped-0.030
Token flower
Token ID15061
Feature activation+1.25e+00

Pos logit contributions
 forgot+0.101
 stayed+0.081
 hoped+0.073
 waited+0.072
 managed+0.068
Neg logit contributions
 This-0.120
 Today-0.112
elly-0.110
ummy-0.109
ore-0.105
Token is
Token ID318
Feature activation+3.07e+00

Pos logit contributions
 forgot+0.030
 stayed+0.025
 hoped+0.024
 waited+0.024
 sighed+0.024
Neg logit contributions
 This-0.019
ore-0.017
ummy-0.017
elly-0.017
 Today-0.016
Token too
Token ID1165
Feature activation+1.17e+00

Pos logit contributions
 forgot+0.063
 stayed+0.052
 hoped+0.048
 waited+0.048
 forget+0.045
Neg logit contributions
 This-0.060
 Today-0.055
ummy-0.054
elly-0.053
ires-0.051
Token sm
Token ID895
Feature activation-1.05e+01

Pos logit contributions
 forgot+0.024
 stayed+0.019
 waited+0.017
 bit+0.017
 hoped+0.017
Neg logit contributions
 Today-0.024
 This-0.024
ires-0.021
 These-0.021
uttering-0.020
Tokenelly
Token ID6148
Feature activation-4.20e+00

Pos logit contributions
 This+0.073
 Today+0.070
ires+0.046
uttering+0.040
 These+0.039
Neg logit contributions
 forgot-0.323
 stayed-0.291
 waited-0.272
 cleaned-0.268
 learned-0.267
Token.
Token ID13
Feature activation-2.66e+00

Pos logit contributions
 This+0.064
 Today+0.063
uttering+0.058
elly+0.058
ires+0.057
Neg logit contributions
 forgot-0.103
 stayed-0.091
 waited-0.083
 hoped-0.080
 never-0.078
Token Please
Token ID4222
Feature activation+2.02e-01

Pos logit contributions
uttering+0.029
elly+0.027
 Today+0.027
 This+0.026
ires+0.026
Neg logit contributions
 forgot-0.073
 stayed-0.066
 waited-0.060
 hoped-0.060
 learned-0.058
Token take
Token ID1011
Feature activation-1.77e+00

Pos logit contributions
 forgot+0.004
 stayed+0.003
 hoped+0.003
 waited+0.002
 sighed+0.002
Neg logit contributions
 This-0.004
 Today-0.004
ummy-0.004
ore-0.004
elly-0.004
Token it
Token ID340
Feature activation-5.31e-01

Pos logit contributions
 This+0.032
 Today+0.028
ore+0.027
ummy+0.027
elly+0.027
Neg logit contributions
 forgot-0.042
 stayed-0.034
 hoped-0.031
 forget-0.031
 waited-0.031
Token,
Token ID11
Feature activation+1.25e+00

Pos logit contributions
 This+0.008
elly+0.008
 Today+0.008
ires+0.008
uttering+0.008
Neg logit contributions
 forgot-0.013
 stayed-0.011
 waited-0.010
 forget-0.010
 wouldn-0.010
Token but
Token ID475
Feature activation+2.69e+00

Pos logit contributions
 forgot+0.030
 stayed+0.025
 waited+0.023
 forget+0.022
 hoped+0.022
Neg logit contributions
 This-0.020
 Today-0.019
elly-0.016
ires-0.015
ummy-0.015
Token it
Token ID340
Feature activation+4.22e+00

Pos logit contributions
 forgot+0.067
 stayed+0.057
 forget+0.052
 hoped+0.051
 waited+0.051
Neg logit contributions
 This-0.040
 Today-0.037
ummy-0.033
ires-0.032
ore-0.032
Token smelled
Token ID37609
Feature activation-2.35e+00

Pos logit contributions
 forgot+0.089
ode+0.077
 forget+0.077
ppa+0.076
 passengers+0.073
Neg logit contributions
 This-0.053
time-0.047
ore-0.046
 Today-0.046
iring-0.044
Token very
Token ID845
Feature activation-2.19e-01

Pos logit contributions
 This+0.046
 Today+0.045
elly+0.044
ummy+0.042
ore+0.042
Neg logit contributions
 forgot-0.049
 stayed-0.042
 waited-0.036
 hoped-0.036
 forget-0.035
Token sm
Token ID895
Feature activation-1.05e+01

Pos logit contributions
 This+0.005
 Today+0.004
ore+0.004
elly+0.004
uttering+0.004
Neg logit contributions
 forgot-0.005
 stayed-0.004
 hoped-0.003
 waited-0.003
 forget-0.003
Tokenelly
Token ID6148
Feature activation-3.88e+00

Pos logit contributions
 This+0.086
 Today+0.081
 These+0.056
ires+0.053
uttering+0.051
Neg logit contributions
 forgot-0.302
 stayed-0.274
 cleaned-0.253
 waited-0.253
 learned-0.251
Token.
Token ID13
Feature activation-3.67e+00

Pos logit contributions
 This+0.056
 Today+0.055
uttering+0.052
ires+0.050
elly+0.049
Neg logit contributions
 forgot-0.096
 stayed-0.087
 waited-0.078
 hoped-0.076
 wouldn-0.076
Token He
Token ID679
Feature activation+7.54e+00

Pos logit contributions
elly+0.056
uttering+0.056
ore+0.050
ires+0.049
ummy+0.049
Neg logit contributions
 forgot-0.089
 stayed-0.078
 waited-0.076
 hoped-0.073
 learned-0.070
Token quickly
Token ID2952
Feature activation+4.44e+00

Pos logit contributions
ode+0.113
 forget+0.109
 forgot+0.107
 promise+0.101
 least+0.101
Neg logit contributions
 This-0.113
 A-0.109
 On-0.107
looking-0.106
-0.105
Token backed
Token ID9763
Feature activation-3.55e+00

Pos logit contributions
 least+0.062
 forgot+0.060
ode+0.056
 forget+0.055
 promise+0.054
Neg logit contributions
 This-0.079
looking-0.078
elly-0.071
 On-0.067
.-0.066
Token I
Token ID314
Feature activation+5.46e+00

Pos logit contributions
 This+0.031
 Today+0.030
elly+0.028
ummy+0.028
ires+0.027
Neg logit contributions
 forgot-0.046
 stayed-0.039
 waited-0.036
 hoped-0.035
 forget-0.034
Token can
Token ID460
Feature activation+7.17e-01

Pos logit contributions
 forgot+0.100
 stayed+0.081
 waited+0.071
 hoped+0.071
 sighed+0.066
Neg logit contributions
 This-0.122
 Today-0.117
elly-0.111
ummy-0.110
ore-0.109
Token find
Token ID1064
Feature activation-1.97e+00

Pos logit contributions
 forgot+0.016
 stayed+0.014
 waited+0.012
 forget+0.012
 hoped+0.012
Neg logit contributions
 This-0.013
 Today-0.012
elly-0.012
ires-0.011
ummy-0.011
Token something
Token ID1223
Feature activation-1.21e+00

Pos logit contributions
 Today+0.032
 This+0.032
elly+0.030
uttering+0.028
ummy+0.028
Neg logit contributions
 forgot-0.046
 stayed-0.041
 waited-0.037
 hoped-0.036
 learned-0.035
Token gl
Token ID1278
Feature activation-6.12e+00

Pos logit contributions
 This+0.017
 Today+0.017
elly+0.016
uttering+0.015
ummy+0.014
Neg logit contributions
 forgot-0.031
 stayed-0.028
 waited-0.025
 forget-0.025
 hoped-0.025
Tokenimmer
Token ID10957
Feature activation-1.05e+01

Pos logit contributions
 This+0.117
 Today+0.107
elly+0.105
+0.105
 These+0.104
Neg logit contributions
 forgot-0.116
 stayed-0.105
 promise-0.093
 wouldn-0.091
ode-0.089
Tokening
Token ID278
Feature activation-4.29e+00

Pos logit contributions
 This+0.173
 Today+0.156
 Playing+0.152
uttering+0.150
 These+0.150
Neg logit contributions
 forgot-0.215
 stayed-0.197
 waited-0.177
 wouldn-0.177
 kept-0.173
Token?"
Token ID1701
Feature activation-5.06e+00

Pos logit contributions
 This+0.058
 Today+0.055
elly+0.052
ummy+0.051
ires+0.049
Neg logit contributions
 forgot-0.113
 stayed-0.101
 waited-0.092
 hoped-0.090
 forget-0.088
Token
Token ID220
Feature activation-6.61e+00

Pos logit contributions
 This+0.065
 Today+0.061
elly+0.056
ummy+0.055
ore+0.053
Neg logit contributions
 forgot-0.141
 stayed-0.124
 waited-0.114
 hoped-0.113
 forget-0.110
Token
Token ID198
Feature activation-6.59e+00

Pos logit contributions
elly+0.097
uttering+0.094
 Today+0.088
ummy+0.087
ocol+0.086
Neg logit contributions
 forgot-0.151
 stayed-0.129
 hoped-0.125
 never-0.121
 learned-0.120
Token
Token ID198
Feature activation-5.73e+00

Pos logit contributions
elly+0.084
 Today+0.080
ires+0.079
uttering+0.079
ummy+0.078
Neg logit contributions
 forgot-0.171
 stayed-0.154
 waited-0.146
 learned-0.144
 hoped-0.142
Token mother
Token ID2802
Feature activation+1.92e+00

Pos logit contributions
 This+0.002
 Today+0.002
ummy+0.002
elly+0.002
ires+0.002
Neg logit contributions
 forgot-0.002
 stayed-0.002
 managed-0.002
 waited-0.002
 hoped-0.002
Token.
Token ID13
Feature activation-2.53e+00

Pos logit contributions
 forgot+0.051
 stayed+0.045
 waited+0.041
 hoped+0.041
 forget+0.040
Neg logit contributions
 This-0.026
 Today-0.025
elly-0.023
ires-0.022
uttering-0.022
Token We
Token ID775
Feature activation+6.28e+00

Pos logit contributions
uttering+0.036
elly+0.032
ires+0.032
looking+0.030
igsaw+0.029
Neg logit contributions
 forgot-0.058
 stayed-0.053
 waited-0.050
 hoped-0.048
 forget-0.048
Token love
Token ID1842
Feature activation-2.52e+00

Pos logit contributions
 forgot+0.136
 stayed+0.116
 sighed+0.112
ode+0.110
 hoped+0.108
Neg logit contributions
 Today-0.083
 This-0.082
-0.074
elly-0.072
ore-0.065
Token g
Token ID308
Feature activation-6.03e+00

Pos logit contributions
 This+0.047
 Today+0.047
elly+0.045
uttering+0.043
ore+0.042
Neg logit contributions
 forgot-0.054
 stayed-0.046
 waited-0.042
 hoped-0.040
 forget-0.039
Tokenaj
Token ID1228
Feature activation-1.05e+01

Pos logit contributions
 This+0.059
 Today+0.053
+0.049
 Where+0.045
 late+0.042
Neg logit contributions
 forgot-0.168
 stayed-0.144
 waited-0.137
 laughed-0.134
 argued-0.134
Tokenar
Token ID283
Feature activation-4.08e+00

Pos logit contributions
 Today+0.169
 This+0.167
elly+0.161
uttering+0.156
ore+0.156
Neg logit contributions
 forgot-0.229
 stayed-0.205
 waited-0.187
 learned-0.171
 hugged-0.170
Token ka
Token ID38387
Feature activation-2.44e+00

Pos logit contributions
 This+0.058
 Today+0.057
elly+0.050
ummy+0.049
ires+0.048
Neg logit contributions
 forgot-0.106
 stayed-0.093
 waited-0.085
 hoped-0.084
 learned-0.082
Token hal
Token ID10284
Feature activation-5.53e+00

Pos logit contributions
 Today+0.047
 This+0.047
elly+0.044
ires+0.043
ore+0.043
Neg logit contributions
 forgot-0.049
 stayed-0.042
 waited-0.037
 hoped-0.035
 learned-0.034
Tokenwa
Token ID10247
Feature activation-1.31e+00

Pos logit contributions
 Today+0.104
 This+0.103
elly+0.102
ires+0.097
igsaw+0.093
Neg logit contributions
 forgot-0.102
 stayed-0.098
 waited-0.081
 wouldn-0.080
 hugged-0.076
Token.
Token ID13
Feature activation-3.03e+00

Pos logit contributions
 This+0.019
 Today+0.019
elly+0.017
uttering+0.017
ires+0.017
Neg logit contributions
 forgot-0.032
 stayed-0.029
 waited-0.026
 learned-0.025
 hoped-0.025
Token,
Token ID11
Feature activation+5.50e-01

Pos logit contributions
 This+0.050
 Today+0.046
ummy+0.043
elly+0.042
ore+0.039
Neg logit contributions
 forgot-0.139
 stayed-0.123
 waited-0.115
 hoped-0.114
 forget-0.111
Token even
Token ID772
Feature activation+4.15e+00

Pos logit contributions
 forgot+0.013
 stayed+0.011
 waited+0.010
 hoped+0.010
 forget+0.010
Neg logit contributions
 This-0.008
 Today-0.008
ummy-0.007
elly-0.007
 late-0.007
Token if
Token ID611
Feature activation+4.45e-01

Pos logit contributions
 forgot+0.105
 stayed+0.091
 waited+0.083
 hoped+0.082
 forget+0.080
Neg logit contributions
 This-0.062
 Today-0.059
elly-0.056
ummy-0.055
ires-0.053
Token it
Token ID340
Feature activation+4.02e+00

Pos logit contributions
 forgot+0.011
 stayed+0.009
 hoped+0.009
 waited+0.009
 forget+0.008
Neg logit contributions
 This-0.007
 Today-0.006
ummy-0.006
elly-0.006
ore-0.006
Token tasted
Token ID29187
Feature activation-4.35e+00

Pos logit contributions
 forgot+0.072
 stayed+0.056
 hoped+0.053
 forget+0.052
 waited+0.051
Neg logit contributions
 This-0.086
 Today-0.080
ummy-0.076
ore-0.076
elly-0.075
Token y
Token ID331
Feature activation-1.04e+01

Pos logit contributions
 This+0.089
 Today+0.087
elly+0.083
ummy+0.081
ore+0.080
Neg logit contributions
 forgot-0.087
 stayed-0.073
 waited-0.064
 hoped-0.062
 forget-0.060
Tokenucky
Token ID5309
Feature activation-7.93e-01

Pos logit contributions
 This+0.091
 Today+0.089
uttering+0.078
+0.072
 outer+0.063
Neg logit contributions
 forgot-0.280
 stayed-0.258
 kept-0.238
 waited-0.237
 bit-0.236
Token.
Token ID13
Feature activation-3.22e+00

Pos logit contributions
 This+0.011
 Today+0.010
elly+0.009
ummy+0.009
ires+0.009
Neg logit contributions
 forgot-0.021
 stayed-0.019
 waited-0.017
 hoped-0.017
 forget-0.017
Token<|endoftext|>
Token ID50256
Feature activation-7.45e+00

Pos logit contributions
uttering+0.038
elly+0.038
 This+0.036
ires+0.036
ummy+0.035
Neg logit contributions
 forgot-0.085
 stayed-0.075
 hoped-0.069
 waited-0.069
 learned-0.068
TokenOnce
Token ID7454
Feature activation-2.99e+00

Pos logit contributions
uttering+0.140
ires+0.136
elly+0.124
ocol+0.124
ummy+0.123
Neg logit contributions
 forgot-0.145
 learned-0.127
 stayed-0.125
 felt-0.120
 had-0.120
Token upon
Token ID2402
Feature activation-2.15e+00

Pos logit contributions
 This+0.050
elly+0.046
 Today+0.046
ach+0.043
ires+0.043
Neg logit contributions
 forgot-0.071
 stayed-0.058
 hoped-0.053
 forget-0.051
 learned-0.051
Token he
Token ID339
Feature activation+7.60e+00

Pos logit contributions
 forgot+0.091
 promise+0.075
 stayed+0.075
 hoped+0.070
 waited+0.070
Neg logit contributions
 This-0.086
 Today-0.078
elly-0.072
ummy-0.072
 late-0.070
Token tried
Token ID3088
Feature activation-3.58e+00

Pos logit contributions
 forgot+0.107
ode+0.097
 forget+0.091
 promise+0.087
 least+0.085
Neg logit contributions
 This-0.141
ore-0.132
 Today-0.131
-0.125
elly-0.125
Token to
Token ID284
Feature activation+2.69e+00

Pos logit contributions
 This+0.048
 Today+0.045
elly+0.042
ummy+0.041
ore+0.039
Neg logit contributions
 forgot-0.097
 stayed-0.085
 waited-0.078
 hoped-0.078
 forget-0.075
Token take
Token ID1011
Feature activation-2.07e+00

Pos logit contributions
 forgot+0.055
 stayed+0.043
 hoped+0.042
 sighed+0.040
 regretted+0.040
Neg logit contributions
 This-0.048
 Today-0.047
ore-0.041
ummy-0.040
ach-0.040
Token deep
Token ID2769
Feature activation-4.88e+00

Pos logit contributions
 This+0.035
 Today+0.032
elly+0.030
ummy+0.030
ore+0.029
Neg logit contributions
 forgot-0.050
 stayed-0.042
 waited-0.039
 hoped-0.038
 forget-0.038
Token breaths
Token ID45576
Feature activation-1.04e+01

Pos logit contributions
 This+0.121
 Today+0.117
elly+0.113
ummy+0.112
ires+0.110
Neg logit contributions
 forgot-0.075
 stayed-0.061
 waited-0.052
 hoped-0.050
 learned-0.047
Token to
Token ID284
Feature activation+1.10e+00

Pos logit contributions
 This+0.150
 Today+0.144
elly+0.132
ires+0.129
ummy+0.128
Neg logit contributions
 forgot-0.267
 stayed-0.234
 waited-0.214
 hoped-0.211
 forget-0.205
Token calm
Token ID9480
Feature activation-5.59e+00

Pos logit contributions
 forgot+0.022
 stayed+0.018
 waited+0.016
 hoped+0.016
 sighed+0.015
Neg logit contributions
 This-0.023
 Today-0.021
ore-0.020
ummy-0.019
ires-0.019
Token down
Token ID866
Feature activation-2.91e+00

Pos logit contributions
 This+0.089
 Today+0.086
elly+0.083
ummy+0.080
ires+0.078
Neg logit contributions
 forgot-0.136
 stayed-0.119
 waited-0.107
 hoped-0.106
 forget-0.102
Token.
Token ID13
Feature activation-3.72e+00

Pos logit contributions
elly+0.044
 This+0.043
 Today+0.043
ummy+0.041
ires+0.040
Neg logit contributions
 forgot-0.068
 stayed-0.062
 waited-0.056
 hoped-0.055
 never-0.054
Token Tim
Token ID5045
Feature activation+5.34e+00

Pos logit contributions
elly+0.054
uttering+0.053
ires+0.050
ummy+0.049
 This+0.049
Neg logit contributions
 forgot-0.091
 stayed-0.079
 waited-0.074
 hoped-0.073
 learned-0.070
Token her
Token ID607
Feature activation+3.56e+00

Pos logit contributions
 This+0.016
 Today+0.015
ummy+0.014
elly+0.013
ires+0.013
Neg logit contributions
 forgot-0.025
 stayed-0.022
 waited-0.020
 hoped-0.019
 forget-0.019
Token cr
Token ID1067
Feature activation-7.38e+00

Pos logit contributions
 forgot+0.071
 stayed+0.058
 waited+0.052
 hoped+0.051
 forget+0.048
Neg logit contributions
 This-0.074
 Today-0.071
elly-0.067
ummy-0.067
ore-0.065
Tokenay
Token ID323
Feature activation-1.72e+00

Pos logit contributions
 This+0.050
 Today+0.046
elly+0.038
ummy+0.034
ore+0.033
Neg logit contributions
 forgot-0.242
 stayed-0.220
 waited-0.204
 hoped-0.203
 learned-0.199
Tokenons
Token ID684
Feature activation-2.46e+00

Pos logit contributions
 This+0.031
 Today+0.030
elly+0.028
ummy+0.028
ires+0.027
Neg logit contributions
 forgot-0.039
 stayed-0.033
 waited-0.030
 hoped-0.029
 learned-0.028
Token to
Token ID284
Feature activation+2.54e+00

Pos logit contributions
 This+0.027
 Today+0.025
elly+0.023
ummy+0.023
ore+0.022
Neg logit contributions
 forgot-0.072
 stayed-0.063
 waited-0.059
 hoped-0.058
 forget-0.057
Token scrib
Token ID44661
Feature activation-1.04e+01

Pos logit contributions
 forgot+0.048
 stayed+0.038
 waited+0.033
 hoped+0.033
 regretted+0.032
Neg logit contributions
 This-0.056
 Today-0.051
ummy-0.048
ires-0.048
ore-0.047
Tokenble
Token ID903
Feature activation-5.05e+00

Pos logit contributions
 This+0.233
 Today+0.232
 These+0.204
elly+0.201
ummy+0.201
Neg logit contributions
 forgot-0.176
 stayed-0.156
 waited-0.130
 hoped-0.130
 managed-0.130
Token on
Token ID319
Feature activation-2.03e+00

Pos logit contributions
 Today+0.076
 This+0.075
elly+0.069
uttering+0.069
ummy+0.069
Neg logit contributions
 forgot-0.119
 stayed-0.107
 waited-0.095
 hoped-0.094
 wouldn-0.094
Token the
Token ID262
Feature activation+2.38e+00

Pos logit contributions
 This+0.035
 Today+0.035
elly+0.033
ummy+0.032
uttering+0.032
Neg logit contributions
 forgot-0.046
 stayed-0.039
 waited-0.036
 hoped-0.035
 learned-0.034
Token wall
Token ID3355
Feature activation-5.19e+00

Pos logit contributions
 forgot+0.048
 stayed+0.039
 hoped+0.034
 waited+0.034
 managed+0.034
Neg logit contributions
 This-0.051
 Today-0.047
ummy-0.046
elly-0.044
ires-0.043
Token.
Token ID13
Feature activation-4.43e+00

Pos logit contributions
 This+0.057
 Today+0.054
elly+0.050
ummy+0.049
ires+0.047
Neg logit contributions
 forgot-0.150
 stayed-0.134
 waited-0.124
 hoped-0.123
 forget-0.119
Token,
Token ID11
Feature activation-6.78e-01

Pos logit contributions
 Today+0.026
elly+0.026
 This+0.025
ires+0.025
ummy+0.024
Neg logit contributions
 forgot-0.044
 stayed-0.040
 waited-0.036
 hoped-0.035
 learned-0.034
Token "
Token ID366
Feature activation-4.41e-01

Pos logit contributions
elly+0.010
 This+0.009
ires+0.009
 Today+0.009
ummy+0.009
Neg logit contributions
 forgot-0.017
 stayed-0.016
 waited-0.014
 hoped-0.014
 wouldn-0.014
TokenThat
Token ID2504
Feature activation+3.92e+00

Pos logit contributions
 This+0.007
 Today+0.007
ummy+0.007
elly+0.007
ires+0.007
Neg logit contributions
 forgot-0.010
 stayed-0.009
 waited-0.008
 hoped-0.008
 forget-0.008
Token tower
Token ID10580
Feature activation-1.52e+00

Pos logit contributions
 forgot+0.076
 stayed+0.062
 hoped+0.057
 waited+0.055
 forget+0.052
Neg logit contributions
 This-0.082
 Today-0.080
ummy-0.075
elly-0.073
ore-0.071
Token looks
Token ID3073
Feature activation-9.00e-01

Pos logit contributions
 This+0.025
 Today+0.023
ummy+0.022
elly+0.022
ore+0.021
Neg logit contributions
 forgot-0.035
 stayed-0.030
 hoped-0.028
 waited-0.027
 sighed-0.026
Token sm
Token ID895
Feature activation-1.04e+01

Pos logit contributions
 This+0.017
 Today+0.017
elly+0.016
ummy+0.016
ore+0.015
Neg logit contributions
 forgot-0.019
 stayed-0.016
 waited-0.015
 hoped-0.014
 forget-0.014
Tokenelly
Token ID6148
Feature activation-4.73e+00

Pos logit contributions
 This+0.088
 Today+0.079
uttering+0.057
ires+0.055
 These+0.052
Neg logit contributions
 forgot-0.297
 stayed-0.272
 waited-0.259
 cleaned-0.252
 kept-0.249
Token.
Token ID13
Feature activation-2.95e+00

Pos logit contributions
 This+0.068
 Today+0.065
uttering+0.061
elly+0.060
ires+0.060
Neg logit contributions
 forgot-0.119
 stayed-0.106
 waited-0.097
 hoped-0.094
 wouldn-0.091
Token Let
Token ID3914
Feature activation+3.85e-01

Pos logit contributions
uttering+0.039
elly+0.038
 This+0.038
 Today+0.037
ummy+0.036
Neg logit contributions
 forgot-0.074
 stayed-0.066
 waited-0.061
 hoped-0.060
 forget-0.057
Token's
Token ID338
Feature activation+5.12e+00

Pos logit contributions
 forgot+0.007
 hoped+0.005
 stayed+0.005
 waited+0.005
 forget+0.004
Neg logit contributions
 This-0.009
 Today-0.008
ummy-0.008
-0.007
ore-0.007
Token go
Token ID467
Feature activation-2.15e+00

Pos logit contributions
 forgot+0.102
 stayed+0.081
 sighed+0.076
 hoped+0.076
 regretted+0.070
Neg logit contributions
 This-0.103
 Today-0.100
ummy-0.091
ore-0.086
ires-0.083
Token.
Token ID13
Feature activation-3.14e+00

Pos logit contributions
 This+0.060
 Today+0.058
elly+0.055
ummy+0.055
ore+0.051
Neg logit contributions
 forgot-0.110
 stayed-0.096
 hoped-0.088
 waited-0.087
 forget-0.085
Token It
Token ID632
Feature activation+4.63e+00

Pos logit contributions
uttering+0.041
elly+0.039
ummy+0.037
ore+0.036
ires+0.035
Neg logit contributions
 forgot-0.079
 stayed-0.071
 waited-0.068
 hoped-0.066
 forget-0.064
Token is
Token ID318
Feature activation+2.71e+00

Pos logit contributions
 forgot+0.104
 argued+0.086
 stayed+0.085
 sighed+0.085
 regretted+0.082
Neg logit contributions
 This-0.075
-0.063
 Today-0.062
ummy-0.059
ore-0.057
Token called
Token ID1444
Feature activation-1.45e+00

Pos logit contributions
 forgot+0.058
 stayed+0.050
 waited+0.044
 hoped+0.044
 forget+0.042
Neg logit contributions
 This-0.051
 Today-0.049
elly-0.047
ummy-0.046
ore-0.045
Token g
Token ID308
Feature activation-6.29e+00

Pos logit contributions
 Today+0.025
elly+0.025
uttering+0.024
 This+0.024
ires+0.023
Neg logit contributions
 forgot-0.029
 stayed-0.026
 waited-0.024
 hoped-0.022
 learned-0.022
Tokenaj
Token ID1228
Feature activation-1.03e+01

Pos logit contributions
 This+0.068
+0.058
 Today+0.055
 Where+0.048
 Of+0.045
Neg logit contributions
 forgot-0.163
 stayed-0.143
 waited-0.135
ppy-0.133
 promise-0.133
Tokenar
Token ID283
Feature activation-2.59e+00

Pos logit contributions
 This+0.169
 Today+0.165
elly+0.159
ore+0.155
ires+0.154
Neg logit contributions
 forgot-0.226
 stayed-0.199
 waited-0.183
 hoped-0.167
 forget-0.165
Token ka
Token ID38387
Feature activation-2.55e+00

Pos logit contributions
 This+0.039
 Today+0.038
elly+0.034
ummy+0.033
ires+0.033
Neg logit contributions
 forgot-0.066
 stayed-0.057
 waited-0.053
 hoped-0.051
 learned-0.049
Token hal
Token ID10284
Feature activation-5.25e+00

Pos logit contributions
 This+0.051
 Today+0.051
elly+0.048
ires+0.047
ore+0.047
Neg logit contributions
 forgot-0.049
 stayed-0.042
 waited-0.036
 hoped-0.035
 forget-0.034
Tokenwa
Token ID10247
Feature activation-6.41e-01

Pos logit contributions
 This+0.098
 Today+0.098
elly+0.096
ires+0.094
igsaw+0.089
Neg logit contributions
 forgot-0.095
 stayed-0.090
 waited-0.076
 wouldn-0.076
 never-0.069
Token.
Token ID13
Feature activation-3.55e+00

Pos logit contributions
 This+0.010
 Today+0.009
elly+0.009
uttering+0.008
ires+0.008
Neg logit contributions
 forgot-0.016
 stayed-0.014
 waited-0.013
 hoped-0.012
 learned-0.012
Token so
Token ID523
Feature activation-1.58e+00

Pos logit contributions
 This+0.060
 Today+0.053
ummy+0.052
elly+0.048
ore+0.047
Neg logit contributions
 forgot-0.129
 stayed-0.111
 waited-0.105
 hoped-0.104
 forget-0.101
Token it
Token ID340
Feature activation+3.55e+00

Pos logit contributions
 This+0.025
 Today+0.024
elly+0.023
ummy+0.023
ires+0.022
Neg logit contributions
 forgot-0.039
 stayed-0.033
 waited-0.030
 hoped-0.030
 forget-0.029
Token wouldn
Token ID3636
Feature activation+3.87e-03

Pos logit contributions
 forgot+0.054
 passengers+0.050
 scar+0.048
ode+0.047
ppa+0.045
Neg logit contributions
 This-0.062
time-0.055
ore-0.055
ires-0.053
-0.053
Token't
Token ID470
Feature activation+4.33e+00

Pos logit contributions
 forgot+0.000
 stayed+0.000
 forget+0.000
 waited+0.000
 never+0.000
Neg logit contributions
 Today-0.000
 This-0.000
elly-0.000
ires-0.000
uttering-0.000
Token get
Token ID651
Feature activation-4.63e-01

Pos logit contributions
 forgot+0.074
 hoped+0.063
 stayed+0.061
 sighed+0.061
 waited+0.058
Neg logit contributions
 This-0.085
 Today-0.080
ummy-0.079
 late-0.072
elly-0.071
Token sm
Token ID895
Feature activation-1.03e+01

Pos logit contributions
 This+0.008
 Today+0.008
elly+0.008
ummy+0.008
ore+0.007
Neg logit contributions
 forgot-0.010
 stayed-0.008
 waited-0.008
 hoped-0.008
 forget-0.007
Tokenelly
Token ID6148
Feature activation-3.80e+00

Pos logit contributions
 This+0.091
 Today+0.086
ires+0.053
 These+0.052
+0.049
Neg logit contributions
 forgot-0.305
 stayed-0.275
 waited-0.253
 cleaned-0.253
 managed-0.252
Token again
Token ID757
Feature activation-1.05e+00

Pos logit contributions
 This+0.062
 Today+0.059
elly+0.055
ummy+0.054
ires+0.053
Neg logit contributions
 forgot-0.092
 stayed-0.080
 waited-0.072
 hoped-0.071
 forget-0.069
Token.
Token ID13
Feature activation-3.64e+00

Pos logit contributions
 This+0.014
 Today+0.013
elly+0.012
ires+0.012
ummy+0.012
Neg logit contributions
 forgot-0.029
 stayed-0.026
 waited-0.023
 hoped-0.023
 forget-0.023
Token The
Token ID383
Feature activation+3.11e+00

Pos logit contributions
uttering+0.046
ach+0.044
ires+0.043
elly+0.042
ummy+0.039
Neg logit contributions
 forgot-0.096
 stayed-0.082
 learned-0.080
 hoped-0.079
 promised-0.077
Token end
Token ID886
Feature activation-5.09e+00

Pos logit contributions
 forgot+0.066
 stayed+0.056
 hoped+0.051
 waited+0.051
 managed+0.049
Neg logit contributions
 Today-0.056
ummy-0.054
 This-0.053
elly-0.051
ires-0.049
Token the
Token ID262
Feature activation+1.62e+00

Pos logit contributions
 Today+0.031
 This+0.030
ires+0.030
ummy+0.030
uttering+0.029
Neg logit contributions
 forgot-0.025
 stayed-0.021
 waited-0.020
 learned-0.020
 hoped-0.019
Token room
Token ID2119
Feature activation-4.87e+00

Pos logit contributions
 forgot+0.028
 stayed+0.023
 waited+0.020
 hoped+0.019
 learned+0.019
Neg logit contributions
 This-0.036
 Today-0.036
elly-0.034
ummy-0.034
ires-0.034
Token and
Token ID290
Feature activation+4.57e+00

Pos logit contributions
 This+0.069
 Today+0.065
elly+0.061
ummy+0.060
ore+0.057
Neg logit contributions
 forgot-0.128
 stayed-0.112
 waited-0.102
 hoped-0.101
 forget-0.099
Token started
Token ID2067
Feature activation-1.04e+00

Pos logit contributions
ode+0.068
 forgot+0.064
 promise+0.059
 stayed+0.058
 forget+0.055
Neg logit contributions
 This-0.096
-0.084
 late-0.081
 Today-0.080
 A-0.079
Token to
Token ID284
Feature activation+2.29e+00

Pos logit contributions
 This+0.015
 Today+0.015
elly+0.014
ummy+0.014
ires+0.014
Neg logit contributions
 forgot-0.026
 stayed-0.023
 waited-0.021
 hoped-0.021
 learned-0.020
Token scrib
Token ID44661
Feature activation-1.03e+01

Pos logit contributions
 forgot+0.045
 stayed+0.038
 hoped+0.035
 waited+0.032
 managed+0.032
Neg logit contributions
 This-0.045
 Today-0.042
ore-0.036
ummy-0.036
elly-0.035
Tokenble
Token ID903
Feature activation-4.42e+00

Pos logit contributions
 This+0.208
 Today+0.207
 These+0.185
ore+0.176
elly+0.176
Neg logit contributions
 forgot-0.195
 stayed-0.171
 hoped-0.150
 waited-0.149
 managed-0.146
Token all
Token ID477
Feature activation+9.80e-01

Pos logit contributions
 Today+0.070
 This+0.067
uttering+0.065
elly+0.063
ummy+0.063
Neg logit contributions
 forgot-0.102
 stayed-0.090
 waited-0.081
 wouldn-0.080
 hoped-0.079
Token over
Token ID625
Feature activation-1.98e+00

Pos logit contributions
 forgot+0.020
 stayed+0.018
 waited+0.016
 hoped+0.016
 learned+0.015
Neg logit contributions
 Today-0.018
 This-0.018
uttering-0.017
ummy-0.016
elly-0.016
Token her
Token ID607
Feature activation+1.95e+00

Pos logit contributions
 This+0.035
 Today+0.034
elly+0.032
ummy+0.031
ore+0.031
Neg logit contributions
 forgot-0.045
 stayed-0.038
 waited-0.035
 hoped-0.034
 learned-0.033
Token pictures
Token ID5986
Feature activation-3.81e+00

Pos logit contributions
 forgot+0.039
 stayed+0.032
 waited+0.028
 hoped+0.028
 forget+0.027
Neg logit contributions
 This-0.040
 Today-0.039
elly-0.037
ummy-0.037
ore-0.036
Token and
Token ID290
Feature activation+4.44e+00

Pos logit contributions
 This+0.082
 Today+0.079
elly+0.073
uttering+0.070
ires+0.070
Neg logit contributions
 forgot-0.123
 stayed-0.109
 waited-0.100
 hoped-0.097
 wouldn-0.092
Token put
Token ID1234
Feature activation-2.53e+00

Pos logit contributions
 forgot+0.080
 stayed+0.066
 hoped+0.061
 learned+0.059
ode+0.057
Neg logit contributions
 This-0.088
 Today-0.082
ummy-0.078
ore-0.078
 late-0.076
Token on
Token ID319
Feature activation-2.61e+00

Pos logit contributions
 This+0.041
 Today+0.039
ummy+0.036
elly+0.036
ore+0.036
Neg logit contributions
 forgot-0.062
 stayed-0.052
 waited-0.047
 hoped-0.047
 forget-0.047
Token your
Token ID534
Feature activation+4.56e+00

Pos logit contributions
 This+0.042
 Today+0.041
elly+0.038
ummy+0.038
ires+0.036
Neg logit contributions
 forgot-0.063
 stayed-0.054
 waited-0.049
 hoped-0.049
 forget-0.047
Token p
Token ID279
Feature activation-4.90e-01

Pos logit contributions
 forgot+0.090
 stayed+0.067
 managed+0.062
 waited+0.062
 hoped+0.061
Neg logit contributions
 This-0.096
 Today-0.094
ummy-0.087
ore-0.084
elly-0.082
Tokenaj
Token ID1228
Feature activation-1.03e+01

Pos logit contributions
 This+0.007
 Today+0.007
elly+0.007
ummy+0.007
ore+0.006
Neg logit contributions
 forgot-0.012
 stayed-0.011
 waited-0.010
 hoped-0.010
 forget-0.009
Tokenamas
Token ID17485
Feature activation-7.09e+00

Pos logit contributions
 This+0.167
 Today+0.162
elly+0.156
ore+0.149
ires+0.147
Neg logit contributions
 forgot-0.241
 stayed-0.210
 waited-0.190
 hoped-0.182
 forget-0.177
Token.
Token ID13
Feature activation-3.38e+00

Pos logit contributions
 This+0.100
 Today+0.096
elly+0.091
ires+0.091
ummy+0.089
Neg logit contributions
 forgot-0.183
 stayed-0.162
 waited-0.149
 hoped-0.146
 never-0.141
Token Then
Token ID3244
Feature activation+6.11e-02

Pos logit contributions
uttering+0.041
elly+0.040
 This+0.039
ummy+0.039
ires+0.038
Neg logit contributions
 forgot-0.089
 stayed-0.079
 waited-0.073
 hoped-0.073
 forget-0.070
Token we
Token ID356
Feature activation+6.17e+00

Pos logit contributions
 forgot+0.002
 stayed+0.001
 hoped+0.001
 sighed+0.001
 waited+0.001
Neg logit contributions
 This-0.001
 Today-0.001
ummy-0.001
-0.001
ore-0.001
Token can
Token ID460
Feature activation-5.66e-01

Pos logit contributions
 forgot+0.123
 stayed+0.100
 hoped+0.095
 sighed+0.090
 argued+0.086
Neg logit contributions
 Today-0.115
 This-0.104
ore-0.104
-0.098
 On-0.089
TokenNo
Token ID2949
Feature activation+2.02e+00

Pos logit contributions
 This+0.001
 Today+0.001
elly+0.001
ummy+0.001
ore+0.001
Neg logit contributions
 forgot-0.002
 stayed-0.002
 waited-0.002
 hoped-0.002
 forget-0.001
Token,
Token ID11
Feature activation+7.29e-01

Pos logit contributions
 forgot+0.061
 stayed+0.054
 hoped+0.051
 waited+0.050
 learned+0.048
Neg logit contributions
 This-0.023
 Today-0.022
ummy-0.019
elly-0.018
ore-0.016
Token it
Token ID340
Feature activation+4.09e+00

Pos logit contributions
 forgot+0.020
 stayed+0.016
 hoped+0.016
 waited+0.016
 learned+0.016
Neg logit contributions
 This-0.010
ummy-0.009
 Today-0.008
elly-0.007
 These-0.007
Token smells
Token ID25760
Feature activation-1.48e+00

Pos logit contributions
 forgot+0.074
 stayed+0.060
 hoped+0.055
 waited+0.053
 sighed+0.052
Neg logit contributions
 This-0.090
 Today-0.082
elly-0.079
ummy-0.078
ore-0.077
Token too
Token ID1165
Feature activation+6.73e-01

Pos logit contributions
 This+0.029
 Today+0.029
elly+0.027
ummy+0.027
uttering+0.027
Neg logit contributions
 forgot-0.030
 stayed-0.025
 waited-0.022
 hoped-0.022
 forget-0.022
Token sm
Token ID895
Feature activation-1.03e+01

Pos logit contributions
 forgot+0.014
 stayed+0.011
 waited+0.011
 bit+0.010
 never+0.010
Neg logit contributions
 This-0.013
 Today-0.013
uttering-0.012
ires-0.012
ore-0.011
Tokenelly
Token ID6148
Feature activation-3.87e+00

Pos logit contributions
 This+0.084
 Today+0.074
ires+0.058
 These+0.057
 outer+0.055
Neg logit contributions
 forgot-0.282
 stayed-0.260
 waited-0.243
 cleaned-0.240
 promised-0.237
Token.
Token ID13
Feature activation-2.63e+00

Pos logit contributions
 This+0.056
 Today+0.056
uttering+0.055
elly+0.052
ires+0.052
Neg logit contributions
 forgot-0.093
 stayed-0.084
 waited-0.077
 hoped-0.073
 wouldn-0.073
Token I
Token ID314
Feature activation+5.41e+00

Pos logit contributions
 Today+0.030
 This+0.030
uttering+0.029
elly+0.029
ummy+0.029
Neg logit contributions
 forgot-0.070
 stayed-0.063
 waited-0.058
 hoped-0.057
 forget-0.056
Token don
Token ID836
Feature activation-2.66e+00

Pos logit contributions
 forgot+0.111
 stayed+0.095
 waited+0.084
 hoped+0.083
 sighed+0.080
Neg logit contributions
 This-0.104
 Today-0.101
elly-0.095
ore-0.093
ummy-0.090
Token't
Token ID470
Feature activation+4.69e+00

Pos logit contributions
elly+0.047
uttering+0.046
 Today+0.046
ires+0.043
 This+0.043
Neg logit contributions
 forgot-0.052
 stayed-0.046
 never-0.043
 waited-0.041
 forget-0.040
Token time
Token ID640
Feature activation-4.18e+00

Pos logit contributions
 This+0.038
 Today+0.038
elly+0.035
ummy+0.034
ore+0.032
Neg logit contributions
 forgot-0.072
 stayed-0.063
 hoped-0.057
 waited-0.057
 forget-0.055
Token.
Token ID13
Feature activation-3.60e+00

Pos logit contributions
 This+0.053
 Today+0.051
elly+0.047
ummy+0.045
ires+0.044
Neg logit contributions
 forgot-0.116
 stayed-0.103
 waited-0.094
 hoped-0.093
 forget-0.091
Token
Token ID220
Feature activation-4.84e+00

Pos logit contributions
 This+0.054
elly+0.052
 Today+0.051
ummy+0.050
uttering+0.050
Neg logit contributions
 forgot-0.088
 stayed-0.077
 waited-0.071
 hoped-0.070
 learned-0.067
Token
Token ID198
Feature activation-4.99e+00

Pos logit contributions
elly+0.072
uttering+0.067
ummy+0.064
 Today+0.063
igsaw+0.061
Neg logit contributions
 forgot-0.113
 stayed-0.099
 hoped-0.092
 waited-0.091
 never-0.090
Token
Token ID198
Feature activation-4.38e+00

Pos logit contributions
 This+0.055
elly+0.055
 Today+0.052
ummy+0.051
uttering+0.049
Neg logit contributions
 forgot-0.140
 stayed-0.125
 waited-0.118
 hoped-0.117
 learned-0.115
TokenNick
Token ID23609
Feature activation+7.19e+00

Pos logit contributions
 This+0.072
 Today+0.070
elly+0.065
ummy+0.064
ore+0.063
Neg logit contributions
 forgot-0.105
 stayed-0.089
 hoped-0.080
 waited-0.080
 forget-0.079
Token carefully
Token ID7773
Feature activation+5.10e+00

Pos logit contributions
 forgot+0.115
ode+0.103
 forget+0.097
 scar+0.083
 promise+0.082
Neg logit contributions
 This-0.121
ore-0.117
-0.113
time-0.107
 Today-0.106
Token hopped
Token ID45230
Feature activation-3.00e+00

Pos logit contributions
 forgot+0.074
 forget+0.054
 promise+0.050
ode+0.050
 stayed+0.049
Neg logit contributions
 This-0.110
ore-0.102
-0.097
elly-0.097
 Today-0.096
Token off
Token ID572
Feature activation-3.61e+00

Pos logit contributions
 This+0.061
 Today+0.059
elly+0.059
ummy+0.058
ires+0.057
Neg logit contributions
 forgot-0.058
 stayed-0.050
 waited-0.045
 hoped-0.043
 learned-0.042
Token his
Token ID465
Feature activation+4.77e+00

Pos logit contributions
 This+0.060
 Today+0.058
elly+0.057
ummy+0.055
ires+0.054
Neg logit contributions
 forgot-0.084
 stayed-0.073
 waited-0.067
 hoped-0.066
 learned-0.064
Token bike
Token ID7161
Feature activation-3.34e+00

Pos logit contributions
 forgot+0.105
 stayed+0.087
 waited+0.081
 hoped+0.080
 managed+0.078
Neg logit contributions
 This-0.087
 Today-0.085
ummy-0.076
elly-0.072
ires-0.071
Token.
Token ID13
Feature activation-3.48e+00

Pos logit contributions
 This+0.058
 Today+0.056
elly+0.053
ummy+0.052
ires+0.050
Neg logit contributions
 forgot-0.090
 stayed-0.079
 waited-0.072
 hoped-0.071
 forget-0.069
Token She
Token ID1375
Feature activation+7.95e+00

Pos logit contributions
uttering+0.043
ummy+0.040
ore+0.039
elly+0.039
 This+0.037
Neg logit contributions
 forgot-0.088
 stayed-0.080
 hoped-0.073
 waited-0.073
 forget-0.071
Token is
Token ID318
Feature activation+3.49e+00

Pos logit contributions
 forgot+0.183
 stayed+0.151
 sighed+0.142
 managed+0.140
 argued+0.140
Neg logit contributions
 This-0.130
 Today-0.111
elly-0.107
-0.104
ires-0.103
Token flexible
Token ID12846
Feature activation-5.06e+00

Pos logit contributions
 forgot+0.082
 stayed+0.070
 waited+0.064
 hoped+0.063
 sighed+0.062
Neg logit contributions
 This-0.056
 Today-0.052
ires-0.049
elly-0.049
ummy-0.049
Token.
Token ID13
Feature activation-3.91e+00

Pos logit contributions
 This+0.087
 Today+0.083
elly+0.078
ummy+0.077
uttering+0.076
Neg logit contributions
 forgot-0.117
 stayed-0.101
 waited-0.091
 hoped-0.091
 learned-0.088
Token She
Token ID1375
Feature activation+8.10e+00

Pos logit contributions
uttering+0.050
ummy+0.045
ore+0.044
elly+0.042
 This+0.042
Neg logit contributions
 forgot-0.099
 stayed-0.089
 hoped-0.083
 waited-0.081
 forget-0.080
Token likes
Token ID7832
Feature activation-2.93e+00

Pos logit contributions
 forgot+0.179
 stayed+0.148
 sighed+0.139
 argued+0.139
 managed+0.135
Neg logit contributions
 This-0.137
 Today-0.116
elly-0.114
ires-0.112
-0.109
Token to
Token ID284
Feature activation+2.27e+00

Pos logit contributions
 This+0.049
 Today+0.047
elly+0.045
ummy+0.044
ires+0.042
Neg logit contributions
 forgot-0.069
 stayed-0.059
 waited-0.054
 hoped-0.053
 forget-0.051
Token play
Token ID711
Feature activation-5.25e+00

Pos logit contributions
 forgot+0.039
 stayed+0.031
 hoped+0.028
 waited+0.027
 managed+0.026
Neg logit contributions
 This-0.052
 Today-0.050
ummy-0.046
elly-0.046
ore-0.045
Token with
Token ID351
Feature activation-1.97e+00

Pos logit contributions
 Today+0.075
 This+0.073
uttering+0.072
elly+0.072
ummy+0.071
Neg logit contributions
 forgot-0.127
 stayed-0.117
 waited-0.105
 learned-0.104
 hoped-0.103
Token you
Token ID345
Feature activation+1.38e+00

Pos logit contributions
 This+0.037
 Today+0.035
elly+0.034
ummy+0.033
ore+0.032
Neg logit contributions
 forgot-0.043
 stayed-0.036
 waited-0.033
 hoped-0.032
 forget-0.031
Token boy
Token ID2933
Feature activation+6.57e+00

Pos logit contributions
 forgot+0.085
 stayed+0.072
 waited+0.065
 hoped+0.065
 managed+0.064
Neg logit contributions
 This-0.058
 Today-0.056
ummy-0.055
elly-0.053
ore-0.051
Token was
Token ID373
Feature activation+3.82e+00

Pos logit contributions
 forgot+0.109
ode+0.093
 scar+0.087
 forget+0.086
 promise+0.082
Neg logit contributions
 This-0.123
ore-0.109
 Today-0.102
-0.100
elly-0.100
Token so
Token ID523
Feature activation+2.75e+00

Pos logit contributions
 forgot+0.081
 stayed+0.066
 waited+0.061
 forget+0.059
 hoped+0.059
Neg logit contributions
 This-0.070
 Today-0.065
uttering-0.061
elly-0.061
ummy-0.061
Token scared
Token ID12008
Feature activation-5.00e+00

Pos logit contributions
 forgot+0.055
 stayed+0.046
 hoped+0.040
 waited+0.040
 learned+0.038
Neg logit contributions
 This-0.057
 Today-0.057
elly-0.054
ummy-0.053
ires-0.051
Token.
Token ID13
Feature activation-3.53e+00

Pos logit contributions
 This+0.076
 Today+0.075
ires+0.069
elly+0.068
uttering+0.068
Neg logit contributions
 forgot-0.123
 stayed-0.109
 waited-0.097
 hoped-0.096
 never-0.094
Token He
Token ID679
Feature activation+8.05e+00

Pos logit contributions
elly+0.037
 Today+0.037
 This+0.037
uttering+0.035
ummy+0.035
Neg logit contributions
 forgot-0.100
 stayed-0.088
 waited-0.083
 hoped-0.082
 learned-0.080
Token quickly
Token ID2952
Feature activation+4.96e+00

Pos logit contributions
ode+0.116
 forgot+0.110
 forget+0.101
 promise+0.095
 least+0.095
Neg logit contributions
 This-0.132
 A-0.123
-0.122
 On-0.121
 Today-0.116
Token stood
Token ID6204
Feature activation-3.35e+00

Pos logit contributions
 forgot+0.065
 least+0.063
ode+0.062
 forget+0.056
 promise+0.056
Neg logit contributions
 This-0.090
looking-0.083
ore-0.079
elly-0.077
.-0.076
Token up
Token ID510
Feature activation-2.69e+00

Pos logit contributions
 This+0.059
 Today+0.055
elly+0.055
ummy+0.052
 These+0.050
Neg logit contributions
 forgot-0.077
 stayed-0.069
 hoped-0.062
 waited-0.062
 learned-0.059
Token and
Token ID290
Feature activation+4.75e+00

Pos logit contributions
 This+0.055
 Today+0.054
elly+0.053
ires+0.051
ummy+0.051
Neg logit contributions
 forgot-0.050
 stayed-0.045
 waited-0.040
 hoped-0.039
 never-0.037
Token ran
Token ID4966
Feature activation-1.89e+00

Pos logit contributions
 forgot+0.072
ode+0.058
 stayed+0.054
 promise+0.053
 forget+0.052
Neg logit contributions
 This-0.102
ore-0.092
-0.091
 Today-0.085
 late-0.085
Token
Token ID198
Feature activation-4.42e+00

Pos logit contributions
 Today+0.062
elly+0.060
 This+0.060
ires+0.056
uttering+0.055
Neg logit contributions
 forgot-0.142
 stayed-0.126
 learned-0.118
 hoped-0.115
 hugged-0.115
TokenB
Token ID33
Feature activation+5.89e-01

Pos logit contributions
 This+0.069
 Today+0.064
elly+0.061
ummy+0.060
ore+0.057
Neg logit contributions
 forgot-0.110
 stayed-0.094
 waited-0.087
 hoped-0.087
 forget-0.084
Tokenenny
Token ID11870
Feature activation+6.96e+00

Pos logit contributions
 forgot+0.012
 stayed+0.010
 waited+0.009
 hoped+0.009
 forget+0.009
Neg logit contributions
 This-0.011
 Today-0.011
ires-0.010
elly-0.010
ummy-0.010
Token's
Token ID338
Feature activation+3.46e+00

Pos logit contributions
 forgot+0.126
ode+0.110
 forget+0.109
 scar+0.098
 nurses+0.097
Neg logit contributions
 This-0.118
 Today-0.098
ore-0.095
 The-0.095
-0.094
Token mom
Token ID1995
Feature activation+5.52e+00

Pos logit contributions
 forgot+0.078
 stayed+0.060
 managed+0.058
 waited+0.058
 forget+0.054
Neg logit contributions
ummy-0.061
 This-0.058
 Today-0.056
ires-0.051
ay-0.048
Tokenmy
Token ID1820
Feature activation+6.39e+00

Pos logit contributions
 forgot+0.098
 forget+0.077
 drowned+0.069
ode+0.068
 wounds+0.064
Neg logit contributions
ummy-0.095
 This-0.094
-0.092
ing-0.087
ore-0.086
Token was
Token ID373
Feature activation+4.32e+00

Pos logit contributions
 forgot+0.111
 forget+0.085
ode+0.078
 stayed+0.073
 drowned+0.072
Neg logit contributions
 This-0.118
-0.116
ummy-0.110
ore-0.109
 Today-0.106
Token very
Token ID845
Feature activation+3.55e+00

Pos logit contributions
 forgot+0.091
 stayed+0.075
 waited+0.067
 hoped+0.066
 forget+0.065
Neg logit contributions
 This-0.083
 Today-0.079
ummy-0.074
elly-0.074
ore-0.072
Token proud
Token ID6613
Feature activation-3.17e+00

Pos logit contributions
 forgot+0.076
 stayed+0.064
 waited+0.057
 hoped+0.056
 forget+0.054
Neg logit contributions
 This-0.068
 Today-0.065
elly-0.062
ummy-0.062
ore-0.060
Token of
Token ID286
Feature activation-1.12e+00

Pos logit contributions
 This+0.036
 Today+0.035
ummy+0.033
elly+0.033
ore+0.030
Neg logit contributions
 forgot-0.092
 stayed-0.081
 waited-0.075
 hoped-0.074
 forget-0.072
Token him
Token ID683
Feature activation+1.30e+00

Pos logit contributions
elly+0.021
 Today+0.020
 This+0.020
uttering+0.020
ore+0.019
Neg logit contributions
 forgot-0.023
 stayed-0.021
 learned-0.018
 never-0.018
 hoped-0.017
Token says
Token ID1139
Feature activation-2.55e+00

Pos logit contributions
 forgot+0.074
 stayed+0.060
 forget+0.051
 hoped+0.050
 managed+0.048
Neg logit contributions
 This-0.091
 Today-0.088
elly-0.084
ore-0.083
ummy-0.081
Token.
Token ID13
Feature activation-3.78e+00

Pos logit contributions
 Today+0.041
elly+0.039
ires+0.038
 This+0.037
ummy+0.036
Neg logit contributions
 forgot-0.061
 stayed-0.054
 waited-0.050
 sighed-0.049
 hugged-0.049
Token
Token ID198
Feature activation-5.53e+00

Pos logit contributions
uttering+0.054
ummy+0.052
ires+0.050
elly+0.048
 This+0.048
Neg logit contributions
 forgot-0.092
 hoped-0.079
 stayed-0.078
 waited-0.077
 learned-0.075
Token
Token ID198
Feature activation-4.48e+00

Pos logit contributions
uttering+0.084
 This+0.080
elly+0.078
ummy+0.076
owers+0.075
Neg logit contributions
 forgot-0.128
 learned-0.107
 hoped-0.106
 never-0.105
 stayed-0.104
Token"
Token ID1
Feature activation-4.46e-01

Pos logit contributions
 This+0.079
 Today+0.075
ummy+0.071
elly+0.071
ires+0.069
Neg logit contributions
 forgot-0.103
 stayed-0.087
 waited-0.080
 hoped-0.079
 learned-0.076
TokenHe
Token ID1544
Feature activation+7.15e+00

Pos logit contributions
 This+0.007
 Today+0.006
elly+0.006
ummy+0.006
ires+0.006
Neg logit contributions
 forgot-0.011
 stayed-0.010
 waited-0.009
 hoped-0.009
 forget-0.009
Token is
Token ID318
Feature activation+3.38e+00

Pos logit contributions
 forgot+0.171
 stayed+0.146
 hoped+0.135
 forget+0.134
 waited+0.132
Neg logit contributions
 This-0.112
 Today-0.098
elly-0.097
ore-0.094
ummy-0.090
Token a
Token ID257
Feature activation+1.79e+00

Pos logit contributions
 forgot+0.068
 stayed+0.057
 waited+0.051
 hoped+0.050
 learned+0.049
Neg logit contributions
 This-0.068
 Today-0.068
elly-0.064
ummy-0.064
ore-0.062
Token lawyer
Token ID6853
Feature activation-1.32e+00

Pos logit contributions
 forgot+0.039
 stayed+0.033
 waited+0.030
 hoped+0.029
 forget+0.028
Neg logit contributions
 This-0.033
 Today-0.032
elly-0.031
ummy-0.030
ore-0.029
Token too
Token ID1165
Feature activation+7.95e-01

Pos logit contributions
 This+0.014
 Today+0.014
elly+0.012
ummy+0.012
ires+0.011
Neg logit contributions
 forgot-0.039
 stayed-0.034
 waited-0.032
 hoped-0.032
 forget-0.031
Token.
Token ID13
Feature activation-2.95e+00

Pos logit contributions
 forgot+0.018
 waited+0.014
 stayed+0.014
 knew+0.014
 hoped+0.013
Neg logit contributions
 This-0.013
uttering-0.013
 Today-0.012
ires-0.012
igsaw-0.012
Token was
Token ID373
Feature activation+3.11e+00

Pos logit contributions
 forgot+0.085
 stayed+0.067
 scar+0.067
 waited+0.066
 hoped+0.065
Neg logit contributions
 This-0.096
 Today-0.083
ore-0.083
-0.082
ummy-0.081
Token important
Token ID1593
Feature activation-1.56e+00

Pos logit contributions
 forgot+0.069
 stayed+0.057
 waited+0.052
 hoped+0.052
 forget+0.051
Neg logit contributions
 This-0.056
 Today-0.053
ummy-0.049
elly-0.049
ires-0.048
Token to
Token ID284
Feature activation+2.11e+00

Pos logit contributions
 This+0.020
 Today+0.019
elly+0.017
ummy+0.017
ore+0.016
Neg logit contributions
 forgot-0.043
 stayed-0.038
 waited-0.035
 hoped-0.034
 forget-0.034
Token stay
Token ID2652
Feature activation-1.14e+00

Pos logit contributions
 forgot+0.036
 stayed+0.025
 hoped+0.025
 sighed+0.024
 waited+0.023
Neg logit contributions
 This-0.049
 Today-0.045
ires-0.042
ummy-0.042
ore-0.040
Token away
Token ID1497
Feature activation-2.99e+00

Pos logit contributions
 This+0.022
 Today+0.021
elly+0.020
ummy+0.019
ore+0.019
Neg logit contributions
 forgot-0.024
 stayed-0.020
 waited-0.018
 hoped-0.018
 forget-0.017
Token from
Token ID422
Feature activation+3.24e-02

Pos logit contributions
 This+0.044
 Today+0.042
elly+0.039
ummy+0.038
ires+0.037
Neg logit contributions
 forgot-0.077
 stayed-0.067
 waited-0.061
 hoped-0.061
 forget-0.059
Token danger
Token ID3514
Feature activation-4.63e+00

Pos logit contributions
 forgot+0.001
 stayed+0.001
 waited+0.001
 hoped+0.001
 forget+0.001
Neg logit contributions
 This-0.001
 Today-0.000
ummy-0.000
ires-0.000
ore-0.000
Token.
Token ID13
Feature activation-3.30e+00

Pos logit contributions
 This+0.062
 Today+0.059
elly+0.055
ummy+0.054
ore+0.052
Neg logit contributions
 forgot-0.124
 stayed-0.109
 waited-0.100
 hoped-0.099
 forget-0.096
Token He
Token ID679
Feature activation+8.45e+00

Pos logit contributions
 This+0.034
 Today+0.034
elly+0.033
uttering+0.032
ummy+0.032
Neg logit contributions
 forgot-0.094
 stayed-0.083
 hoped-0.078
 waited-0.077
 learned-0.077
Token stayed
Token ID9658
Feature activation-2.85e-01

Pos logit contributions
 forgot+0.109
ode+0.107
nes+0.095
 sleeves+0.094
 argued+0.094
Neg logit contributions
-0.149
 This-0.146
-0.145
:-0.139
 late-0.136
Token away
Token ID1497
Feature activation-1.82e+00

Pos logit contributions
 This+0.004
 late+0.004
uttering+0.004
 Today+0.004
ore+0.003
Neg logit contributions
 forgot-0.007
 stayed-0.006
 waited-0.006
 argued-0.005
 forget-0.005
Token,
Token ID11
Feature activation-2.07e+00

Pos logit contributions
 This+0.031
 Today+0.029
ummy+0.026
elly+0.026
ore+0.024
Neg logit contributions
 forgot-0.076
 stayed-0.068
 hoped-0.063
 waited-0.063
 forget-0.061
Token Lily
Token ID20037
Feature activation+5.85e+00

Pos logit contributions
 This+0.034
 Today+0.032
ummy+0.029
elly+0.029
ires+0.028
Neg logit contributions
 forgot-0.050
 stayed-0.043
 hoped-0.039
 waited-0.039
 forget-0.038
Token's
Token ID338
Feature activation+2.91e+00

Pos logit contributions
 forgot+0.078
 stayed+0.072
 promise+0.072
 passengers+0.072
ode+0.071
Neg logit contributions
 This-0.104
-0.099
elly-0.097
 Today-0.093
 late-0.092
Token brother
Token ID3956
Feature activation+3.13e+00

Pos logit contributions
 forgot+0.055
 stayed+0.046
 waited+0.042
 hoped+0.040
 managed+0.038
Neg logit contributions
 This-0.059
 Today-0.059
ummy-0.058
elly-0.055
ires-0.054
Token tried
Token ID3088
Feature activation-2.95e+00

Pos logit contributions
 forgot+0.044
ode+0.041
 stayed+0.039
 promise+0.038
 scar+0.037
Neg logit contributions
 This-0.066
-0.057
 Today-0.057
elly-0.055
ummy-0.055
Token to
Token ID284
Feature activation+3.19e+00

Pos logit contributions
 This+0.034
 Today+0.030
ummy+0.027
elly+0.027
ore+0.025
Neg logit contributions
 forgot-0.086
 stayed-0.075
 waited-0.070
 hoped-0.070
 forget-0.068
Token say
Token ID910
Feature activation-1.84e+00

Pos logit contributions
 forgot+0.067
 hoped+0.054
 regretted+0.054
 stayed+0.053
 wouldn+0.051
Neg logit contributions
 This-0.048
 Today-0.045
ach-0.044
 outdoors-0.043
ummy-0.040
Token sorry
Token ID7926
Feature activation-4.54e+00

Pos logit contributions
 This+0.033
 Today+0.032
elly+0.031
ummy+0.031
ires+0.030
Neg logit contributions
 forgot-0.041
 stayed-0.035
 waited-0.031
 hoped-0.031
 learned-0.030
Token and
Token ID290
Feature activation+4.07e+00

Pos logit contributions
 This+0.070
 Today+0.067
elly+0.063
ummy+0.062
ires+0.060
Neg logit contributions
 forgot-0.113
 stayed-0.099
 waited-0.090
 hoped-0.089
 forget-0.086
Token fix
Token ID4259
Feature activation-3.03e+00

Pos logit contributions
ode+0.068
 forgot+0.057
hew+0.053
 necks+0.052
ppy+0.052
Neg logit contributions
 This-0.074
 late-0.067
 with-0.064
time-0.063
 Of-0.062
Token the
Token ID262
Feature activation+3.62e+00

Pos logit contributions
 This+0.049
 Today+0.047
elly+0.044
ummy+0.044
ires+0.042
Neg logit contributions
 forgot-0.074
 stayed-0.063
 waited-0.058
 hoped-0.057
 forget-0.055
Token hear
Token ID3285
Feature activation-3.87e+00

Pos logit contributions
 forgot+0.051
 stayed+0.042
 waited+0.037
 hoped+0.036
 learned+0.034
Neg logit contributions
 This-0.060
 Today-0.058
elly-0.054
ore-0.053
ummy-0.053
Token anything
Token ID1997
Feature activation-9.08e-01

Pos logit contributions
 This+0.064
 Today+0.060
elly+0.057
ummy+0.056
ore+0.054
Neg logit contributions
 forgot-0.093
 stayed-0.080
 waited-0.073
 hoped-0.071
 forget-0.070
Token.
Token ID13
Feature activation-3.68e+00

Pos logit contributions
 This+0.012
 Today+0.012
ummy+0.012
elly+0.011
uttering+0.011
Neg logit contributions
 forgot-0.024
 stayed-0.022
 hoped-0.020
 waited-0.019
 forget-0.019
Token
Token ID198
Feature activation-5.44e+00

Pos logit contributions
uttering+0.052
ummy+0.048
elly+0.046
ires+0.045
 This+0.044
Neg logit contributions
 forgot-0.094
 stayed-0.081
 hoped-0.079
 waited-0.078
 learned-0.075
Token
Token ID198
Feature activation-4.76e+00

Pos logit contributions
uttering+0.080
ummy+0.078
elly+0.077
ires+0.075
 This+0.074
Neg logit contributions
 forgot-0.126
 never-0.108
 hoped-0.107
 stayed-0.107
 learned-0.104
Token"
Token ID1
Feature activation+1.37e-01

Pos logit contributions
 This+0.075
 Today+0.071
ummy+0.071
uttering+0.070
ore+0.069
Neg logit contributions
 forgot-0.116
 stayed-0.100
 waited-0.095
 hoped-0.091
 learned-0.088
TokenCan
Token ID6090
Feature activation-1.54e+00

Pos logit contributions
 forgot+0.003
 stayed+0.003
 waited+0.003
 hoped+0.003
 learned+0.003
Neg logit contributions
 This-0.002
 Today-0.002
ummy-0.002
elly-0.002
ires-0.002
Token we
Token ID356
Feature activation+5.09e+00

Pos logit contributions
 This+0.026
 Today+0.023
ummy+0.022
ore+0.021
elly+0.021
Neg logit contributions
 forgot-0.037
 stayed-0.031
 hoped-0.029
 waited-0.029
 managed-0.028
Token borrow
Token ID8804
Feature activation-4.27e+00

Pos logit contributions
 forgot+0.102
 stayed+0.082
 hoped+0.076
 waited+0.074
 sighed+0.073
Neg logit contributions
 This-0.105
 Today-0.099
ummy-0.090
ore-0.090
elly-0.087
Token the
Token ID262
Feature activation+2.72e+00

Pos logit contributions
 This+0.071
 Today+0.071
elly+0.069
ummy+0.067
uttering+0.065
Neg logit contributions
 forgot-0.097
 stayed-0.085
 waited-0.077
 hoped-0.076
 learned-0.073
Token dog
Token ID3290
Feature activation-1.16e+00

Pos logit contributions
 forgot+0.055
 stayed+0.046
 waited+0.041
 hoped+0.040
 forget+0.039
Neg logit contributions
 This-0.055
 Today-0.053
elly-0.051
ummy-0.050
ires-0.049
Token.
Token ID13
Feature activation-3.61e+00

Pos logit contributions
 This+0.004
 Today+0.004
elly+0.003
ummy+0.003
ore+0.003
Neg logit contributions
 forgot-0.007
 stayed-0.006
 waited-0.006
 hoped-0.006
 forget-0.006
Token Tim
Token ID5045
Feature activation+5.99e+00

Pos logit contributions
uttering+0.047
elly+0.045
ires+0.044
ore+0.042
ummy+0.041
Neg logit contributions
 forgot-0.091
 stayed-0.079
 hoped-0.074
 waited-0.074
 learned-0.072
Tokenmy
Token ID1820
Feature activation+6.68e+00

Pos logit contributions
 forgot+0.104
 stayed+0.087
 forget+0.086
 hoped+0.084
ode+0.084
Neg logit contributions
 This-0.096
 Today-0.095
elly-0.093
-0.088
ummy-0.088
Token was
Token ID373
Feature activation+3.12e+00

Pos logit contributions
ode+0.121
 forget+0.109
 passengers+0.107
 scar+0.107
 forgot+0.105
Neg logit contributions
 This-0.089
 with-0.080
,-0.077
 at-0.077
-0.076
Token sad
Token ID6507
Feature activation-3.29e+00

Pos logit contributions
 forgot+0.071
 stayed+0.059
 forget+0.055
 waited+0.054
 hoped+0.054
Neg logit contributions
 This-0.052
 Today-0.048
elly-0.045
 late-0.044
uttering-0.044
Token,
Token ID11
Feature activation+8.36e-01

Pos logit contributions
 This+0.050
 Today+0.048
elly+0.045
ummy+0.044
ore+0.042
Neg logit contributions
 forgot-0.084
 stayed-0.073
 waited-0.067
 hoped-0.066
 forget-0.064
Token but
Token ID475
Feature activation+4.29e+00

Pos logit contributions
 forgot+0.020
 stayed+0.017
 waited+0.016
 promise+0.016
 hoped+0.016
Neg logit contributions
 This-0.013
 Today-0.012
ummy-0.011
 late-0.010
elly-0.010
Token his
Token ID465
Feature activation+4.52e+00

Pos logit contributions
 forgot+0.105
 stayed+0.090
 hoped+0.083
 waited+0.083
ode+0.082
Neg logit contributions
 This-0.060
 Today-0.058
ummy-0.052
 late-0.048
elly-0.048
Token mom
Token ID1995
Feature activation+5.06e+00

Pos logit contributions
 forgot+0.088
 stayed+0.072
 waited+0.064
 hoped+0.062
 managed+0.061
Neg logit contributions
 This-0.089
 Today-0.089
ummy-0.087
elly-0.082
ires-0.080
Token promised
Token ID8072
Feature activation-5.25e-01

Pos logit contributions
 forgot+0.077
ode+0.071
 plank+0.071
 passengers+0.067
 forget+0.067
Neg logit contributions
 This-0.076
ummy-0.074
.-0.074
 Today-0.072
-0.071
Token they
Token ID484
Feature activation+7.33e+00

Pos logit contributions
 This+0.007
 Today+0.006
ummy+0.006
elly+0.005
ore+0.005
Neg logit contributions
 forgot-0.015
 stayed-0.013
 hoped-0.012
 waited-0.012
 forget-0.012
Token Mom
Token ID11254
Feature activation+4.09e+00

Pos logit contributions
 This+0.015
 Today+0.013
ummy+0.012
+0.012
ore+0.011
Neg logit contributions
 forgot-0.021
 stayed-0.018
ode-0.016
 forget-0.016
 hoped-0.016
Token said
Token ID531
Feature activation-2.30e+00

Pos logit contributions
 forgot+0.063
 stayed+0.049
 hoped+0.042
 forget+0.042
 waited+0.038
Neg logit contributions
 This-0.098
 Today-0.097
ummy-0.093
elly-0.091
ore-0.089
Token.
Token ID13
Feature activation-4.08e+00

Pos logit contributions
 Today+0.032
 This+0.030
elly+0.030
ires+0.029
ummy+0.027
Neg logit contributions
 forgot-0.061
 stayed-0.055
 waited-0.050
 hoped-0.049
 hugged-0.048
Token "
Token ID366
Feature activation-1.50e+00

Pos logit contributions
elly+0.050
ires+0.050
 This+0.049
ummy+0.048
uttering+0.048
Neg logit contributions
 forgot-0.106
 stayed-0.094
 waited-0.089
 hoped-0.089
 learned-0.084
TokenWe
Token ID1135
Feature activation+6.81e+00

Pos logit contributions
 This+0.023
 Today+0.022
elly+0.021
ummy+0.020
ires+0.019
Neg logit contributions
 forgot-0.038
 stayed-0.033
 waited-0.030
 hoped-0.029
 forget-0.029
Token have
Token ID423
Feature activation+2.33e+00

Pos logit contributions
 forgot+0.131
 stayed+0.113
 scar+0.108
 sighed+0.105
 hoped+0.103
Neg logit contributions
 This-0.112
 Today-0.107
ore-0.097
-0.094
 These-0.090
Token to
Token ID284
Feature activation+2.50e+00

Pos logit contributions
 forgot+0.068
 stayed+0.058
 forget+0.055
 hoped+0.055
 promise+0.053
Neg logit contributions
 This-0.026
 Today-0.020
elly-0.019
ummy-0.019
 late-0.018
Token eat
Token ID4483
Feature activation-5.60e+00

Pos logit contributions
 forgot+0.047
 stayed+0.036
 hoped+0.035
 sighed+0.034
 regretted+0.033
Neg logit contributions
 This-0.050
 Today-0.049
ach-0.043
ummy-0.043
time-0.042
Token lunch
Token ID9965
Feature activation-8.92e+00

Pos logit contributions
 This+0.100
 Today+0.098
elly+0.093
ummy+0.089
uttering+0.088
Neg logit contributions
 forgot-0.124
 stayed-0.108
 waited-0.098
 hoped-0.095
 learned-0.092
Token first
Token ID717
Feature activation-2.39e+00

Pos logit contributions
 This+0.128
 Today+0.122
elly+0.113
ummy+0.110
ore+0.107
Neg logit contributions
 forgot-0.232
 stayed-0.203
 waited-0.188
 hoped-0.184
 learned-0.177
Token.
Token ID13
Feature activation-3.15e+00

Pos logit contributions
 This+0.033
 Today+0.031
elly+0.030
uttering+0.029
ires+0.029
Neg logit contributions
 forgot-0.062
 stayed-0.055
 waited-0.051
 hoped-0.050
 learned-0.048
Token
Token ID198
Feature activation-5.08e+00

Pos logit contributions
ocol+0.070
ummy+0.069
uttering+0.069
elly+0.066
ires+0.065
Neg logit contributions
 forgot-0.088
 stayed-0.072
 waited-0.071
 hoped-0.071
 learned-0.067
Token
Token ID198
Feature activation-4.40e+00

Pos logit contributions
elly+0.073
uttering+0.072
ummy+0.071
 This+0.069
 Today+0.069
Neg logit contributions
 forgot-0.122
 stayed-0.105
 hoped-0.104
 learned-0.103
 never-0.102
Token"
Token ID1
Feature activation-1.94e-01

Pos logit contributions
 This+0.066
 Today+0.065
ummy+0.062
elly+0.060
ires+0.057
Neg logit contributions
 forgot-0.113
 stayed-0.098
 waited-0.091
 hoped-0.089
 learned-0.088
TokenHelp
Token ID22087
Feature activation-1.56e+00

Pos logit contributions
 This+0.003
 Today+0.002
elly+0.002
+0.002
 late+0.002
Neg logit contributions
 forgot-0.005
 stayed-0.004
 forget-0.004
 hoped-0.004
 wouldn-0.004
Token!
Token ID0
Feature activation-2.16e+00

Pos logit contributions
 This+0.022
 Today+0.021
elly+0.019
ires+0.019
ummy+0.018
Neg logit contributions
 forgot-0.041
 stayed-0.036
 waited-0.034
 hoped-0.033
 forget-0.032
Token Help
Token ID10478
Feature activation-3.64e+00

Pos logit contributions
 Today+0.030
ires+0.030
elly+0.030
 This+0.029
ummy+0.029
Neg logit contributions
 forgot-0.055
 stayed-0.048
 waited-0.045
 hoped-0.043
 forget-0.042
Token!"
Token ID2474
Feature activation-4.03e+00

Pos logit contributions
 This+0.055
 Today+0.052
ires+0.049
elly+0.048
uttering+0.048
Neg logit contributions
 forgot-0.092
 stayed-0.080
 waited-0.074
 forget-0.070
 hoped-0.070
Token Lily
Token ID20037
Feature activation+5.21e+00

Pos logit contributions
 This+0.067
 Today+0.064
elly+0.061
ummy+0.060
ires+0.058
Neg logit contributions
 forgot-0.096
 stayed-0.083
 waited-0.075
 hoped-0.074
 forget-0.072
Token and
Token ID290
Feature activation+2.06e+00

Pos logit contributions
 forgot+0.113
 stayed+0.096
 hoped+0.083
 waited+0.083
 managed+0.082
Neg logit contributions
 This-0.094
 Today-0.093
elly-0.087
ore-0.084
-0.082
Token Tom
Token ID4186
Feature activation+5.26e+00

Pos logit contributions
 forgot+0.044
 stayed+0.038
 waited+0.036
 hoped+0.033
 forget+0.032
Neg logit contributions
elly-0.038
 Today-0.038
 This-0.038
ummy-0.037
ore-0.037
Token shout
Token ID9191
Feature activation-4.35e+00

Pos logit contributions
 forgot+0.107
 stayed+0.087
 hoped+0.077
 waited+0.075
 managed+0.075
Neg logit contributions
 This-0.100
 Today-0.099
ore-0.091
-0.086
elly-0.084
Token there
Token ID612
Feature activation+7.50e-02

Pos logit contributions
ires+0.080
elly+0.079
uttering+0.075
oky+0.071
eddy+0.071
Neg logit contributions
 forgot-0.062
 stayed-0.053
 laughed-0.046
 never-0.044
 didn-0.042
Token was
Token ID373
Feature activation-7.10e-01

Pos logit contributions
 forgot+0.001
 stayed+0.001
 waited+0.001
 hoped+0.001
 learned+0.001
Neg logit contributions
 This-0.002
 Today-0.002
elly-0.002
ummy-0.002
ires-0.002
Token a
Token ID257
Feature activation-5.04e-01

Pos logit contributions
ore+0.015
 This+0.015
elly+0.014
ires+0.014
ings+0.014
Neg logit contributions
 forgot-0.012
 stayed-0.011
 waited-0.010
 learned-0.010
 never-0.009
Token little
Token ID1310
Feature activation-9.41e-01

Pos logit contributions
 This+0.010
 Today+0.009
elly+0.009
ummy+0.009
ore+0.009
Neg logit contributions
 forgot-0.010
 stayed-0.009
 waited-0.008
 hoped-0.008
 forget-0.007
Token robot
Token ID9379
Feature activation-1.62e-01

Pos logit contributions
 This+0.019
 Today+0.019
elly+0.019
ummy+0.018
ore+0.017
Neg logit contributions
 forgot-0.019
 stayed-0.016
 waited-0.014
 hoped-0.014
 managed-0.013
Token.
Token ID13
Feature activation-3.49e+00

Pos logit contributions
 This+0.003
 Today+0.003
elly+0.003
ummy+0.003
ires+0.003
Neg logit contributions
 forgot-0.003
 stayed-0.003
 waited-0.002
 hoped-0.002
 learned-0.002
Token He
Token ID679
Feature activation+6.68e+00

Pos logit contributions
uttering+0.054
elly+0.049
ires+0.048
ummy+0.047
ore+0.044
Neg logit contributions
 forgot-0.082
 stayed-0.074
 waited-0.070
 hoped-0.070
 learned-0.069
Token was
Token ID373
Feature activation+2.92e+00

Pos logit contributions
 forgot+0.123
 stayed+0.098
 forget+0.087
 waited+0.087
 hoped+0.085
Neg logit contributions
 This-0.145
 Today-0.138
elly-0.130
ore-0.127
ummy-0.126
Token a
Token ID257
Feature activation+1.36e+00

Pos logit contributions
 forgot+0.058
 stayed+0.049
 waited+0.043
 hoped+0.043
 forget+0.041
Neg logit contributions
 This-0.060
 Today-0.058
elly-0.055
ummy-0.055
ires-0.053
Token very
Token ID845
Feature activation+2.39e+00

Pos logit contributions
 forgot+0.031
 stayed+0.026
 waited+0.024
 hoped+0.023
 forget+0.022
Neg logit contributions
 This-0.024
 Today-0.023
elly-0.022
ummy-0.022
ore-0.021
Token persistent
Token ID16218
Feature activation-1.34e+00

Pos logit contributions
 forgot+0.052
 stayed+0.043
 waited+0.039
 hoped+0.038
 forget+0.038
Neg logit contributions
 This-0.045
 Today-0.044
elly-0.041
ummy-0.041
ore-0.040
Token.
Token ID13
Feature activation-4.72e+00

Pos logit contributions
elly+0.037
 Today+0.035
 This+0.035
ummy+0.034
ires+0.034
Neg logit contributions
 forgot-0.062
 stayed-0.056
 waited-0.051
 hoped-0.050
 hugged-0.050
Token "
Token ID366
Feature activation-1.40e+00

Pos logit contributions
ocol+0.076
igsaw+0.071
ummy+0.071
uttering+0.070
ires+0.070
Neg logit contributions
 forgot-0.106
 waited-0.091
 hoped-0.090
 stayed-0.089
 learned-0.085
TokenWe
Token ID1135
Feature activation+6.52e+00

Pos logit contributions
 Today+0.030
 This+0.030
ummy+0.029
elly+0.027
ore+0.027
Neg logit contributions
 forgot-0.027
 stayed-0.022
 waited-0.021
 hoped-0.020
 learned-0.019
Token did
Token ID750
Feature activation-5.59e-01

Pos logit contributions
 forgot+0.101
 scar+0.101
 passengers+0.093
ode+0.092
 stayed+0.088
Neg logit contributions
 This-0.105
 Today-0.101
-0.095
elly-0.087
ore-0.086
Token not
Token ID407
Feature activation+3.92e+00

Pos logit contributions
elly+0.015
 Today+0.015
 This+0.014
ummy+0.014
uttering+0.014
Neg logit contributions
 forgot-0.008
 stayed-0.006
 waited-0.005
 never-0.005
 hoped-0.005
Token know
Token ID760
Feature activation-2.44e+00

Pos logit contributions
 forgot+0.073
 stayed+0.060
 hoped+0.053
 waited+0.052
 forget+0.049
Neg logit contributions
 This-0.085
 Today-0.082
elly-0.079
ummy-0.077
ore-0.075
Token.
Token ID13
Feature activation-3.45e+00

Pos logit contributions
 Today+0.037
 This+0.037
elly+0.034
uttering+0.034
ore+0.032
Neg logit contributions
 forgot-0.061
 stayed-0.054
 waited-0.049
 hoped-0.048
 learned-0.047
Token We
Token ID775
Feature activation+6.14e+00

Pos logit contributions
uttering+0.054
elly+0.049
 Today+0.048
ummy+0.048
ore+0.047
Neg logit contributions
 forgot-0.080
 stayed-0.069
 waited-0.067
 hoped-0.066
 forget-0.062
Token just
Token ID655
Feature activation+5.22e+00

Pos logit contributions
ode+0.085
 forgot+0.083
 scar+0.082
 passengers+0.079
 forth+0.077
Neg logit contributions
 This-0.106
elly-0.104
 Today-0.096
-0.095
ore-0.093
Token wanted
Token ID2227
Feature activation-1.31e+00

Pos logit contributions
 forgot+0.091
 stayed+0.075
ode+0.073
 scar+0.070
 forget+0.069
Neg logit contributions
 This-0.103
 Today-0.093
elly-0.090
ore-0.085
-0.084
Token to
Token ID284
Feature activation+1.85e+00

Pos logit contributions
 This+0.020
 Today+0.019
elly+0.018
ummy+0.017
ore+0.017
Neg logit contributions
 forgot-0.033
 stayed-0.028
 waited-0.026
 hoped-0.026
 learned-0.025
Token
Token ID198
Feature activation-5.02e+00

Pos logit contributions
elly+0.072
 Today+0.070
ires+0.069
 This+0.068
uttering+0.068
Neg logit contributions
 forgot-0.147
 stayed-0.132
 waited-0.123
 learned-0.123
 never-0.123
Token"
Token ID1
Feature activation+4.91e-01

Pos logit contributions
 This+0.087
 Today+0.085
elly+0.081
ummy+0.080
ires+0.078
Neg logit contributions
 forgot-0.113
 stayed-0.098
 waited-0.089
 hoped-0.086
 learned-0.085
TokenIt
Token ID1026
Feature activation+4.32e+00

Pos logit contributions
 forgot+0.013
 stayed+0.012
 hoped+0.011
 waited+0.011
 forget+0.010
Neg logit contributions
 This-0.006
elly-0.006
 Today-0.006
ires-0.005
ummy-0.005
Token's
Token ID338
Feature activation+2.60e+00

Pos logit contributions
 forgot+0.076
 stayed+0.059
 hoped+0.058
 waited+0.056
 learned+0.053
Neg logit contributions
 This-0.097
 Today-0.088
ummy-0.083
elly-0.078
 That-0.078
Token not
Token ID407
Feature activation+3.82e+00

Pos logit contributions
 forgot+0.058
 stayed+0.048
 hoped+0.046
 waited+0.044
 sighed+0.043
Neg logit contributions
 This-0.046
 Today-0.045
ummy-0.042
elly-0.040
ires-0.038
Token polite
Token ID23507
Feature activation-3.06e+00

Pos logit contributions
 forgot+0.095
 stayed+0.080
 hoped+0.076
 waited+0.075
 sighed+0.074
Neg logit contributions
 This-0.058
 Today-0.053
ummy-0.049
elly-0.047
ires-0.045
Token to
Token ID284
Feature activation+1.83e+00

Pos logit contributions
 This+0.042
 Today+0.040
elly+0.037
ummy+0.036
ires+0.036
Neg logit contributions
 forgot-0.081
 stayed-0.072
 waited-0.065
 hoped-0.064
 forget-0.063
Token lend
Token ID22096
Feature activation-4.13e+00

Pos logit contributions
 forgot+0.031
 stayed+0.025
 waited+0.022
 hoped+0.022
 learned+0.020
Neg logit contributions
 This-0.043
 Today-0.041
ummy-0.039
elly-0.039
ires-0.038
Token things
Token ID1243
Feature activation-2.36e+00

Pos logit contributions
 This+0.072
 Today+0.071
elly+0.068
ummy+0.067
uttering+0.065
Neg logit contributions
 forgot-0.092
 stayed-0.079
 waited-0.070
 hoped-0.069
 learned-0.068
Token without
Token ID1231
Feature activation+1.88e+00

Pos logit contributions
 This+0.036
 Today+0.035
elly+0.032
ummy+0.031
ires+0.031
Neg logit contributions
 forgot-0.059
 stayed-0.051
 waited-0.047
 hoped-0.046
 forget-0.045
Token asking
Token ID4737
Feature activation-3.31e+00

Pos logit contributions
 forgot+0.043
 stayed+0.036
 hoped+0.033
 waited+0.033
 forget+0.032
Neg logit contributions
 This-0.032
 Today-0.029
ummy-0.029
elly-0.028
ires-0.027
Token noisy
Token ID31210
Feature activation-1.08e+00

Pos logit contributions
 forgot+0.055
 stayed+0.047
 hoped+0.044
 waited+0.043
 wouldn+0.043
Neg logit contributions
 This-0.026
 Today-0.025
ummy-0.021
elly-0.021
-0.021
Token wind
Token ID2344
Feature activation-2.98e+00

Pos logit contributions
 This+0.020
 Today+0.019
ummy+0.018
elly+0.018
ore+0.017
Neg logit contributions
 forgot-0.025
 stayed-0.020
 hoped-0.019
 waited-0.019
 forget-0.018
Token.
Token ID13
Feature activation-3.52e+00

Pos logit contributions
 This+0.034
 Today+0.032
elly+0.030
ummy+0.029
ore+0.028
Neg logit contributions
 forgot-0.085
 stayed-0.075
 waited-0.070
 hoped-0.069
 forget-0.068
Token<|endoftext|>
Token ID50256
Feature activation-7.57e+00

Pos logit contributions
elly+0.040
uttering+0.038
 This+0.038
ummy+0.037
ires+0.036
Neg logit contributions
 forgot-0.097
 stayed-0.086
 waited-0.081
 hoped-0.081
 learned-0.077
TokenOnce
Token ID7454
Feature activation-2.91e+00

Pos logit contributions
ires+0.124
uttering+0.120
ummy+0.112
ocol+0.109
elly+0.108
Neg logit contributions
 forgot-0.158
 stayed-0.147
 waited-0.140
 had-0.140
 learned-0.140
Token upon
Token ID2402
Feature activation-2.17e+00

Pos logit contributions
 This+0.045
elly+0.043
 Today+0.041
uttering+0.039
ach+0.039
Neg logit contributions
 forgot-0.072
 stayed-0.060
 hoped-0.056
 waited-0.054
 forget-0.053
Token a
Token ID257
Feature activation-1.18e+00

Pos logit contributions
ummy+0.040
 This+0.039
elly+0.039
 Today+0.039
ires+0.037
Neg logit contributions
 forgot-0.046
 stayed-0.041
 waited-0.037
 hoped-0.037
 learned-0.036
Token time
Token ID640
Feature activation-3.73e+00

Pos logit contributions
 This+0.021
 Today+0.020
elly+0.019
ummy+0.019
ires+0.019
Neg logit contributions
 forgot-0.027
 stayed-0.023
 waited-0.021
 hoped-0.020
 learned-0.020
Token there
Token ID612
Feature activation+4.29e-02

Pos logit contributions
elly+0.080
ires+0.080
uttering+0.073
eddy+0.072
oky+0.071
Neg logit contributions
 forgot-0.063
 stayed-0.055
 laughed-0.047
 never-0.046
 waited-0.043
Token was
Token ID373
Feature activation-9.09e-01

Pos logit contributions
 forgot+0.001
 stayed+0.001
 waited+0.000
 hoped+0.000
 learned+0.000
Neg logit contributions
 This-0.001
 Today-0.001
elly-0.001
ummy-0.001
ires-0.001
Token a
Token ID257
Feature activation-5.16e-01

Pos logit contributions
ore+0.019
 This+0.018
elly+0.018
 Today+0.017
ummy+0.017
Neg logit contributions
 forgot-0.016
 stayed-0.014
 waited-0.013
 learned-0.013
 never-0.012
Token tops
Token ID21246
Feature activation-3.44e+00

Pos logit contributions
 forgot+0.090
 stayed+0.076
 waited+0.068
 hoped+0.067
 learned+0.064
Neg logit contributions
 This-0.079
 Today-0.077
ummy-0.073
elly-0.072
ires-0.070
Token spin
Token ID7906
Feature activation-5.49e+00

Pos logit contributions
 This+0.058
 Today+0.056
ummy+0.052
elly+0.052
ore+0.050
Neg logit contributions
 forgot-0.081
 stayed-0.070
 waited-0.063
 hoped-0.063
 learned-0.060
Token and
Token ID290
Feature activation+4.99e+00

Pos logit contributions
 This+0.099
 Today+0.097
elly+0.094
ummy+0.092
ires+0.089
Neg logit contributions
 forgot-0.117
 stayed-0.103
 waited-0.092
 hoped-0.090
 learned-0.086
Token spin
Token ID7906
Feature activation-6.14e+00

Pos logit contributions
 forgot+0.094
 stayed+0.078
 hoped+0.067
 waited+0.067
 promised+0.064
Neg logit contributions
 This-0.106
 Today-0.103
ore-0.088
ires-0.088
ummy-0.087
Token and
Token ID290
Feature activation+4.59e+00

Pos logit contributions
 This+0.109
 Today+0.107
elly+0.106
ummy+0.105
uttering+0.101
Neg logit contributions
 forgot-0.130
 stayed-0.115
 waited-0.103
 hoped-0.102
 learned-0.098
Token spin
Token ID7906
Feature activation-6.46e+00

Pos logit contributions
 forgot+0.088
 stayed+0.074
 hoped+0.064
 waited+0.064
 promised+0.062
Neg logit contributions
 This-0.095
 Today-0.091
ore-0.079
elly-0.077
ires-0.076
Token.
Token ID13
Feature activation-4.45e+00

Pos logit contributions
 This+0.102
 Today+0.101
elly+0.099
ummy+0.099
uttering+0.096
Neg logit contributions
 forgot-0.147
 stayed-0.132
 waited-0.119
 hoped-0.119
 never-0.114
Token They
Token ID1119
Feature activation+7.40e+00

Pos logit contributions
uttering+0.084
ummy+0.075
elly+0.074
ach+0.074
inking+0.072
Neg logit contributions
 forgot-0.084
 hoped-0.068
 stayed-0.068
 waited-0.066
 learned-0.064
Token cheer
Token ID14042
Feature activation-4.86e+00

Pos logit contributions
 forgot+0.147
 stayed+0.131
 regretted+0.126
 punished+0.125
 promised+0.120
Neg logit contributions
 This-0.124
 Today-0.122
 These-0.095
-0.094
ore-0.091
Token for
Token ID329
Feature activation-2.77e-01

Pos logit contributions
 This+0.090
 Today+0.087
elly+0.087
ore+0.082
ummy+0.082
Neg logit contributions
 forgot-0.104
 stayed-0.090
 waited-0.080
 hoped-0.079
 forget-0.075
Token their
Token ID511
Feature activation+3.50e+00

Pos logit contributions
 This+0.004
 Today+0.004
ires+0.004
ummy+0.004
ore+0.003
Neg logit contributions
 forgot-0.007
 stayed-0.006
 regretted-0.005
 managed-0.005
 waited-0.005
Token but
Token ID475
Feature activation+3.84e+00

Pos logit contributions
 forgot+0.019
 stayed+0.016
 waited+0.015
 hoped+0.015
 promise+0.015
Neg logit contributions
 This-0.012
 Today-0.011
ummy-0.009
elly-0.009
ore-0.009
Token he
Token ID339
Feature activation+7.57e+00

Pos logit contributions
 forgot+0.087
 stayed+0.076
ode+0.072
 hoped+0.070
 waited+0.069
Neg logit contributions
 This-0.058
 Today-0.055
ummy-0.049
elly-0.049
 late-0.047
Token took
Token ID1718
Feature activation-8.55e-01

Pos logit contributions
ode+0.102
 forgot+0.096
 stations+0.093
 forget+0.091
 scar+0.090
Neg logit contributions
 This-0.120
:-0.116
elly-0.113
 with-0.113
-0.112
Token a
Token ID257
Feature activation+1.56e+00

Pos logit contributions
 This+0.013
 Today+0.012
ummy+0.011
elly+0.011
ore+0.011
Neg logit contributions
 forgot-0.022
 stayed-0.019
 waited-0.017
 hoped-0.017
 forget-0.017
Token deep
Token ID2769
Feature activation-2.98e+00

Pos logit contributions
 forgot+0.038
 stayed+0.034
 hoped+0.031
 waited+0.030
 learned+0.028
Neg logit contributions
 This-0.025
 Today-0.024
ore-0.023
elly-0.022
ummy-0.021
Token breath
Token ID8033
Feature activation-6.75e+00

Pos logit contributions
 This+0.069
 Today+0.068
elly+0.064
ummy+0.064
ore+0.064
Neg logit contributions
 forgot-0.052
 stayed-0.042
 waited-0.035
 hoped-0.035
 forget-0.033
Token and
Token ID290
Feature activation+5.68e+00

Pos logit contributions
 This+0.113
 Today+0.108
elly+0.103
ummy+0.102
ires+0.101
Neg logit contributions
 forgot-0.156
 stayed-0.136
 waited-0.123
 hoped-0.121
 learned-0.117
Token began
Token ID2540
Feature activation-1.53e+00

Pos logit contributions
ode+0.080
 forgot+0.074
 promise+0.063
 forget+0.061
 stayed+0.057
Neg logit contributions
 This-0.114
 late-0.107
 A-0.105
-0.100
ore-0.098
Token to
Token ID284
Feature activation+3.03e+00

Pos logit contributions
 Today+0.024
 This+0.024
elly+0.024
ummy+0.023
ires+0.022
Neg logit contributions
 forgot-0.037
 stayed-0.033
 waited-0.030
 hoped-0.029
 learned-0.028
Token dance
Token ID9280
Feature activation-6.20e+00

Pos logit contributions
 forgot+0.061
 stayed+0.049
 hoped+0.046
 waited+0.044
 regretted+0.042
Neg logit contributions
 This-0.056
 Today-0.055
ore-0.048
 outdoors-0.047
uttering-0.045
Token.
Token ID13
Feature activation-4.18e+00

Pos logit contributions
 This+0.088
 Today+0.085
ummy+0.083
elly+0.081
ires+0.079
Neg logit contributions
 forgot-0.157
 stayed-0.141
 waited-0.127
 hoped-0.126
 learned-0.123
Tokenoppy
Token ID26696
Feature activation+5.66e+00

Pos logit contributions
 This+0.009
 Today+0.008
elly+0.007
ummy+0.007
ires+0.007
Neg logit contributions
 forgot-0.007
 stayed-0.006
 waited-0.005
 hoped-0.005
 forget-0.005
Token decided
Token ID3066
Feature activation-8.70e-01

Pos logit contributions
 forget+0.089
 forgot+0.089
 least+0.087
ode+0.086
 passengers+0.083
Neg logit contributions
 This-0.089
-0.078
ummy-0.076
elly-0.075
 Today-0.073
Token to
Token ID284
Feature activation+2.34e+00

Pos logit contributions
 This+0.010
 Today+0.008
ummy+0.007
elly+0.007
ore+0.007
Neg logit contributions
 forgot-0.025
 stayed-0.022
 waited-0.021
 hoped-0.021
 forget-0.020
Token take
Token ID1011
Feature activation-1.64e+00

Pos logit contributions
 forgot+0.052
 sighed+0.042
 stayed+0.041
 regretted+0.041
 hoped+0.040
Neg logit contributions
 This-0.043
 Today-0.039
ummy-0.035
 On-0.034
ore-0.033
Token a
Token ID257
Feature activation+1.85e+00

Pos logit contributions
 This+0.027
 Today+0.027
elly+0.026
ummy+0.025
ires+0.024
Neg logit contributions
 forgot-0.039
 stayed-0.034
 waited-0.031
 hoped-0.030
 learned-0.030
Token nap
Token ID25422
Feature activation-6.19e+00

Pos logit contributions
 forgot+0.036
 stayed+0.030
 waited+0.026
 hoped+0.026
 learned+0.024
Neg logit contributions
 This-0.039
 Today-0.038
elly-0.036
ummy-0.036
ore-0.035
Token next
Token ID1306
Feature activation-2.24e+00

Pos logit contributions
 This+0.080
 Today+0.077
elly+0.072
ummy+0.072
ore+0.069
Neg logit contributions
 forgot-0.168
 stayed-0.145
 waited-0.135
 hoped-0.133
 forget-0.131
Token to
Token ID284
Feature activation+3.84e-01

Pos logit contributions
 This+0.032
 Today+0.031
elly+0.029
ires+0.029
ummy+0.028
Neg logit contributions
 forgot-0.057
 stayed-0.050
 waited-0.046
 hoped-0.045
 forget-0.044
Token the
Token ID262
Feature activation+1.74e+00

Pos logit contributions
 forgot+0.009
 stayed+0.008
 waited+0.007
 hoped+0.007
 forget+0.007
Neg logit contributions
 This-0.006
 Today-0.006
ummy-0.005
ore-0.005
elly-0.005
Token squash
Token ID34613
Feature activation-1.53e+00

Pos logit contributions
 forgot+0.035
 stayed+0.029
 waited+0.026
 forget+0.025
 hoped+0.025
Neg logit contributions
 This-0.036
 Today-0.035
elly-0.033
ore-0.032
ummy-0.031
Token.
Token ID13
Feature activation-3.93e+00

Pos logit contributions
 This+0.019
 Today+0.018
ummy+0.016
elly+0.016
ore+0.016
Neg logit contributions
 forgot-0.043
 stayed-0.037
 waited-0.035
 hoped-0.034
 forget-0.033
Token bad
Token ID2089
Feature activation-1.81e-01

Pos logit contributions
 forgot+0.084
 stayed+0.076
 waited+0.071
 argued+0.069
 hoped+0.068
Neg logit contributions
 This-0.048
 Today-0.047
ore-0.039
 late-0.039
ummy-0.039
Token ending
Token ID7464
Feature activation-4.26e+00

Pos logit contributions
 Today+0.003
 This+0.003
ummy+0.003
ore+0.002
elly+0.002
Neg logit contributions
 forgot-0.004
 stayed-0.004
 hoped-0.003
 waited-0.003
 managed-0.003
Token for
Token ID329
Feature activation-1.28e+00

Pos logit contributions
 This+0.054
 Today+0.050
elly+0.047
ummy+0.047
ore+0.046
Neg logit contributions
 forgot-0.116
 stayed-0.101
 waited-0.094
 hoped-0.094
 forget-0.092
Token him
Token ID683
Feature activation+1.82e+00

Pos logit contributions
 This+0.019
ummy+0.017
 Today+0.017
ires+0.017
ore+0.016
Neg logit contributions
 forgot-0.033
 stayed-0.027
 hoped-0.025
 waited-0.025
 forget-0.025
Token.
Token ID13
Feature activation-2.85e+00

Pos logit contributions
 forgot+0.051
 stayed+0.045
 waited+0.043
 hoped+0.042
 sighed+0.041
Neg logit contributions
 This-0.021
 Today-0.019
elly-0.017
ummy-0.017
ore-0.016
Token<|endoftext|>
Token ID50256
Feature activation-7.51e+00

Pos logit contributions
 This+0.025
 Today+0.025
elly+0.023
ummy+0.022
uttering+0.021
Neg logit contributions
 forgot-0.087
 stayed-0.078
 waited-0.073
 hoped-0.073
 learned-0.071
TokenMax
Token ID11518
Feature activation+3.88e+00

Pos logit contributions
ires+0.138
uttering+0.138
ocol+0.131
elly+0.127
ummy+0.127
Neg logit contributions
 forgot-0.141
 learned-0.126
 stayed-0.125
 had-0.122
 never-0.120
Token was
Token ID373
Feature activation+2.21e+00

Pos logit contributions
 forgot+0.065
 stayed+0.052
 forget+0.046
 waited+0.045
 hoped+0.044
Neg logit contributions
 This-0.087
 Today-0.083
elly-0.079
-0.077
ummy-0.076
Token very
Token ID845
Feature activation+2.42e+00

Pos logit contributions
 forgot+0.052
 stayed+0.045
 waited+0.041
 hoped+0.040
 learned+0.039
Neg logit contributions
 This-0.037
 Today-0.036
elly-0.034
ummy-0.033
ires-0.032
Token tired
Token ID10032
Feature activation-4.71e+00

Pos logit contributions
 forgot+0.052
 stayed+0.045
 waited+0.040
 hoped+0.039
 forget+0.038
Neg logit contributions
 This-0.045
 Today-0.044
elly-0.042
ummy-0.041
ires-0.040
Token.
Token ID13
Feature activation-2.62e+00

Pos logit contributions
 This+0.056
 Today+0.053
elly+0.049
ummy+0.049
ore+0.046
Neg logit contributions
 forgot-0.135
 stayed-0.118
 hoped-0.110
 waited-0.109
 forget-0.106
Token because
Token ID780
Feature activation+3.60e-01

Pos logit contributions
 Today+0.077
 This+0.076
ithering+0.072
elly+0.072
ore+0.071
Neg logit contributions
 forgot-0.093
 stayed-0.081
 waited-0.074
 never-0.069
 kept-0.068
Token she
Token ID673
Feature activation+8.21e+00

Pos logit contributions
 forgot+0.008
 stayed+0.007
 waited+0.006
 hoped+0.006
 forget+0.006
Neg logit contributions
 This-0.006
 Today-0.006
elly-0.006
ummy-0.005
ore-0.005
Token was
Token ID373
Feature activation+3.50e+00

Pos logit contributions
 forgot+0.136
ode+0.128
 promise+0.125
 scar+0.123
 forget+0.118
Neg logit contributions
 This-0.157
ore-0.132
-0.130
 Today-0.128
looking-0.128
Token going
Token ID1016
Feature activation-2.98e+00

Pos logit contributions
 forgot+0.088
 stayed+0.075
 waited+0.068
 hoped+0.068
 forget+0.067
Neg logit contributions
 This-0.054
 Today-0.049
ummy-0.046
elly-0.045
uttering-0.044
Token to
Token ID284
Feature activation+6.95e-01

Pos logit contributions
elly+0.050
 This+0.049
 Today+0.048
ummy+0.047
ires+0.047
Neg logit contributions
 forgot-0.066
 stayed-0.059
 waited-0.054
 hoped-0.051
 never-0.051
Token drive
Token ID3708
Feature activation-6.46e+00

Pos logit contributions
 forgot+0.014
 stayed+0.012
 waited+0.011
 hoped+0.011
 forget+0.011
Neg logit contributions
 This-0.013
 Today-0.013
elly-0.013
ummy-0.012
ires-0.012
Token for
Token ID329
Feature activation-1.11e+00

Pos logit contributions
 This+0.105
 Today+0.103
elly+0.102
ummy+0.099
ires+0.096
Neg logit contributions
 forgot-0.147
 stayed-0.129
 waited-0.120
 hoped-0.116
 learned-0.113
Token the
Token ID262
Feature activation+1.45e+00

Pos logit contributions
 This+0.017
 Today+0.016
elly+0.015
ummy+0.015
ires+0.014
Neg logit contributions
 forgot-0.028
 stayed-0.025
 waited-0.023
 hoped-0.022
 forget-0.022
Token first
Token ID717
Feature activation-9.13e-01

Pos logit contributions
 forgot+0.032
 stayed+0.027
 hoped+0.025
 waited+0.024
 learned+0.023
Neg logit contributions
 This-0.026
 Today-0.026
ummy-0.024
elly-0.024
ires-0.023
Token time
Token ID640
Feature activation-4.11e+00

Pos logit contributions
 This+0.016
 Today+0.015
elly+0.015
ummy+0.014
ore+0.014
Neg logit contributions
 forgot-0.021
 stayed-0.018
 waited-0.016
 hoped-0.016
 forget-0.015
Token.
Token ID13
Feature activation-3.57e+00

Pos logit contributions
 This+0.051
 Today+0.048
elly+0.044
ummy+0.043
ires+0.042
Neg logit contributions
 forgot-0.115
 stayed-0.102
 waited-0.095
 hoped-0.093
 forget-0.090