TOP ACTIVATIONS
MAX = 13.688

he tried to take deep breaths to calm down . Tim
" I want to c uddle with you , mom .
, it kept on flying err atically with inexplicable speed .
play tug - of - war with it .
sob and he tried to plead but the old man had
She stood up and started sway ing to the music .
her eyes and took deep breaths . Soon , she felt
he thought it was too sm elly . Jane said ,
play tug - of - war !" The birds
new word , ' emer gency ', so she whispered the
feet . She took big breaths of fresh air and her
a key and tried to cover the drawer with it ,
˜ S ail ors Wanted â . Do
she had to go to bed with no chalk . <|endoftext|>
to grow l and sn arl to try and scare her
you . It is too sm elly for us . We
her cr ay ons to scrib ble on the wall .
could take lots of deep breaths and get lots of oxygen
play tug - of - war ," said the oct opus
her mom my watched in amaz ement as the machine flew

MIN ACTIVATIONS
MIN = -10.044

Lucy and her mom completed their mission . They had found
. They hoped to rebuild their village and make it even
checking that she had everything she needed . She even missed
One day , a mis chie vous young boy decided to
the prince and princess sealed their marriage with a kiss .
animals in the forest have their own tw igs that shine
best of friends . Everywhere Lucy went , the rabbit was
As M argo walked away , she thought
The friends used their numbers to try and make
be careful with the things she cut . <|endoftext|> Once upon
it wasn 't the flowers she was looking for .
branches . The bears used their strong arms to clear away
't known that the dish she had chosen was meant for
bad ! The dog ruined our work !" The dog bar
warm and bright . Everywhere Molly looked , she saw new
. " The cat ruined our chair !" They
and sugar . Even though she was only three years old
S ue felt guilty because she made the calendar messy .
the p uddle . Although she couldn 't go for a
. Sam and Sara used their creative minds and made up

INTERVAL 7.755 - 13.688
CONTAINS 0.092%

take out the journal and write something down . Every time
She put Anna on her bed and gave her a kiss
her neck and started to rub it .
started to sort them into piles . The
day , she wanted to write more . She looked for

INTERVAL 1.822 - 7.755
CONTAINS 39.401%

things that are not yours . The v ase was very
a bee flew by her . Jenny felt a bit scared
- of - war !" The birds agreed and
. She sang so many songs that all of the neighborhood
wondered what he was dreaming about . One day

INTERVAL -4.111 - 1.822
CONTAINS 43.524%

after her . He wanted to give it back to her
" You are too loud and messy . Go play somewhere
fun playing with clay on the lawn .
great time picking out her toy and she couldn 't wait
relieved , and Sue was feeling much better too ! They

INTERVAL -10.044 - -4.111
CONTAINS 16.984%

tide . The tide was the water that came and went
from the ground and opened the cherry by smashing the rock
" Now you have a fairy mark ," Fay e
named Lily . She had a cute puppy named Max .
so proud of how brave she had been .
Token he
Token ID339
Feature activation-6.26e+00

Pos logit contributions
 promise+0.060
 forgot+0.060
ode+0.055
 forget+0.049
 head+0.049
Neg logit contributions
 This-0.062
 late-0.055
 Do-0.050
ore-0.049
ges-0.049
Token tried
Token ID3088
Feature activation+5.56e+00

Pos logit contributions
ode+0.090
 promise+0.083
 forgot+0.078
 passengers+0.077
 way+0.076
Neg logit contributions
 This-0.109
ore-0.101
 late-0.096
-0.094
 Playing-0.087
Token to
Token ID284
Feature activation-9.29e-01

Pos logit contributions
 This+0.069
ore+0.057
ires+0.054
 Today+0.052
uttering+0.050
Neg logit contributions
 forgot-0.137
 way-0.118
 promise-0.118
 stayed-0.117
 forget-0.114
Token take
Token ID1011
Feature activation+2.85e+00

Pos logit contributions
 forgot+0.017
 regretted+0.014
ode+0.013
 sighed+0.013
 hoped+0.013
Neg logit contributions
 This-0.016
ore-0.013
 late-0.013
 Today-0.013
 here-0.012
Token deep
Token ID2769
Feature activation+3.93e+00

Pos logit contributions
 This+0.042
ore+0.034
 late+0.032
 Today+0.031
ires+0.030
Neg logit contributions
 forgot-0.067
 promise-0.057
 forget-0.055
 stayed-0.054
ode-0.054
Token breaths
Token ID45576
Feature activation+1.09e+01

Pos logit contributions
 This+0.093
ore+0.083
ires+0.081
 Today+0.080
uttering+0.080
Neg logit contributions
 forgot-0.052
 way-0.039
 promise-0.039
 stayed-0.038
 bit-0.036
Token to
Token ID284
Feature activation+2.78e-01

Pos logit contributions
 This+0.156
ore+0.131
ires+0.123
 Today+0.122
uttering+0.117
Neg logit contributions
 forgot-0.243
 promise-0.207
 way-0.204
 stayed-0.204
 forget-0.199
Token calm
Token ID9480
Feature activation+6.02e+00

Pos logit contributions
 This+0.005
ore+0.005
 late+0.004
ires+0.004
 Today+0.004
Neg logit contributions
 forgot-0.005
ode-0.004
 promise-0.004
 stayed-0.004
 regretted-0.004
Token down
Token ID866
Feature activation+3.58e+00

Pos logit contributions
 This+0.082
ore+0.071
uttering+0.066
ires+0.066
 Today+0.065
Neg logit contributions
 forgot-0.138
 way-0.118
 stayed-0.117
 promise-0.117
 forget-0.113
Token.
Token ID13
Feature activation+4.37e+00

Pos logit contributions
 This+0.052
ires+0.046
uttering+0.046
ore+0.045
 Today+0.043
Neg logit contributions
 forgot-0.072
 way-0.066
 stayed-0.063
 bit-0.063
 promise-0.062
Token Tim
Token ID5045
Feature activation-5.42e+00

Pos logit contributions
 This+0.057
uttering+0.057
ore+0.055
ires+0.054
ges+0.051
Neg logit contributions
 forgot-0.094
 way-0.081
 stayed-0.078
 promise-0.077
 learned-0.075
Token "
Token ID366
Feature activation+2.17e+00

Pos logit contributions
 forgot+0.061
 promise+0.050
 stayed+0.048
 way+0.048
ode+0.047
Neg logit contributions
 This-0.067
ore-0.059
 late-0.056
 Today-0.055
ires-0.055
TokenI
Token ID40
Feature activation-3.78e+00

Pos logit contributions
 This+0.032
ore+0.028
ires+0.026
 Today+0.025
uttering+0.025
Neg logit contributions
 forgot-0.048
 promise-0.040
 stayed-0.040
 way-0.039
 forget-0.039
Token want
Token ID765
Feature activation+3.20e+00

Pos logit contributions
 forgot+0.069
 way+0.055
 promise+0.055
 stayed+0.055
ode+0.054
Neg logit contributions
 This-0.070
ore-0.062
 late-0.059
 Today-0.059
ires-0.056
Token to
Token ID284
Feature activation-1.58e-02

Pos logit contributions
 This+0.041
ore+0.033
 late+0.031
 Today+0.030
ires+0.030
Neg logit contributions
 forgot-0.078
 promise-0.067
 stayed-0.066
 way-0.065
 forget-0.065
Token c
Token ID269
Feature activation+6.55e+00

Pos logit contributions
 forgot+0.000
 stayed+0.000
 promise+0.000
 regretted+0.000
ode+0.000
Neg logit contributions
 This-0.000
ore-0.000
 Today-0.000
 late-0.000
ires-0.000
Tokenuddle
Token ID24500
Feature activation+1.06e+01

Pos logit contributions
 This+0.171
 Do+0.156
ges+0.156
 late+0.156
 Today+0.154
Neg logit contributions
 forgot-0.050
 promise-0.042
 scar-0.037
ode-0.032
 regretted-0.031
Token with
Token ID351
Feature activation+1.61e+00

Pos logit contributions
 This+0.147
uttering+0.132
ires+0.128
 Today+0.122
ore+0.122
Neg logit contributions
 forgot-0.219
 promise-0.197
 stayed-0.195
 bit-0.188
 way-0.188
Token you
Token ID345
Feature activation-1.65e+00

Pos logit contributions
 This+0.028
ore+0.024
 late+0.023
ires+0.023
 Today+0.023
Neg logit contributions
 forgot-0.032
 promise-0.026
 stayed-0.025
 way-0.025
 forget-0.025
Token,
Token ID11
Feature activation+6.11e-01

Pos logit contributions
 forgot+0.039
 promise+0.034
 stayed+0.033
 way+0.033
 forget+0.033
Neg logit contributions
 This-0.022
ore-0.018
 late-0.016
ires-0.016
 Today-0.016
Token mom
Token ID1995
Feature activation-2.10e+00

Pos logit contributions
 This+0.010
 Today+0.008
ore+0.008
 late+0.008
ires+0.008
Neg logit contributions
 forgot-0.013
 stayed-0.010
 promise-0.010
 regretted-0.010
ode-0.010
Token.
Token ID13
Feature activation+2.78e+00

Pos logit contributions
 forgot+0.048
 promise+0.041
 way+0.040
 stayed+0.040
 forget+0.039
Neg logit contributions
 This-0.030
ore-0.027
uttering-0.026
ires-0.025
 Today-0.024
Token,
Token ID11
Feature activation+1.16e+00

Pos logit contributions
 This+0.025
ore+0.018
 Today+0.016
 late+0.015
ires+0.015
Neg logit contributions
 forgot-0.066
ode-0.058
 promise-0.058
 stayed-0.056
 forget-0.056
Token it
Token ID340
Feature activation-3.51e+00

Pos logit contributions
 This+0.015
 late+0.012
ore+0.012
 Today+0.011
ires+0.011
Neg logit contributions
 forgot-0.028
 promise-0.025
ode-0.024
 stayed-0.024
 way-0.023
Token kept
Token ID4030
Feature activation+2.17e+00

Pos logit contributions
ode+0.053
 promise+0.051
 passengers+0.047
 forgot+0.044
 way+0.044
Neg logit contributions
 late-0.055
 This-0.053
overed-0.050
-0.049
ore-0.048
Token on
Token ID319
Feature activation+1.54e+00

Pos logit contributions
 This+0.032
ore+0.028
 Today+0.026
ires+0.026
 late+0.025
Neg logit contributions
 forgot-0.048
 promise-0.040
 stayed-0.040
 way-0.040
 forget-0.039
Token flying
Token ID7348
Feature activation+4.69e+00

Pos logit contributions
 This+0.025
ore+0.021
 late+0.020
 Today+0.020
ires+0.020
Neg logit contributions
 forgot-0.032
 promise-0.027
 stayed-0.026
 way-0.026
 forget-0.026
Token err
Token ID11454
Feature activation+1.04e+01

Pos logit contributions
 This+0.066
ore+0.056
 late+0.054
 Today+0.051
+0.049
Neg logit contributions
 forgot-0.109
 promise-0.093
 forget-0.089
ode-0.088
 stayed-0.088
Tokenatically
Token ID4142
Feature activation+1.08e+00

Pos logit contributions
 This+0.199
ore+0.173
 Today+0.169
ires+0.164
 late+0.162
Neg logit contributions
 forgot-0.179
 promise-0.146
 stayed-0.143
 way-0.140
 forget-0.137
Token with
Token ID351
Feature activation-1.05e+00

Pos logit contributions
 This+0.015
ore+0.013
 late+0.012
 Today+0.012
ires+0.012
Neg logit contributions
 forgot-0.024
 promise-0.021
 stayed-0.020
 way-0.020
 forget-0.020
Token inexplicable
Token ID49602
Feature activation-3.26e+00

Pos logit contributions
 forgot+0.026
 promise+0.023
ode+0.022
 forget+0.021
 stayed+0.021
Neg logit contributions
 This-0.014
 late-0.010
ore-0.010
ges-0.010
ires-0.009
Token speed
Token ID2866
Feature activation+2.73e+00

Pos logit contributions
 forgot+0.050
 promise+0.036
 stayed+0.035
 forget+0.035
ode+0.034
Neg logit contributions
 This-0.070
ore-0.062
uttering-0.060
 Today-0.060
ires-0.058
Token.
Token ID13
Feature activation+4.22e+00

Pos logit contributions
 This+0.033
ore+0.027
 late+0.024
 Today+0.024
ires+0.023
Neg logit contributions
 forgot-0.069
 promise-0.060
 stayed-0.058
 way-0.057
 forget-0.057
Token play
Token ID711
Feature activation+5.25e+00

Pos logit contributions
 forgot+0.009
 regretted+0.008
 sighed+0.008
 scar+0.007
ode+0.007
Neg logit contributions
 This-0.009
ore-0.007
 Today-0.007
 On-0.007
ires-0.006
Token tug
Token ID27762
Feature activation+6.67e+00

Pos logit contributions
 This+0.074
ore+0.063
ires+0.060
 Today+0.059
 late+0.058
Neg logit contributions
 forgot-0.118
 promise-0.103
 stayed-0.101
 way-0.099
 forget-0.097
Token-
Token ID12
Feature activation+2.21e+00

Pos logit contributions
 This+0.097
ore+0.078
 Today+0.077
uttering+0.073
ires+0.073
Neg logit contributions
 forgot-0.153
 stayed-0.129
 promise-0.128
 way-0.126
 scar-0.123
Tokenof
Token ID1659
Feature activation+2.40e+00

Pos logit contributions
 This+0.038
ore+0.034
 Today+0.032
ires+0.032
 late+0.032
Neg logit contributions
 forgot-0.043
 promise-0.035
 stayed-0.035
 way-0.034
 forget-0.034
Token-
Token ID12
Feature activation+1.99e+00

Pos logit contributions
 This+0.036
ore+0.030
 late+0.028
 Today+0.028
ires+0.028
Neg logit contributions
 forgot-0.053
 promise-0.045
 stayed-0.045
 way-0.044
 forget-0.043
Tokenwar
Token ID5767
Feature activation+1.03e+01

Pos logit contributions
 This+0.035
ore+0.031
 Today+0.029
ires+0.029
 late+0.029
Neg logit contributions
 forgot-0.038
 promise-0.031
 stayed-0.031
 way-0.030
 forget-0.030
Token with
Token ID351
Feature activation+7.23e-01

Pos logit contributions
 This+0.128
ore+0.108
ires+0.104
 Today+0.103
+0.100
Neg logit contributions
 forgot-0.243
 stayed-0.211
 way-0.210
 promise-0.207
 bit-0.202
Token it
Token ID340
Feature activation+2.56e-01

Pos logit contributions
 This+0.008
ore+0.006
ges+0.006
ires+0.006
 late+0.005
Neg logit contributions
 forgot-0.019
ode-0.017
 promise-0.016
 forget-0.016
 regretted-0.016
Token.
Token ID13
Feature activation+4.47e+00

Pos logit contributions
 This+0.003
ore+0.003
ires+0.002
 Today+0.002
 late+0.002
Neg logit contributions
 forgot-0.006
 promise-0.005
 stayed-0.005
 way-0.005
 forget-0.005
Token
Token ID220
Feature activation+4.94e+00

Pos logit contributions
 This+0.048
ore+0.044
ires+0.041
uttering+0.041
 late+0.038
Neg logit contributions
 forgot-0.112
 way-0.096
 promise-0.094
 stayed-0.094
 forget-0.091
Token
Token ID198
Feature activation+4.72e+00

Pos logit contributions
 This+0.065
uttering+0.058
ore+0.057
ocol+0.057
used+0.055
Neg logit contributions
 forgot-0.102
 way-0.087
 promise-0.086
 learned-0.084
 hoped-0.084
Token sob
Token ID27355
Feature activation+5.81e+00

Pos logit contributions
 forgot+0.041
ode+0.034
 passengers+0.033
 regretted+0.032
 scar+0.031
Neg logit contributions
 This-0.043
 Today-0.036
ore-0.035
 late-0.033
 On-0.032
Token and
Token ID290
Feature activation-3.82e+00

Pos logit contributions
 This+0.077
ore+0.062
+0.061
 late+0.059
 Today+0.058
Neg logit contributions
 forgot-0.137
 promise-0.120
 head-0.119
 stayed-0.118
 way-0.114
Token he
Token ID339
Feature activation-6.88e+00

Pos logit contributions
ode+0.063
 forgot+0.050
 promise+0.050
 passengers+0.047
 scar+0.046
Neg logit contributions
 This-0.067
 late-0.060
ore-0.054
 with-0.054
 That-0.053
Token tried
Token ID3088
Feature activation+4.53e+00

Pos logit contributions
ode+0.117
 sandbox+0.097
 promise+0.095
 forget+0.092
 matter+0.090
Neg logit contributions
 with-0.093
 at-0.087
 This-0.085
-0.085
-0.084
Token to
Token ID284
Feature activation-1.67e+00

Pos logit contributions
 This+0.057
ore+0.047
 late+0.043
 Today+0.042
ires+0.042
Neg logit contributions
 forgot-0.111
 promise-0.096
 stayed-0.094
 way-0.093
 forget-0.092
Token plead
Token ID30701
Feature activation+1.03e+01

Pos logit contributions
 forgot+0.030
 regretted+0.026
 scar+0.023
 sighed+0.023
ode+0.023
Neg logit contributions
 This-0.025
 here-0.022
?-0.022
 Today-0.021
ore-0.021
Token but
Token ID475
Feature activation-1.83e+00

Pos logit contributions
 This+0.156
+0.148
ore+0.140
 Today+0.134
 Playing+0.133
Neg logit contributions
 forgot-0.195
 promise-0.168
 stayed-0.166
 head-0.165
 way-0.159
Token the
Token ID262
Feature activation-6.33e+00

Pos logit contributions
 forgot+0.038
ode+0.037
 scar+0.034
 promise+0.034
 passengers+0.032
Neg logit contributions
 This-0.026
 late-0.023
ore-0.022
 Today-0.019
-0.018
Token old
Token ID1468
Feature activation-5.43e+00

Pos logit contributions
 forgot+0.129
 stayed+0.104
ode+0.104
 forget+0.099
 promise+0.099
Neg logit contributions
 This-0.108
 late-0.096
ore-0.095
 Today-0.092
ires-0.087
Token man
Token ID582
Feature activation-4.63e+00

Pos logit contributions
 forgot+0.080
 stayed+0.059
 promise+0.058
ode+0.058
 forget+0.058
Neg logit contributions
 This-0.122
ore-0.110
 late-0.108
 Today-0.106
-0.103
Token had
Token ID550
Feature activation-2.06e+00

Pos logit contributions
ode+0.070
 scar+0.066
 sandbox+0.065
 forgot+0.064
 passengers+0.063
Neg logit contributions
 This-0.071
ore-0.070
 with-0.062
used-0.062
 at-0.061
Token She
Token ID1375
Feature activation-6.55e+00

Pos logit contributions
uttering+0.045
ore+0.044
 This+0.044
ires+0.043
 late+0.038
Neg logit contributions
 forgot-0.094
 stayed-0.081
 way-0.079
 promise-0.079
 learned-0.078
Token stood
Token ID6204
Feature activation+5.07e+00

Pos logit contributions
ode+0.086
 forgot+0.082
 way+0.075
 promise+0.074
 passengers+0.073
Neg logit contributions
 This-0.132
-0.119
ore-0.117
 late-0.112
 Playing-0.109
Token up
Token ID510
Feature activation+3.29e+00

Pos logit contributions
 This+0.099
ore+0.085
 These+0.081
 Today+0.079
 Playing+0.077
Neg logit contributions
 forgot-0.090
 head-0.081
 stayed-0.077
 scar-0.075
 promise-0.075
Token and
Token ID290
Feature activation-3.29e+00

Pos logit contributions
 This+0.064
ore+0.057
 Playing+0.056
ires+0.056
 Today+0.054
Neg logit contributions
 forgot-0.051
 way-0.045
 bit-0.044
 head-0.043
 stayed-0.043
Token started
Token ID2067
Feature activation+3.78e+00

Pos logit contributions
 forgot+0.045
 promise+0.039
ode+0.038
 way+0.037
 passengers+0.035
Neg logit contributions
 This-0.072
ore-0.065
 late-0.063
-0.062
ges-0.059
Token sway
Token ID20009
Feature activation+1.02e+01

Pos logit contributions
 This+0.049
ore+0.041
ires+0.039
 Today+0.038
 late+0.036
Neg logit contributions
 forgot-0.090
 way-0.077
 stayed-0.077
 promise-0.077
 forget-0.075
Tokening
Token ID278
Feature activation+3.55e+00

Pos logit contributions
 This+0.166
ore+0.138
 Playing+0.135
ires+0.131
 Today+0.130
Neg logit contributions
 forgot-0.199
 stayed-0.178
 head-0.169
 bit-0.168
 promise-0.165
Token to
Token ID284
Feature activation+1.43e+00

Pos logit contributions
 This+0.051
ore+0.043
ires+0.040
 Today+0.040
 late+0.039
Neg logit contributions
 forgot-0.080
 promise-0.068
 stayed-0.067
 way-0.067
 forget-0.065
Token the
Token ID262
Feature activation-4.76e+00

Pos logit contributions
 This+0.019
ore+0.016
ges+0.014
ires+0.014
 late+0.014
Neg logit contributions
 forgot-0.034
 promise-0.029
ode-0.029
 stayed-0.028
 way-0.028
Token music
Token ID2647
Feature activation+3.71e+00

Pos logit contributions
 forgot+0.080
 stayed+0.058
 hoped+0.056
 promise+0.055
ode+0.054
Neg logit contributions
 This-0.093
ore-0.088
 late-0.084
 Today-0.081
-0.080
Token.
Token ID13
Feature activation+4.86e+00

Pos logit contributions
 This+0.041
ore+0.034
 Today+0.030
 late+0.029
uttering+0.027
Neg logit contributions
 forgot-0.096
 promise-0.082
ode-0.081
 forget-0.079
 stayed-0.079
Token her
Token ID607
Feature activation-5.68e+00

Pos logit contributions
 This+0.077
ore+0.069
 Today+0.064
uttering+0.063
ires+0.063
Neg logit contributions
 forgot-0.095
 way-0.082
 stayed-0.080
 head-0.078
 promise-0.077
Token eyes
Token ID2951
Feature activation+4.69e+00

Pos logit contributions
 forgot+0.095
 stayed+0.068
 forget+0.067
ode+0.065
 promise+0.065
Neg logit contributions
 This-0.120
ore-0.108
 Today-0.103
ires-0.103
 late-0.099
Token and
Token ID290
Feature activation-4.71e+00

Pos logit contributions
 This+0.086
ore+0.076
ires+0.072
 Today+0.071
 late+0.070
Neg logit contributions
 forgot-0.086
 promise-0.070
 way-0.069
 stayed-0.069
 forget-0.067
Token took
Token ID1718
Feature activation+1.87e+00

Pos logit contributions
ode+0.059
 forgot+0.051
 promise+0.050
 passengers+0.048
 crew+0.045
Neg logit contributions
 This-0.094
 late-0.090
-0.086
ore-0.083
 early-0.079
Token deep
Token ID2769
Feature activation+2.94e+00

Pos logit contributions
 This+0.025
ore+0.020
 late+0.019
ires+0.018
 Today+0.018
Neg logit contributions
 forgot-0.046
 promise-0.039
 forget-0.038
 stayed-0.038
ode-0.038
Token breaths
Token ID45576
Feature activation+1.01e+01

Pos logit contributions
 This+0.069
ore+0.062
ires+0.060
 Today+0.060
uttering+0.059
Neg logit contributions
 forgot-0.039
 promise-0.030
 way-0.029
 stayed-0.029
 scar-0.027
Token.
Token ID13
Feature activation+4.38e+00

Pos logit contributions
 This+0.141
ore+0.119
ires+0.110
 Today+0.109
 late+0.108
Neg logit contributions
 forgot-0.233
 promise-0.198
 stayed-0.195
 way-0.194
 forget-0.190
Token Soon
Token ID15894
Feature activation-1.40e+00

Pos logit contributions
ore+0.045
 This+0.042
uttering+0.042
ires+0.040
ach+0.037
Neg logit contributions
 forgot-0.102
 way-0.089
 stayed-0.086
 head-0.085
 learned-0.085
Token,
Token ID11
Feature activation+1.37e+00

Pos logit contributions
 forgot+0.036
 promise+0.034
ode+0.033
 head+0.031
 forget+0.031
Neg logit contributions
 This-0.014
 late-0.010
ore-0.010
-0.009
 Today-0.009
Token she
Token ID673
Feature activation-7.09e+00

Pos logit contributions
 This+0.016
 late+0.013
ore+0.012
+0.011
 Today+0.011
Neg logit contributions
 forgot-0.034
 promise-0.032
ode-0.030
 stayed-0.029
 way-0.029
Token felt
Token ID2936
Feature activation-7.36e-01

Pos logit contributions
 promise+0.096
ode+0.093
 passengers+0.090
 way+0.088
 forgot+0.084
Neg logit contributions
-0.126
ore-0.116
 This-0.115
 late-0.108
to-0.101
Token he
Token ID339
Feature activation-5.94e+00

Pos logit contributions
 forgot+0.027
 promise+0.024
ode+0.023
 stayed+0.022
 forget+0.022
Neg logit contributions
 This-0.017
ore-0.014
 late-0.014
ires-0.013
 Today-0.013
Token thought
Token ID1807
Feature activation+4.45e+00

Pos logit contributions
 forgot+0.082
ode+0.081
 promise+0.075
 passengers+0.075
 scar+0.074
Neg logit contributions
 This-0.119
ore-0.103
-0.102
 late-0.098
 Today-0.093
Token it
Token ID340
Feature activation-1.21e+00

Pos logit contributions
 This+0.060
ore+0.048
 late+0.044
 Today+0.044
ires+0.043
Neg logit contributions
 forgot-0.107
 promise-0.093
 forget-0.089
ode-0.089
 stayed-0.088
Token was
Token ID373
Feature activation-2.02e+00

Pos logit contributions
 forgot+0.018
 promise+0.015
ode+0.015
 passengers+0.014
 forget+0.014
Neg logit contributions
 This-0.026
ore-0.022
 Today-0.021
 late-0.021
-0.021
Token too
Token ID1165
Feature activation-9.63e-01

Pos logit contributions
 forgot+0.039
 promise+0.033
ode+0.031
 stayed+0.031
 forget+0.031
Neg logit contributions
 This-0.035
 late-0.030
ore-0.029
ires-0.028
 Today-0.028
Token sm
Token ID895
Feature activation+1.01e+01

Pos logit contributions
 forgot+0.016
 way+0.012
 bit+0.012
 promise+0.012
 stayed+0.011
Neg logit contributions
 This-0.020
ore-0.018
ges-0.018
uttering-0.018
 Today-0.018
Tokenelly
Token ID6148
Feature activation+5.09e+00

Pos logit contributions
 This+0.119
 Today+0.090
 outer+0.084
 Do+0.080
overed+0.080
Neg logit contributions
 forgot-0.222
ode-0.202
 bit-0.195
 regretted-0.191
 stayed-0.190
Token.
Token ID13
Feature activation+4.16e+00

Pos logit contributions
 This+0.079
uttering+0.070
ires+0.068
ore+0.067
 Today+0.066
Neg logit contributions
 forgot-0.105
 way-0.092
 stayed-0.089
 promise-0.087
 bit-0.085
TokenJane
Token ID41083
Feature activation-6.34e+00

Pos logit contributions
 This+0.050
ore+0.045
uttering+0.043
ires+0.042
 late+0.039
Neg logit contributions
 forgot-0.099
 promise-0.083
 way-0.083
 stayed-0.083
 forget-0.081
Token said
Token ID531
Feature activation+3.07e+00

Pos logit contributions
 passengers+0.092
ode+0.086
 captain+0.082
 way+0.081
 promise+0.081
Neg logit contributions
 This-0.112
ore-0.100
-0.099
 late-0.095
to-0.092
Token,
Token ID11
Feature activation+1.42e+00

Pos logit contributions
 This+0.045
ore+0.041
ires+0.041
 Today+0.039
 late+0.039
Neg logit contributions
 forgot-0.067
 stayed-0.057
 promise-0.055
 way-0.054
 learned-0.053
Token play
Token ID711
Feature activation+5.04e+00

Pos logit contributions
 forgot+0.092
 regretted+0.075
 sighed+0.071
 promise+0.069
 stayed+0.069
Neg logit contributions
 This-0.096
ore-0.077
 Today-0.076
ires-0.072
-0.071
Token tug
Token ID27762
Feature activation+6.86e+00

Pos logit contributions
 This+0.081
ore+0.070
ires+0.066
 Today+0.066
 late+0.065
Neg logit contributions
 forgot-0.105
 promise-0.089
 stayed-0.087
 way-0.086
 forget-0.084
Token-
Token ID12
Feature activation+2.22e+00

Pos logit contributions
 This+0.097
ore+0.078
 Today+0.076
uttering+0.074
ires+0.074
Neg logit contributions
 forgot-0.158
 promise-0.134
 stayed-0.132
 way-0.132
 bit-0.128
Tokenof
Token ID1659
Feature activation+2.64e+00

Pos logit contributions
 This+0.038
 Today+0.033
ore+0.033
ires+0.033
 late+0.032
Neg logit contributions
 forgot-0.042
 stayed-0.034
 promise-0.034
 way-0.034
 forget-0.033
Token-
Token ID12
Feature activation+2.06e+00

Pos logit contributions
 This+0.041
ore+0.035
 late+0.034
 Today+0.034
uttering+0.033
Neg logit contributions
 forgot-0.055
 promise-0.047
 stayed-0.046
 way-0.046
 bit-0.044
Tokenwar
Token ID5767
Feature activation+1.01e+01

Pos logit contributions
 This+0.037
 Today+0.032
ore+0.032
ires+0.031
 late+0.031
Neg logit contributions
 forgot-0.039
 stayed-0.031
 promise-0.031
 way-0.031
 forget-0.030
Token!"
Token ID2474
Feature activation+4.05e+00

Pos logit contributions
 This+0.134
ore+0.114
ires+0.109
 Today+0.109
uttering+0.108
Neg logit contributions
 forgot-0.229
 stayed-0.195
 promise-0.194
 way-0.193
 bit-0.187
Token
Token ID198
Feature activation+5.59e+00

Pos logit contributions
 This+0.034
ore+0.022
 late+0.020
 Today+0.018
+0.018
Neg logit contributions
 forgot-0.120
 promise-0.108
ode-0.106
 stayed-0.105
 forget-0.104
Token
Token ID198
Feature activation+4.51e+00

Pos logit contributions
 This+0.069
uttering+0.065
ires+0.061
ore+0.057
ocol+0.056
Neg logit contributions
 forgot-0.125
 way-0.108
 promise-0.107
 learned-0.106
 stayed-0.103
TokenThe
Token ID464
Feature activation-6.00e+00

Pos logit contributions
 This+0.060
 late+0.049
ore+0.046
 Playing+0.043
 Today+0.043
Neg logit contributions
 forgot-0.106
 promise-0.092
 way-0.091
 stayed-0.089
ode-0.089
Token birds
Token ID10087
Feature activation-3.43e+00

Pos logit contributions
 forgot+0.103
ode+0.080
 promise+0.078
 regretted+0.075
 forget+0.075
Neg logit contributions
 This-0.117
-0.104
uttering-0.102
ires-0.101
 Today-0.101
Token new
Token ID649
Feature activation-2.78e+00

Pos logit contributions
 forgot+0.065
 stayed+0.052
 promise+0.051
ode+0.050
 forget+0.050
Neg logit contributions
 This-0.067
ore-0.059
 Today-0.056
 late-0.055
ires-0.054
Token word
Token ID1573
Feature activation+3.04e+00

Pos logit contributions
 forgot+0.051
 stayed+0.040
 promise+0.039
 forget+0.038
ode+0.038
Neg logit contributions
 This-0.054
ore-0.047
 Today-0.045
 late-0.044
ires-0.043
Token,
Token ID11
Feature activation-3.33e-01

Pos logit contributions
 This+0.039
ore+0.033
ires+0.030
 late+0.030
 Today+0.030
Neg logit contributions
 forgot-0.072
 promise-0.062
 stayed-0.062
 way-0.061
 forget-0.060
Token '
Token ID705
Feature activation+1.74e+00

Pos logit contributions
 forgot+0.006
 promise+0.005
 stayed+0.005
 way+0.005
 forget+0.005
Neg logit contributions
 This-0.006
ore-0.005
 late-0.005
ires-0.005
 Today-0.005
Tokenemer
Token ID24677
Feature activation+3.98e+00

Pos logit contributions
 This+0.028
ore+0.024
ires+0.024
 Today+0.024
uttering+0.022
Neg logit contributions
 forgot-0.035
 stayed-0.030
 promise-0.029
 bit-0.029
 forget-0.028
Tokengency
Token ID4949
Feature activation+9.98e+00

Pos logit contributions
 This+0.075
ires+0.068
 late+0.067
 Today+0.065
uttering+0.064
Neg logit contributions
 forgot-0.069
 promise-0.058
 stayed-0.056
 bit-0.054
ode-0.054
Token',
Token ID3256
Feature activation+1.80e+00

Pos logit contributions
 This+0.122
uttering+0.114
ires+0.107
 Today+0.106
ore+0.105
Neg logit contributions
 forgot-0.217
 promise-0.185
 stayed-0.184
 learned-0.183
 way-0.183
Token so
Token ID523
Feature activation+8.72e-01

Pos logit contributions
 This+0.027
ore+0.022
 late+0.021
 Today+0.021
ires+0.020
Neg logit contributions
 forgot-0.040
 promise-0.034
ode-0.033
 way-0.033
 stayed-0.033
Token she
Token ID673
Feature activation-6.81e+00

Pos logit contributions
 This+0.012
ore+0.010
 late+0.009
 Today+0.009
ires+0.009
Neg logit contributions
 forgot-0.020
 promise-0.017
ode-0.017
 stayed-0.017
 way-0.017
Token whispered
Token ID25029
Feature activation+6.63e+00

Pos logit contributions
ode+0.085
 way+0.077
 promise+0.076
 forgot+0.076
 passengers+0.072
Neg logit contributions
 This-0.126
 late-0.116
ore-0.115
-0.109
?-0.109
Token the
Token ID262
Feature activation-4.96e+00

Pos logit contributions
 This+0.095
ore+0.085
 Today+0.083
ires+0.082
 late+0.079
Neg logit contributions
 forgot-0.141
 stayed-0.123
 promise-0.118
 way-0.117
 head-0.116
Token feet
Token ID3625
Feature activation+4.55e+00

Pos logit contributions
 forgot+0.068
 promise+0.047
 stayed+0.047
ode+0.045
 way+0.044
Neg logit contributions
 This-0.110
ore-0.099
 Today-0.095
uttering-0.094
ires-0.093
Token.
Token ID13
Feature activation+4.11e+00

Pos logit contributions
 This+0.057
ore+0.047
 late+0.043
 Today+0.043
uttering+0.042
Neg logit contributions
 forgot-0.110
 promise-0.096
 stayed-0.092
 way-0.092
 forget-0.091
Token She
Token ID1375
Feature activation-7.57e+00

Pos logit contributions
 This+0.042
ore+0.038
uttering+0.035
 late+0.035
ires+0.034
Neg logit contributions
 forgot-0.104
 way-0.090
 stayed-0.088
 promise-0.087
 forget-0.087
Token took
Token ID1718
Feature activation+1.73e+00

Pos logit contributions
ode+0.115
 promise+0.104
 passengers+0.094
 way+0.094
 forgot+0.092
Neg logit contributions
 This-0.123
-0.117
ore-0.114
 late-0.113
-0.105
Token big
Token ID1263
Feature activation+2.49e-01

Pos logit contributions
 This+0.022
ore+0.018
 late+0.016
 Today+0.016
+0.016
Neg logit contributions
 forgot-0.043
 promise-0.037
 forget-0.036
ode-0.036
 stayed-0.035
Token breaths
Token ID45576
Feature activation+9.93e+00

Pos logit contributions
 This+0.005
ore+0.004
 Today+0.004
 late+0.004
+0.004
Neg logit contributions
 forgot-0.004
 promise-0.003
 stayed-0.003
 forget-0.003
ode-0.003
Token of
Token ID286
Feature activation-1.23e+00

Pos logit contributions
 This+0.164
ore+0.144
 late+0.136
 Today+0.133
ires+0.132
Neg logit contributions
 forgot-0.204
 promise-0.171
 stayed-0.165
 forget-0.163
 way-0.163
Token fresh
Token ID4713
Feature activation+1.52e+00

Pos logit contributions
 forgot+0.030
 promise+0.024
ode+0.024
 stayed+0.024
 forget+0.023
Neg logit contributions
 This-0.016
ore-0.014
 late-0.013
 Today-0.013
ires-0.013
Token air
Token ID1633
Feature activation+5.11e+00

Pos logit contributions
 This+0.038
ore+0.035
uttering+0.034
ires+0.034
 late+0.034
Neg logit contributions
 forgot-0.017
 way-0.013
 stayed-0.012
 promise-0.012
 scar-0.011
Token and
Token ID290
Feature activation-3.89e+00

Pos logit contributions
 This+0.083
ore+0.072
ires+0.067
 Today+0.067
 late+0.066
Neg logit contributions
 forgot-0.106
 promise-0.088
 stayed-0.087
 way-0.087
 forget-0.084
Token her
Token ID607
Feature activation-6.48e+00

Pos logit contributions
 forgot+0.062
 promise+0.057
ode+0.056
 captain+0.050
 crew+0.049
Neg logit contributions
 This-0.072
 late-0.066
ore-0.063
-0.059
 Today-0.059
Token a
Token ID257
Feature activation-3.26e+00

Pos logit contributions
 This+0.050
ore+0.042
ires+0.042
 Playing+0.039
 Today+0.039
Neg logit contributions
 forgot-0.054
 way-0.049
 stayed-0.048
 promise-0.048
 head-0.047
Token key
Token ID1994
Feature activation+3.45e+00

Pos logit contributions
 forgot+0.059
 stayed+0.047
ode+0.046
 hoped+0.044
 heads+0.043
Neg logit contributions
 This-0.059
 late-0.052
 Today-0.052
ore-0.052
-0.048
Token and
Token ID290
Feature activation-4.11e+00

Pos logit contributions
 This+0.047
ore+0.040
ires+0.037
 Today+0.037
 late+0.036
Neg logit contributions
 forgot-0.080
 promise-0.069
 stayed-0.068
 way-0.067
 forget-0.066
Token tried
Token ID3088
Feature activation+5.89e+00

Pos logit contributions
 forgot+0.072
ode+0.064
 promise+0.062
 way+0.058
 forget+0.057
Neg logit contributions
 This-0.075
 late-0.062
ore-0.060
-0.058
 Today-0.057
Token to
Token ID284
Feature activation-4.89e-01

Pos logit contributions
 This+0.070
ore+0.057
ires+0.051
 Today+0.051
 late+0.051
Neg logit contributions
 forgot-0.149
 promise-0.129
 stayed-0.127
 way-0.126
 forget-0.124
Token cover
Token ID3002
Feature activation+9.92e+00

Pos logit contributions
 forgot+0.009
 regretted+0.008
ode+0.008
 sighed+0.007
 learned+0.007
Neg logit contributions
 This-0.008
ore-0.007
 late-0.007
 Today-0.006
ires-0.006
Token the
Token ID262
Feature activation-4.43e+00

Pos logit contributions
 This+0.152
ore+0.131
 Today+0.122
 late+0.121
uttering+0.121
Neg logit contributions
 forgot-0.211
 promise-0.179
 way-0.177
 stayed-0.177
 forget-0.171
Token drawer
Token ID33451
Feature activation+5.06e+00

Pos logit contributions
 forgot+0.077
 stayed+0.055
 forget+0.053
 learned+0.053
 hoped+0.052
Neg logit contributions
 This-0.085
ore-0.076
 late-0.075
ires-0.073
 Today-0.072
Token with
Token ID351
Feature activation-4.02e-01

Pos logit contributions
 This+0.073
ore+0.062
 late+0.057
 Today+0.057
ires+0.057
Neg logit contributions
 forgot-0.114
 promise-0.097
 stayed-0.095
 way-0.094
 forget-0.093
Token it
Token ID340
Feature activation+6.42e-01

Pos logit contributions
 forgot+0.009
 promise+0.008
ode+0.008
 forget+0.008
 stayed+0.007
Neg logit contributions
 This-0.006
 late-0.005
ore-0.005
ires-0.004
 Today-0.004
Token,
Token ID11
Feature activation+2.93e-01

Pos logit contributions
 This+0.008
ore+0.007
ires+0.006
 Today+0.006
 late+0.006
Neg logit contributions
 forgot-0.016
 promise-0.014
 stayed-0.013
 way-0.013
 forget-0.013
Token
Token ID26391
Feature activation+3.56e+00

Pos logit contributions
ires+0.015
uttering+0.015
ges+0.014
 This+0.014
 late+0.014
Neg logit contributions
 forgot-0.023
 promise-0.020
 stayed-0.019
 learned-0.019
 way-0.019
Token˜
Token ID41185
Feature activation+3.52e+00

Pos logit contributions
ires+0.044
 This+0.042
uttering+0.041
 late+0.040
ore+0.040
Neg logit contributions
 forgot-0.082
 way-0.066
 forget-0.066
 stayed-0.065
 promise-0.065
TokenS
Token ID50
Feature activation+1.95e-01

Pos logit contributions
 This+0.049
ires+0.042
 late+0.042
ore+0.042
uttering+0.042
Neg logit contributions
 forgot-0.077
 promise-0.066
 stayed-0.066
 way-0.065
 head-0.064
Tokenail
Token ID603
Feature activation-2.24e+00

Pos logit contributions
 This+0.004
 late+0.003
ore+0.003
uttering+0.003
ires+0.003
Neg logit contributions
 forgot-0.003
 promise-0.003
 stayed-0.002
 way-0.002
ode-0.002
Tokenors
Token ID669
Feature activation+1.33e-01

Pos logit contributions
 forgot+0.046
 promise+0.039
 stayed+0.038
 way+0.038
 forget+0.037
Neg logit contributions
 This-0.037
ore-0.031
 Today-0.029
 late-0.029
ires-0.029
Token Wanted
Token ID41536
Feature activation+9.90e+00

Pos logit contributions
 This+0.002
ore+0.002
 Today+0.002
ires+0.002
+0.002
Neg logit contributions
 forgot-0.002
 promise-0.002
 way-0.002
 stayed-0.002
 forget-0.002
Tokenâ
Token ID22940
Feature activation+4.25e-01

Pos logit contributions
 This+0.137
ore+0.118
ires+0.117
uttering+0.115
 late+0.113
Neg logit contributions
 forgot-0.207
 stayed-0.185
 way-0.176
 promise-0.176
 passengers-0.174
Token
Token ID26391
Feature activation+3.55e+00

Pos logit contributions
 This+0.008
ires+0.007
ore+0.007
uttering+0.007
 late+0.007
Neg logit contributions
 forgot-0.007
 promise-0.006
 stayed-0.006
 way-0.006
 forget-0.006
Token
Token ID8151
Feature activation+7.07e+00

Pos logit contributions
 This+0.049
ires+0.049
ore+0.045
 late+0.045
uttering+0.044
Neg logit contributions
 forgot-0.077
 way-0.061
 stayed-0.061
 forget-0.061
 promise-0.061
Token.
Token ID13
Feature activation+4.25e+00

Pos logit contributions
 This+0.104
ires+0.098
uttering+0.095
 late+0.094
ore+0.090
Neg logit contributions
 forgot-0.142
 way-0.115
 promise-0.114
 stayed-0.114
 learned-0.108
Token Do
Token ID2141
Feature activation+2.51e+00

Pos logit contributions
 This+0.050
ore+0.048
uttering+0.047
ires+0.047
 late+0.042
Neg logit contributions
 forgot-0.095
 stayed-0.081
 way-0.080
 promise-0.080
 forget-0.079
Token she
Token ID673
Feature activation-5.96e+00

Pos logit contributions
ode+0.058
 passengers+0.053
 forgot+0.053
 scar+0.049
 promise+0.048
Neg logit contributions
 This-0.079
 That-0.064
 Today-0.063
-0.061
ore-0.060
Token had
Token ID550
Feature activation-1.05e+00

Pos logit contributions
 forgot+0.073
ode+0.068
 way+0.060
 promise+0.060
 passengers+0.059
Neg logit contributions
 This-0.131
ore-0.118
-0.115
 late-0.114
 Today-0.109
Token to
Token ID284
Feature activation-8.14e-01

Pos logit contributions
 forgot+0.018
 promise+0.015
ode+0.015
 forget+0.014
 way+0.014
Neg logit contributions
 This-0.020
 late-0.017
ore-0.017
-0.016
uttering-0.016
Token go
Token ID467
Feature activation+3.82e+00

Pos logit contributions
 forgot+0.014
ode+0.011
 regretted+0.011
 scar+0.010
 stayed+0.010
Neg logit contributions
 This-0.016
 late-0.013
 Today-0.013
ore-0.013
-0.012
Token to
Token ID284
Feature activation+2.00e+00

Pos logit contributions
 This+0.063
ore+0.054
ires+0.052
 Today+0.050
uttering+0.050
Neg logit contributions
 forgot-0.078
 promise-0.066
 way-0.065
 stayed-0.064
 forget-0.064
Token bed
Token ID3996
Feature activation+9.89e+00

Pos logit contributions
 This+0.032
ore+0.028
ires+0.026
uttering+0.026
 Today+0.026
Neg logit contributions
 forgot-0.042
 promise-0.035
 way-0.035
 stayed-0.034
 forget-0.034
Token with
Token ID351
Feature activation+1.09e+00

Pos logit contributions
 This+0.146
ore+0.122
ires+0.117
 Today+0.117
 Playing+0.113
Neg logit contributions
 forgot-0.219
 way-0.184
 stayed-0.183
 promise-0.181
 head-0.177
Token no
Token ID645
Feature activation-2.79e+00

Pos logit contributions
 This+0.014
ore+0.012
 late+0.011
 Today+0.010
ires+0.010
Neg logit contributions
 forgot-0.027
 promise-0.023
 stayed-0.022
ode-0.022
 forget-0.022
Token chalk
Token ID30860
Feature activation+5.99e+00

Pos logit contributions
 forgot+0.051
 stayed+0.038
ode+0.037
 forget+0.037
 promise+0.036
Neg logit contributions
 This-0.052
 Today-0.048
 late-0.047
ore-0.047
ires-0.044
Token.
Token ID13
Feature activation+3.93e+00

Pos logit contributions
 This+0.073
ore+0.060
 late+0.055
 Today+0.054
ires+0.054
Neg logit contributions
 forgot-0.147
 promise-0.128
 stayed-0.124
 way-0.124
 forget-0.123
Token<|endoftext|>
Token ID50256
Feature activation+7.04e+00

Pos logit contributions
ore+0.040
 This+0.040
uttering+0.040
ires+0.037
ges+0.033
Neg logit contributions
 forgot-0.095
 way-0.081
 promise-0.080
 forget-0.079
 stayed-0.079
Token to
Token ID284
Feature activation-1.70e+00

Pos logit contributions
 This+0.043
ore+0.035
ires+0.033
 Today+0.032
 late+0.031
Neg logit contributions
 forgot-0.089
 promise-0.077
 way-0.076
 stayed-0.076
 forget-0.074
Token grow
Token ID1663
Feature activation+5.43e+00

Pos logit contributions
 forgot+0.027
ode+0.021
 stayed+0.020
 promise+0.020
 way+0.020
Neg logit contributions
 This-0.034
ore-0.029
 Today-0.028
 late-0.028
-0.027
Tokenl
Token ID75
Feature activation+4.26e+00

Pos logit contributions
 This+0.093
ore+0.080
 Today+0.076
ires+0.074
uttering+0.073
Neg logit contributions
 forgot-0.109
 promise-0.090
 stayed-0.089
 way-0.089
 forget-0.086
Token and
Token ID290
Feature activation-3.16e+00

Pos logit contributions
 This+0.062
ore+0.051
 Today+0.049
ires+0.048
 late+0.047
Neg logit contributions
 forgot-0.093
 stayed-0.080
 promise-0.079
 way-0.079
ode-0.077
Token sn
Token ID3013
Feature activation+4.58e+00

Pos logit contributions
 forgot+0.052
ode+0.043
 promise+0.042
 way+0.039
 stayed+0.039
Neg logit contributions
 This-0.062
ore-0.052
 late-0.051
 Today-0.050
 Do-0.049
Tokenarl
Token ID7063
Feature activation+9.89e+00

Pos logit contributions
 This+0.070
 Today+0.059
 Do+0.056
ires+0.055
 late+0.054
Neg logit contributions
 forgot-0.094
 stayed-0.083
 promise-0.082
 learned-0.077
 bit-0.075
Token to
Token ID284
Feature activation+1.81e+00

Pos logit contributions
 This+0.131
ore+0.107
 Today+0.102
 late+0.098
uttering+0.096
Neg logit contributions
 forgot-0.234
 way-0.201
 promise-0.198
 stayed-0.195
 learned-0.188
Token try
Token ID1949
Feature activation+5.54e+00

Pos logit contributions
 This+0.032
ore+0.027
 late+0.027
 Today+0.026
ires+0.025
Neg logit contributions
 forgot-0.035
ode-0.029
 promise-0.028
 stayed-0.028
 way-0.027
Token and
Token ID290
Feature activation-3.19e+00

Pos logit contributions
 This+0.085
ore+0.074
ires+0.072
 Today+0.070
uttering+0.068
Neg logit contributions
 forgot-0.117
 way-0.101
 promise-0.099
 stayed-0.098
 forget-0.094
Token scare
Token ID19437
Feature activation+4.62e+00

Pos logit contributions
 forgot+0.053
ode+0.043
 promise+0.041
 stayed+0.040
 regretted+0.040
Neg logit contributions
 This-0.061
ore-0.052
 late-0.051
 Today-0.048
 Do-0.048
Token her
Token ID607
Feature activation-3.25e+00

Pos logit contributions
 This+0.074
ore+0.064
ges+0.058
 late+0.057
+0.056
Neg logit contributions
 forgot-0.100
 promise-0.084
ode-0.084
 forget-0.081
 stayed-0.080
Token you
Token ID345
Feature activation-1.35e+00

Pos logit contributions
 This+0.084
ore+0.074
ires+0.070
 Today+0.070
uttering+0.070
Neg logit contributions
 forgot-0.108
 promise-0.092
 stayed-0.090
 forget-0.088
 way-0.088
Token.
Token ID13
Feature activation+2.53e+00

Pos logit contributions
 forgot+0.033
 promise+0.028
 way+0.028
 stayed+0.027
 forget+0.027
Neg logit contributions
 This-0.018
ore-0.015
ires-0.014
 late-0.013
 Today-0.013
Token It
Token ID632
Feature activation-3.12e+00

Pos logit contributions
 This+0.024
uttering+0.021
ore+0.021
ires+0.020
 late+0.020
Neg logit contributions
 forgot-0.066
 promise-0.058
 stayed-0.057
 forget-0.056
 way-0.055
Token is
Token ID318
Feature activation-2.03e+00

Pos logit contributions
 forgot+0.070
ode+0.064
 passengers+0.062
 scar+0.062
 forget+0.060
Neg logit contributions
 This-0.042
ore-0.034
-0.032
 That-0.030
 late-0.030
Token too
Token ID1165
Feature activation-1.27e+00

Pos logit contributions
 forgot+0.041
ode+0.035
 promise+0.035
 forget+0.033
 stayed+0.033
Neg logit contributions
 This-0.032
 late-0.030
ires-0.025
ore-0.025
 Today-0.025
Token sm
Token ID895
Feature activation+9.88e+00

Pos logit contributions
 forgot+0.021
 way+0.017
 promise+0.017
 bit+0.017
 stayed+0.016
Neg logit contributions
 This-0.026
ore-0.023
ges-0.023
ires-0.023
uttering-0.022
Tokenelly
Token ID6148
Feature activation+5.25e+00

Pos logit contributions
 This+0.106
 Today+0.074
used+0.070
uttering+0.068
overed+0.068
Neg logit contributions
 forgot-0.227
ode-0.205
 bit-0.201
 stayed-0.199
 learned-0.197
Token for
Token ID329
Feature activation+2.68e+00

Pos logit contributions
 This+0.088
uttering+0.077
ires+0.074
ore+0.074
 Today+0.072
Neg logit contributions
 forgot-0.100
 way-0.087
 stayed-0.086
 promise-0.085
 bit-0.083
Token us
Token ID514
Feature activation-5.67e-01

Pos logit contributions
 This+0.049
ore+0.044
 Today+0.041
ires+0.041
 late+0.041
Neg logit contributions
 forgot-0.050
 promise-0.041
 stayed-0.040
 way-0.040
 forget-0.039
Token.
Token ID13
Feature activation+3.59e+00

Pos logit contributions
 forgot+0.014
 promise+0.012
 stayed+0.012
 way+0.012
 forget+0.011
Neg logit contributions
 This-0.007
ore-0.006
ires-0.006
 Today-0.006
 late-0.005
Token We
Token ID775
Feature activation-4.40e+00

Pos logit contributions
uttering+0.036
 This+0.035
ore+0.033
ires+0.031
 late+0.030
Neg logit contributions
 forgot-0.087
 promise-0.077
 stayed-0.076
 forget-0.074
 bit-0.072
Token her
Token ID607
Feature activation-5.10e+00

Pos logit contributions
 This+0.026
ore+0.021
 late+0.020
 Today+0.019
ires+0.019
Neg logit contributions
 forgot-0.045
 promise-0.038
 stayed-0.038
 forget-0.037
ode-0.037
Token cr
Token ID1067
Feature activation+5.27e+00

Pos logit contributions
 forgot+0.080
 stayed+0.060
ode+0.058
 promise+0.057
 forget+0.057
Neg logit contributions
 This-0.111
ore-0.098
 Today-0.094
ires-0.092
 late-0.092
Tokenay
Token ID323
Feature activation+6.96e-01

Pos logit contributions
 This+0.055
ore+0.044
 late+0.040
 Today+0.039
ires+0.038
Neg logit contributions
 forgot-0.137
 promise-0.120
 stayed-0.118
 way-0.117
ode-0.116
Tokenons
Token ID684
Feature activation+2.93e+00

Pos logit contributions
 This+0.011
ore+0.010
 late+0.009
 Today+0.009
ires+0.009
Neg logit contributions
 forgot-0.014
 promise-0.012
 stayed-0.012
 way-0.012
 forget-0.012
Token to
Token ID284
Feature activation-1.76e+00

Pos logit contributions
 This+0.035
ore+0.028
 Today+0.025
 late+0.025
ires+0.025
Neg logit contributions
 forgot-0.074
 promise-0.064
 stayed-0.063
 way-0.062
 forget-0.062
Token scrib
Token ID44661
Feature activation+9.87e+00

Pos logit contributions
 forgot+0.029
 regretted+0.022
ode+0.022
 stayed+0.022
 way+0.022
Neg logit contributions
 This-0.037
ore-0.031
 late-0.030
ires-0.030
 Today-0.029
Tokenble
Token ID903
Feature activation+5.35e+00

Pos logit contributions
 This+0.213
 Today+0.187
ore+0.183
 Do+0.178
 Playing+0.172
Neg logit contributions
 forgot-0.142
 head-0.122
 stayed-0.118
 captain-0.113
 h-0.110
Token on
Token ID319
Feature activation+2.67e+00

Pos logit contributions
 This+0.078
uttering+0.067
 Today+0.066
ore+0.066
 Playing+0.064
Neg logit contributions
 forgot-0.109
 way-0.096
 promise-0.095
 stayed-0.094
 bit-0.093
Token the
Token ID262
Feature activation-4.67e+00

Pos logit contributions
 This+0.041
ore+0.036
 Today+0.033
 late+0.033
ires+0.033
Neg logit contributions
 forgot-0.057
 promise-0.048
 way-0.047
 stayed-0.047
 forget-0.046
Token wall
Token ID3355
Feature activation+5.20e+00

Pos logit contributions
 forgot+0.079
 stayed+0.058
 regretted+0.055
 hoped+0.053
 promise+0.052
Neg logit contributions
 This-0.101
ore-0.085
 late-0.082
ires-0.081
 Today-0.081
Token.
Token ID13
Feature activation+4.76e+00

Pos logit contributions
 This+0.060
ore+0.048
ires+0.044
 Today+0.043
 late+0.043
Neg logit contributions
 forgot-0.132
 promise-0.114
 stayed-0.113
 way-0.112
 forget-0.110
Token could
Token ID714
Feature activation+1.25e+00

Pos logit contributions
ode+0.111
 promise+0.106
 forget+0.101
 forgot+0.097
 forehead+0.091
Neg logit contributions
-0.107
 This-0.104
ore-0.099
 late-0.094
-0.088
Token take
Token ID1011
Feature activation+2.00e+00

Pos logit contributions
 This+0.022
ore+0.019
 late+0.018
 Today+0.018
ires+0.017
Neg logit contributions
 forgot-0.023
 regretted-0.019
ode-0.019
 way-0.019
 promise-0.019
Token lots
Token ID6041
Feature activation+2.12e+00

Pos logit contributions
 This+0.029
ore+0.023
 late+0.021
+0.021
 Today+0.020
Neg logit contributions
 forgot-0.048
 promise-0.042
 forget-0.040
ode-0.039
 stayed-0.039
Token of
Token ID286
Feature activation-1.02e+00

Pos logit contributions
 This+0.031
ore+0.027
 late+0.024
ires+0.024
 Today+0.024
Neg logit contributions
 forgot-0.048
 promise-0.041
 stayed-0.040
 way-0.039
 forget-0.039
Token deep
Token ID2769
Feature activation+2.83e+00

Pos logit contributions
 forgot+0.017
 promise+0.013
 forget+0.013
 stayed+0.012
ode+0.012
Neg logit contributions
 This-0.021
ore-0.020
-0.019
 late-0.018
ires-0.018
Token breaths
Token ID45576
Feature activation+9.86e+00

Pos logit contributions
 This+0.065
ore+0.059
 late+0.056
ires+0.056
 Today+0.056
Neg logit contributions
 forgot-0.040
 promise-0.030
 stayed-0.029
 way-0.029
 forget-0.028
Token and
Token ID290
Feature activation-3.45e+00

Pos logit contributions
 This+0.168
ore+0.144
 Today+0.138
ires+0.137
 late+0.133
Neg logit contributions
 forgot-0.195
 stayed-0.160
 way-0.160
 promise-0.159
 forget-0.154
Token get
Token ID651
Feature activation+1.34e+00

Pos logit contributions
 forgot+0.058
ode+0.052
 promise+0.047
 regretted+0.047
atha+0.045
Neg logit contributions
 This-0.060
ore-0.051
 late-0.051
 Today-0.051
 Do-0.047
Token lots
Token ID6041
Feature activation+6.86e-01

Pos logit contributions
 This+0.021
ore+0.019
 late+0.018
ires+0.016
+0.016
Neg logit contributions
 forgot-0.028
 promise-0.023
ode-0.023
 forget-0.023
 way-0.023
Token of
Token ID286
Feature activation-1.67e+00

Pos logit contributions
 This+0.010
ore+0.009
 late+0.008
ires+0.008
 Today+0.008
Neg logit contributions
 forgot-0.015
 promise-0.013
 stayed-0.013
 way-0.013
 forget-0.012
Token oxygen
Token ID11863
Feature activation+4.36e+00

Pos logit contributions
 forgot+0.027
 forget+0.020
ode+0.020
 stayed+0.020
 promise+0.020
Neg logit contributions
 This-0.035
ore-0.033
 late-0.032
-0.031
 Today-0.030
Token play
Token ID711
Feature activation+4.94e+00

Pos logit contributions
 forgot+0.092
 regretted+0.077
 sighed+0.072
 stayed+0.071
 way+0.070
Neg logit contributions
 This-0.086
ore-0.070
 Today-0.070
 late-0.063
-0.062
Token tug
Token ID27762
Feature activation+6.86e+00

Pos logit contributions
 This+0.078
ore+0.067
ires+0.062
 Today+0.062
 late+0.062
Neg logit contributions
 forgot-0.105
 promise-0.088
 stayed-0.086
 way-0.086
 forget-0.084
Token-
Token ID12
Feature activation+2.16e+00

Pos logit contributions
 This+0.099
ore+0.080
 Today+0.078
uttering+0.077
ires+0.077
Neg logit contributions
 forgot-0.154
 promise-0.131
 stayed-0.129
 way-0.128
 bit-0.126
Tokenof
Token ID1659
Feature activation+2.43e+00

Pos logit contributions
 This+0.038
ires+0.034
 Today+0.034
ore+0.033
uttering+0.032
Neg logit contributions
 forgot-0.040
 stayed-0.032
 promise-0.032
 way-0.032
 forget-0.031
Token-
Token ID12
Feature activation+1.91e+00

Pos logit contributions
 This+0.040
ore+0.035
 late+0.033
 Today+0.033
ires+0.033
Neg logit contributions
 forgot-0.049
 promise-0.041
 stayed-0.040
 way-0.040
 forget-0.039
Tokenwar
Token ID5767
Feature activation+9.85e+00

Pos logit contributions
 This+0.035
ires+0.031
 Today+0.031
ore+0.030
uttering+0.030
Neg logit contributions
 forgot-0.034
 stayed-0.027
 promise-0.027
 way-0.027
 forget-0.026
Token,"
Token ID553
Feature activation+2.48e+00

Pos logit contributions
 This+0.129
ore+0.108
ires+0.102
 Today+0.100
uttering+0.100
Neg logit contributions
 forgot-0.229
 promise-0.197
 stayed-0.195
 way-0.194
 forget-0.188
Token said
Token ID531
Feature activation+3.86e+00

Pos logit contributions
 This+0.056
ore+0.049
 late+0.049
+0.048
 Today+0.045
Neg logit contributions
 forgot-0.036
ode-0.032
 promise-0.028
 way-0.028
 forget-0.027
Token the
Token ID262
Feature activation-5.06e+00

Pos logit contributions
 This+0.063
ore+0.055
ires+0.052
 Today+0.052
uttering+0.051
Neg logit contributions
 forgot-0.079
 promise-0.066
 stayed-0.065
 way-0.064
 forget-0.062
Token oct
Token ID19318
Feature activation-2.18e-01

Pos logit contributions
 forgot+0.090
 stayed+0.070
 promise+0.068
 forget+0.066
ode+0.066
Neg logit contributions
 This-0.100
ore-0.090
-0.085
 Today-0.083
ires-0.081
Tokenopus
Token ID25790
Feature activation-1.36e+00

Pos logit contributions
 forgot+0.004
 promise+0.003
ode+0.003
 stayed+0.003
 bit+0.003
Neg logit contributions
 This-0.004
 late-0.004
 Today-0.004
ires-0.003
uttering-0.003
Token her
Token ID607
Feature activation-5.04e+00

Pos logit contributions
 forgot+0.082
 promise+0.072
ode+0.070
 way+0.067
 stayed+0.067
Neg logit contributions
 This-0.085
 late-0.074
ore-0.074
ires-0.070
ges-0.068
Token mom
Token ID1995
Feature activation-2.20e+00

Pos logit contributions
 forgot+0.081
ode+0.062
 stayed+0.061
 forget+0.058
 promise+0.058
Neg logit contributions
 This-0.103
ore-0.089
 Today-0.089
ires-0.087
 late-0.086
Tokenmy
Token ID1820
Feature activation-2.13e+00

Pos logit contributions
 forgot+0.038
 promise+0.031
 way+0.030
 stayed+0.029
ode+0.029
Neg logit contributions
 This-0.042
ore-0.037
 late-0.035
 Today-0.035
-0.035
Token watched
Token ID7342
Feature activation+8.08e+00

Pos logit contributions
 forgot+0.037
 promise+0.030
 way+0.029
 stayed+0.029
 forget+0.028
Neg logit contributions
 This-0.042
ore-0.037
 late-0.035
 Today-0.035
ires-0.035
Token in
Token ID287
Feature activation+1.34e-03

Pos logit contributions
 This+0.127
ore+0.113
uttering+0.109
iffs+0.107
ires+0.105
Neg logit contributions
 forgot-0.158
 promise-0.136
 stayed-0.136
 way-0.134
 head-0.129
Token amaz
Token ID40642
Feature activation+9.84e+00

Pos logit contributions
 This+0.000
ore+0.000
ires+0.000
 Today+0.000
 late+0.000
Neg logit contributions
 forgot-0.000
 promise-0.000
 way-0.000
 stayed-0.000
 forget-0.000
Tokenement
Token ID972
Feature activation+6.01e+00

Pos logit contributions
 This+0.162
ore+0.139
 Today+0.134
 late+0.133
ges+0.130
Neg logit contributions
 forgot-0.187
 stayed-0.163
 promise-0.161
 way-0.158
ode-0.152
Token as
Token ID355
Feature activation+3.63e+00

Pos logit contributions
 This+0.087
ore+0.075
ires+0.068
 Today+0.068
 late+0.068
Neg logit contributions
 forgot-0.132
 stayed-0.111
 promise-0.111
 way-0.110
 forget-0.108
Token the
Token ID262
Feature activation-4.38e+00

Pos logit contributions
 This+0.050
ore+0.042
 late+0.040
ires+0.039
 Today+0.038
Neg logit contributions
 forgot-0.084
 promise-0.072
 stayed-0.070
ode-0.070
 way-0.069
Token machine
Token ID4572
Feature activation+1.34e+00

Pos logit contributions
 forgot+0.079
ode+0.060
 stayed+0.060
 hoped+0.058
 forget+0.057
Neg logit contributions
 This-0.081
ore-0.072
 late-0.071
 Today-0.070
-0.069
Token flew
Token ID13112
Feature activation+4.61e+00

Pos logit contributions
 This+0.028
ore+0.025
 late+0.023
+0.023
 Today+0.023
Neg logit contributions
 forgot-0.021
ode-0.017
 promise-0.017
 forget-0.016
 scar-0.015
Token Lucy
Token ID22162
Feature activation-7.61e+00

Pos logit contributions
 This+0.012
 Today+0.008
ore+0.008
 late+0.008
+0.007
Neg logit contributions
 forgot-0.023
ode-0.021
 promise-0.020
 passengers-0.019
 scar-0.019
Token and
Token ID290
Feature activation-3.39e+00

Pos logit contributions
 forgot+0.136
ode+0.133
 promise+0.133
 passengers+0.124
 scar+0.124
Neg logit contributions
 This-0.115
ore-0.092
-0.090
 late-0.086
 Playing-0.081
Token her
Token ID607
Feature activation-7.07e+00

Pos logit contributions
 forgot+0.090
ode+0.079
 promise+0.078
 stayed+0.076
 forget+0.075
Neg logit contributions
 This-0.038
ore-0.027
 Today-0.027
 late-0.025
ires-0.024
Token mom
Token ID1995
Feature activation-5.64e+00

Pos logit contributions
 forgot+0.134
ode+0.125
 stayed+0.111
 regretted+0.106
 forget+0.104
Neg logit contributions
 This-0.113
 Today-0.101
ires-0.094
-0.093
ummy-0.092
Token completed
Token ID5668
Feature activation+1.47e+00

Pos logit contributions
 promise+0.080
 forgot+0.079
 wounds+0.073
 tears+0.071
 boo+0.069
Neg logit contributions
 This-0.090
ges-0.081
 at-0.078
ing-0.078
 selling-0.076
Token their
Token ID511
Feature activation-1.00e+01

Pos logit contributions
 This+0.022
ore+0.018
 late+0.017
ires+0.017
 Today+0.017
Neg logit contributions
 forgot-0.033
 promise-0.028
 stayed-0.028
 way-0.027
 forget-0.027
Token mission
Token ID4365
Feature activation+4.05e+00

Pos logit contributions
 forgot+0.160
 regretted+0.118
ode+0.117
 stayed+0.114
 hoped+0.109
Neg logit contributions
 This-0.216
 Today-0.185
ore-0.174
 late-0.169
ires-0.168
Token.
Token ID13
Feature activation+3.45e+00

Pos logit contributions
 This+0.043
ore+0.034
 late+0.030
 Today+0.029
ires+0.028
Neg logit contributions
 forgot-0.107
 promise-0.093
ode-0.093
 stayed-0.091
 forget-0.091
Token They
Token ID1119
Feature activation-6.67e+00

Pos logit contributions
 This+0.041
ore+0.039
uttering+0.037
ires+0.036
 late+0.034
Neg logit contributions
 forgot-0.078
 way-0.068
 stayed-0.066
 promise-0.066
 forget-0.064
Token had
Token ID550
Feature activation-2.52e+00

Pos logit contributions
ode+0.102
 wounds+0.092
 promise+0.091
 way+0.089
 forgot+0.087
Neg logit contributions
 This-0.098
 On-0.088
 Inside-0.085
 at-0.084
ges-0.082
Token found
Token ID1043
Feature activation+1.63e+00

Pos logit contributions
 promise+0.049
 forgot+0.048
ode+0.047
 head+0.044
 forget+0.043
Neg logit contributions
 This-0.039
 late-0.034
-0.028
 spending-0.028
 selling-0.026
Token.
Token ID13
Feature activation+3.82e+00

Pos logit contributions
 forgot+0.037
ode+0.032
 promise+0.032
 forget+0.032
 scar+0.031
Neg logit contributions
 This-0.017
ore-0.014
 late-0.013
 Today-0.011
ges-0.011
Token They
Token ID1119
Feature activation-6.77e+00

Pos logit contributions
 This+0.038
ore+0.030
ires+0.027
 late+0.026
 Today+0.026
Neg logit contributions
 forgot-0.103
 promise-0.090
 stayed-0.088
 way-0.088
 forget-0.087
Token hoped
Token ID10719
Feature activation+1.87e+00

Pos logit contributions
ode+0.124
 wig+0.109
 scar+0.109
 way+0.108
 sleeves+0.108
Neg logit contributions
-0.070
-0.065
 This-0.062
 at-0.061
 him-0.061
Token to
Token ID284
Feature activation-7.27e-01

Pos logit contributions
 This+0.021
 late+0.017
ore+0.016
ires+0.014
 Today+0.013
Neg logit contributions
 forgot-0.048
 promise-0.043
ode-0.043
 head-0.040
 forget-0.040
Token rebuild
Token ID17884
Feature activation+4.10e+00

Pos logit contributions
 forgot+0.012
 sighed+0.010
 regretted+0.010
 scar+0.010
ode+0.010
Neg logit contributions
 This-0.013
 late-0.012
ore-0.011
 Do-0.011
ires-0.010
Token their
Token ID511
Feature activation-9.83e+00

Pos logit contributions
 This+0.049
ore+0.040
 late+0.038
ires+0.036
+0.034
Neg logit contributions
 forgot-0.103
ode-0.087
 promise-0.086
 stayed-0.085
 forget-0.084
Token village
Token ID7404
Feature activation+3.32e-01

Pos logit contributions
 forgot+0.170
 stayed+0.130
ode+0.128
 promise+0.121
 forget+0.120
Neg logit contributions
 This-0.190
ore-0.168
 late-0.168
ires-0.162
 Today-0.161
Token and
Token ID290
Feature activation-3.63e+00

Pos logit contributions
 This+0.005
ore+0.004
 late+0.004
 Today+0.004
ires+0.004
Neg logit contributions
 forgot-0.007
ode-0.006
 promise-0.006
 stayed-0.006
 scar-0.005
Token make
Token ID787
Feature activation+2.42e+00

Pos logit contributions
 forgot+0.058
ode+0.058
 scar+0.054
 promise+0.050
 sleeves+0.049
Neg logit contributions
 This-0.061
 late-0.056
ore-0.049
 Do-0.048
 selling-0.046
Token it
Token ID340
Feature activation-2.57e+00

Pos logit contributions
 This+0.035
 late+0.030
ore+0.029
ires+0.028
+0.027
Neg logit contributions
 forgot-0.055
ode-0.046
 promise-0.046
 forget-0.045
 stayed-0.044
Token even
Token ID772
Feature activation-5.55e+00

Pos logit contributions
 forgot+0.042
 promise+0.033
 stayed+0.032
ode+0.032
 way+0.032
Neg logit contributions
 This-0.052
ore-0.045
 late-0.045
 Today-0.043
ires-0.043
Token checking
Token ID10627
Feature activation+4.73e+00

Pos logit contributions
 forgot+0.023
 promise+0.019
 stayed+0.019
 forget+0.018
 way+0.018
Neg logit contributions
 This-0.016
ore-0.014
 late-0.013
ires-0.012
-0.012
Token that
Token ID326
Feature activation-1.17e+00

Pos logit contributions
 This+0.071
ore+0.061
 Today+0.057
ires+0.056
 late+0.056
Neg logit contributions
 forgot-0.103
 promise-0.087
 way-0.087
 stayed-0.086
 forget-0.084
Token she
Token ID673
Feature activation-8.40e+00

Pos logit contributions
 forgot+0.025
ode+0.021
 promise+0.021
 stayed+0.020
 forget+0.019
Neg logit contributions
 This-0.018
ore-0.016
 Today-0.015
 late-0.015
ires-0.014
Token had
Token ID550
Feature activation-2.74e+00

Pos logit contributions
ode+0.117
 passengers+0.109
 scar+0.109
 captain+0.108
 promise+0.104
Neg logit contributions
 This-0.144
ore-0.134
-0.129
 late-0.129
?-0.118
Token everything
Token ID2279
Feature activation+1.24e+00

Pos logit contributions
ode+0.038
 forgot+0.038
 promise+0.036
 scar+0.033
 forget+0.032
Neg logit contributions
 This-0.053
 late-0.049
ore-0.043
-0.042
uttering-0.041
Token she
Token ID673
Feature activation-9.70e+00

Pos logit contributions
 This+0.015
ore+0.012
 late+0.012
ires+0.011
 Today+0.011
Neg logit contributions
 forgot-0.030
 promise-0.026
 stayed-0.026
ode-0.026
 way-0.025
Token needed
Token ID2622
Feature activation+1.68e+00

Pos logit contributions
ode+0.111
 forgot+0.104
 scar+0.103
 passengers+0.102
 way+0.100
Neg logit contributions
 This-0.204
 late-0.184
ore-0.184
-0.182
 Playing-0.168
Token.
Token ID13
Feature activation+3.66e+00

Pos logit contributions
 This+0.021
ore+0.018
ires+0.017
 Today+0.016
uttering+0.016
Neg logit contributions
 forgot-0.040
 promise-0.035
 way-0.035
 stayed-0.035
 forget-0.033
Token She
Token ID1375
Feature activation-7.75e+00

Pos logit contributions
 This+0.035
ore+0.031
uttering+0.028
ires+0.027
 late+0.026
Neg logit contributions
 forgot-0.097
 way-0.082
 promise-0.082
 stayed-0.082
 learned-0.081
Token even
Token ID772
Feature activation-7.10e+00

Pos logit contributions
ode+0.141
 passengers+0.118
 mate+0.115
ologist+0.110
 sandbox+0.110
Neg logit contributions
:-0.101
 This-0.094
 late-0.092
-0.090
 with-0.089
Token missed
Token ID6825
Feature activation+3.42e+00

Pos logit contributions
ode+0.106
 promise+0.085
 heads+0.081
 head+0.078
 shoulders+0.077
Neg logit contributions
 late-0.135
 This-0.118
ges-0.112
ore-0.111
to-0.106
TokenOne
Token ID3198
Feature activation-1.55e+00

Pos logit contributions
 This+0.062
ore+0.056
ires+0.054
uttering+0.051
ays+0.050
Neg logit contributions
 forgot-0.085
 stayed-0.072
 way-0.071
 promise-0.070
 learned-0.070
Token day
Token ID1110
Feature activation+3.90e+00

Pos logit contributions
 forgot+0.030
 promise+0.025
 stayed+0.024
 way+0.024
 forget+0.024
Neg logit contributions
 This-0.027
ore-0.024
ires-0.022
 late-0.022
 Today-0.022
Token,
Token ID11
Feature activation+2.01e+00

Pos logit contributions
ires+0.068
uttering+0.068
 This+0.068
ore+0.064
elly+0.062
Neg logit contributions
 forgot-0.070
 way-0.058
 stayed-0.058
 bit-0.057
 laughed-0.054
Token a
Token ID257
Feature activation-3.54e+00

Pos logit contributions
 This+0.028
ore+0.023
ires+0.021
 Today+0.021
 late+0.021
Neg logit contributions
 forgot-0.047
 promise-0.040
 stayed-0.040
 way-0.039
 forget-0.039
Token mis
Token ID2984
Feature activation-1.13e+00

Pos logit contributions
 forgot+0.060
ode+0.051
 stayed+0.050
 promise+0.047
 argued+0.047
Neg logit contributions
 This-0.065
 late-0.060
ore-0.059
-0.057
 Today-0.054
Tokenchie
Token ID3043
Feature activation-9.67e+00

Pos logit contributions
 forgot+0.020
 way+0.016
 promise+0.015
 stayed+0.015
 forget+0.015
Neg logit contributions
 This-0.023
ore-0.021
uttering-0.021
ges-0.019
 late-0.019
Tokenvous
Token ID31222
Feature activation-1.45e+00

Pos logit contributions
 forgot+0.190
 promise+0.165
ode+0.162
 scar+0.159
 forget+0.158
Neg logit contributions
 This-0.165
ore-0.147
 late-0.137
 Today-0.131
-0.127
Token young
Token ID1862
Feature activation-3.97e+00

Pos logit contributions
 forgot+0.024
 promise+0.018
 stayed+0.018
 forget+0.018
ode+0.018
Neg logit contributions
 This-0.031
ore-0.028
 Today-0.027
-0.026
 late-0.025
Token boy
Token ID2933
Feature activation-3.68e+00

Pos logit contributions
 forgot+0.060
 promise+0.048
ode+0.045
 stayed+0.044
 forget+0.044
Neg logit contributions
 This-0.086
 late-0.078
ore-0.078
-0.075
 Today-0.073
Token decided
Token ID3066
Feature activation+2.42e+00

Pos logit contributions
 forgot+0.053
 promise+0.040
 stayed+0.039
 way+0.038
 forget+0.037
Neg logit contributions
 This-0.084
ore-0.076
ires-0.073
 Today-0.073
 late-0.073
Token to
Token ID284
Feature activation-5.44e-01

Pos logit contributions
 This+0.032
ore+0.028
ires+0.027
 Today+0.026
uttering+0.026
Neg logit contributions
 forgot-0.058
 stayed-0.050
 way-0.049
 promise-0.048
 forget-0.047
Token the
Token ID262
Feature activation-7.10e+00

Pos logit contributions
 This+0.033
ore+0.029
 Today+0.027
ires+0.026
uttering+0.026
Neg logit contributions
 forgot-0.040
 promise-0.033
 way-0.033
 stayed-0.033
 forget-0.032
Token prince
Token ID19716
Feature activation-5.39e+00

Pos logit contributions
 forgot+0.103
ode+0.086
 promise+0.078
 stayed+0.077
 regretted+0.074
Neg logit contributions
 This-0.146
 late-0.132
ires-0.124
-0.120
ore-0.120
Token and
Token ID290
Feature activation-4.71e+00

Pos logit contributions
 forgot+0.074
ode+0.070
 promise+0.069
 scar+0.065
 way+0.062
Neg logit contributions
 This-0.103
ore-0.092
-0.090
 late-0.083
ges-0.083
Token princess
Token ID21752
Feature activation-5.81e+00

Pos logit contributions
 forgot+0.095
ode+0.086
 promise+0.084
 stayed+0.077
 forget+0.075
Neg logit contributions
 This-0.077
 late-0.061
ore-0.059
-0.058
 Today-0.057
Token sealed
Token ID15283
Feature activation+3.94e+00

Pos logit contributions
ode+0.079
 forgot+0.076
 promise+0.072
 scar+0.069
 way+0.065
Neg logit contributions
 This-0.108
ore-0.100
-0.095
ges-0.095
uttering-0.087
Token their
Token ID511
Feature activation-9.61e+00

Pos logit contributions
 This+0.051
ore+0.042
 late+0.039
ires+0.038
 Today+0.037
Neg logit contributions
 forgot-0.096
 promise-0.082
 forget-0.080
 stayed-0.080
ode-0.080
Token marriage
Token ID4845
Feature activation-2.72e-01

Pos logit contributions
 forgot+0.164
ode+0.124
 stayed+0.123
 forget+0.120
 regretted+0.115
Neg logit contributions
 This-0.194
ires-0.163
ore-0.160
 Today-0.159
 late-0.151
Token with
Token ID351
Feature activation-1.78e+00

Pos logit contributions
 forgot+0.007
ode+0.006
 forget+0.006
 stayed+0.006
 regretted+0.006
Neg logit contributions
 This-0.003
ore-0.002
 late-0.002
 Today-0.002
ires-0.002
Token a
Token ID257
Feature activation-4.88e+00

Pos logit contributions
 forgot+0.038
ode+0.033
 promise+0.031
 forget+0.030
 stayed+0.030
Neg logit contributions
 This-0.027
 late-0.022
ore-0.021
-0.020
ires-0.020
Token kiss
Token ID9245
Feature activation+2.26e+00

Pos logit contributions
 forgot+0.098
ode+0.086
 stayed+0.084
 heads+0.080
 argued+0.076
Neg logit contributions
 This-0.076
ore-0.068
 late-0.067
uttering-0.062
 Today-0.062
Token.
Token ID13
Feature activation+4.14e+00

Pos logit contributions
 This+0.024
ore+0.019
 Today+0.017
 late+0.017
uttering+0.016
Neg logit contributions
 forgot-0.059
 promise-0.051
 way-0.050
 stayed-0.050
 forget-0.050
Token animals
Token ID4695
Feature activation-4.64e+00

Pos logit contributions
 forgot+0.094
atha+0.075
ode+0.074
 argued+0.074
 slammed+0.073
Neg logit contributions
-0.073
 This-0.064
 outer-0.061
ires-0.060
 Today-0.059
Token in
Token ID287
Feature activation-2.82e+00

Pos logit contributions
 forgot+0.080
 scar+0.067
 promise+0.066
ode+0.066
 way+0.065
Neg logit contributions
 This-0.082
ore-0.079
-0.068
ges-0.068
ires-0.067
Token the
Token ID262
Feature activation-5.67e+00

Pos logit contributions
 forgot+0.058
 promise+0.049
 way+0.049
 stayed+0.048
 forget+0.047
Neg logit contributions
 This-0.045
ore-0.039
ires-0.038
 late-0.037
uttering-0.037
Token forest
Token ID8222
Feature activation+8.78e-01

Pos logit contributions
 forgot+0.118
 promise+0.092
 stayed+0.091
ode+0.090
 argued+0.088
Neg logit contributions
 This-0.094
-0.085
 Today-0.079
ore-0.078
 late-0.076
Token have
Token ID423
Feature activation-2.67e+00

Pos logit contributions
 This+0.018
ore+0.016
 late+0.015
+0.015
 Today+0.015
Neg logit contributions
 forgot-0.013
 promise-0.011
ode-0.011
 scar-0.010
 way-0.010
Token their
Token ID511
Feature activation-9.59e+00

Pos logit contributions
 forgot+0.057
 promise+0.051
ode+0.049
 head+0.048
 forget+0.048
Neg logit contributions
 This-0.040
 late-0.033
ore-0.032
-0.030
uttering-0.029
Token own
Token ID898
Feature activation-7.51e+00

Pos logit contributions
 forgot+0.176
 regretted+0.127
ode+0.127
 stayed+0.127
 forget+0.125
Neg logit contributions
 This-0.177
ore-0.154
-0.152
 Today-0.150
ires-0.146
Token tw
Token ID665
Feature activation-2.43e+00

Pos logit contributions
 forgot+0.117
ode+0.083
 stayed+0.082
 forget+0.081
 promise+0.081
Neg logit contributions
 This-0.156
ore-0.140
-0.136
 Today-0.135
uttering-0.131
Tokenigs
Token ID9235
Feature activation+1.35e+00

Pos logit contributions
 forgot+0.034
 promise+0.025
 stayed+0.025
 way+0.024
 forget+0.024
Neg logit contributions
 This-0.056
ore-0.051
ires-0.049
 Today-0.048
uttering-0.048
Token that
Token ID326
Feature activation-2.90e+00

Pos logit contributions
 This+0.020
ore+0.017
 late+0.015
 Today+0.015
ires+0.015
Neg logit contributions
 forgot-0.030
 promise-0.026
 stayed-0.025
 way-0.025
ode-0.024
Token shine
Token ID18340
Feature activation+3.38e+00

Pos logit contributions
 forgot+0.049
ode+0.042
 promise+0.042
 scar+0.039
 regretted+0.038
Neg logit contributions
 This-0.057
ore-0.050
-0.045
 late-0.045
 Today-0.044
Token best
Token ID1266
Feature activation-2.65e+00

Pos logit contributions
 forgot+0.105
 sighed+0.089
 regretted+0.085
 stayed+0.080
 sank+0.077
Neg logit contributions
 This-0.077
 late-0.069
uttering-0.068
 Today-0.064
ires-0.061
Token of
Token ID286
Feature activation-2.21e+00

Pos logit contributions
 forgot+0.061
 promise+0.052
 stayed+0.051
 forget+0.050
ode+0.050
Neg logit contributions
 This-0.038
ore-0.033
 late-0.030
uttering-0.030
ires-0.030
Token friends
Token ID2460
Feature activation-2.81e+00

Pos logit contributions
 forgot+0.032
 forget+0.023
ode+0.022
 promise+0.021
 bit+0.021
Neg logit contributions
 This-0.051
ires-0.046
ore-0.045
uttering-0.044
 late-0.044
Token.
Token ID13
Feature activation+3.14e+00

Pos logit contributions
 forgot+0.068
 promise+0.059
 way+0.057
 stayed+0.057
 forget+0.056
Neg logit contributions
 This-0.036
ore-0.030
 late-0.027
 Today-0.027
ires-0.026
Token Everywhere
Token ID48201
Feature activation+1.56e+00

Pos logit contributions
 This+0.037
ore+0.034
uttering+0.032
ires+0.031
 late+0.031
Neg logit contributions
 forgot-0.074
 way-0.064
 promise-0.063
 stayed-0.063
 forget-0.062
Token Lucy
Token ID22162
Feature activation-9.56e+00

Pos logit contributions
 This+0.022
ore+0.017
 late+0.017
+0.016
 Today+0.016
Neg logit contributions
 forgot-0.035
ode-0.032
 promise-0.031
 forget-0.030
 head-0.029
Token went
Token ID1816
Feature activation+5.77e-01

Pos logit contributions
 promise+0.147
 forgot+0.136
ode+0.132
 passengers+0.129
 captain+0.123
Neg logit contributions
 This-0.159
-0.155
ore-0.149
ges-0.137
elly-0.136
Token,
Token ID11
Feature activation-9.02e-01

Pos logit contributions
 This+0.009
ore+0.008
ires+0.008
 Today+0.008
 late+0.007
Neg logit contributions
 forgot-0.012
 way-0.010
 stayed-0.010
 learned-0.010
 forget-0.009
Token the
Token ID262
Feature activation-6.36e+00

Pos logit contributions
 forgot+0.021
 promise+0.020
ode+0.019
 stayed+0.018
 regretted+0.018
Neg logit contributions
 This-0.011
 late-0.009
ore-0.009
ges-0.008
ires-0.008
Token rabbit
Token ID22746
Feature activation-4.83e+00

Pos logit contributions
 forgot+0.101
ode+0.074
 stayed+0.073
 promise+0.072
 forget+0.070
Neg logit contributions
 This-0.137
 Today-0.121
 late-0.120
-0.117
ore-0.115
Token was
Token ID373
Feature activation-3.38e+00

Pos logit contributions
 forgot+0.063
 promise+0.061
ode+0.057
 forget+0.052
 passengers+0.051
Neg logit contributions
 This-0.098
-0.087
ore-0.084
 Playing-0.082
ges-0.078
Token
Token ID220
Feature activation+4.95e+00

Pos logit contributions
 This+0.049
ires+0.049
uttering+0.048
ore+0.047
 late+0.045
Neg logit contributions
 forgot-0.079
 way-0.066
 stayed-0.065
 forget-0.063
 learned-0.063
Token
Token ID198
Feature activation+4.50e+00

Pos logit contributions
uttering+0.060
 This+0.060
ocol+0.059
ore+0.059
ires+0.058
Neg logit contributions
 forgot-0.097
 way-0.082
 stayed-0.081
 learned-0.077
 hoped-0.075
Token
Token ID198
Feature activation+3.84e+00

Pos logit contributions
 This+0.054
ires+0.050
uttering+0.048
ore+0.047
elly+0.046
Neg logit contributions
 forgot-0.101
 stayed-0.088
 learned-0.087
 way-0.083
 laughed-0.083
TokenAs
Token ID1722
Feature activation+2.77e+00

Pos logit contributions
 This+0.062
ore+0.054
 Today+0.050
ires+0.050
 late+0.050
Neg logit contributions
 forgot-0.080
 promise-0.067
 stayed-0.066
 way-0.065
 forget-0.064
Token M
Token ID337
Feature activation-4.10e+00

Pos logit contributions
 This+0.041
ore+0.035
 late+0.033
 Today+0.032
+0.031
Neg logit contributions
 forgot-0.062
 promise-0.053
ode-0.053
 stayed-0.052
 way-0.051
Tokenargo
Token ID9448
Feature activation-9.53e+00

Pos logit contributions
 forgot+0.068
 promise+0.056
 stayed+0.055
 way+0.054
 forget+0.051
Neg logit contributions
 This-0.082
 late-0.071
ore-0.071
ires-0.068
uttering-0.067
Token walked
Token ID6807
Feature activation+2.73e+00

Pos logit contributions
 forgot+0.146
ode+0.145
 passengers+0.136
 captain+0.135
 promise+0.130
Neg logit contributions
 This-0.155
-0.155
ore-0.152
 Today-0.129
 On-0.127
Token away
Token ID1497
Feature activation+1.98e+00

Pos logit contributions
 This+0.053
ore+0.047
 late+0.044
 Today+0.044
ires+0.044
Neg logit contributions
 forgot-0.049
 promise-0.040
 stayed-0.038
 way-0.038
 forget-0.038
Token,
Token ID11
Feature activation+1.28e+00

Pos logit contributions
 This+0.022
ore+0.018
 late+0.017
 Today+0.015
uttering+0.015
Neg logit contributions
 forgot-0.050
ode-0.045
 promise-0.045
 stayed-0.042
 forget-0.042
Token she
Token ID673
Feature activation-6.95e+00

Pos logit contributions
 This+0.014
ore+0.011
 late+0.011
+0.010
 Today+0.010
Neg logit contributions
 forgot-0.032
ode-0.030
 promise-0.030
 stayed-0.027
 head-0.027
Token thought
Token ID1807
Feature activation+3.27e+00

Pos logit contributions
ode+0.104
 passengers+0.088
 promise+0.086
 heads+0.084
 scar+0.079
Neg logit contributions
 This-0.108
-0.107
 late-0.105
-0.104
 with-0.100
Token
Token ID198
Feature activation+4.05e+00

Pos logit contributions
 This+0.025
ore+0.023
ires+0.022
uttering+0.021
 late+0.020
Neg logit contributions
 forgot-0.042
 promise-0.035
 way-0.034
 stayed-0.034
 forget-0.034
Token
Token ID198
Feature activation+3.62e+00

Pos logit contributions
 This+0.060
uttering+0.054
ires+0.053
ges+0.052
ore+0.051
Neg logit contributions
 forgot-0.079
 learned-0.069
 promise-0.069
 way-0.068
 stayed-0.066
TokenThe
Token ID464
Feature activation-6.39e+00

Pos logit contributions
 This+0.054
 late+0.045
ore+0.045
 Today+0.042
ires+0.042
Neg logit contributions
 forgot-0.079
 promise-0.069
 way-0.067
 stayed-0.066
 forget-0.065
Token friends
Token ID2460
Feature activation-4.58e+00

Pos logit contributions
 forgot+0.119
 stayed+0.092
ode+0.091
 promise+0.089
 regretted+0.089
Neg logit contributions
 This-0.124
 Today-0.105
ore-0.104
 late-0.103
ires-0.101
Token used
Token ID973
Feature activation+2.72e-01

Pos logit contributions
 forgot+0.060
ode+0.057
 scar+0.055
 way+0.053
 passengers+0.050
Neg logit contributions
 This-0.091
ore-0.085
-0.079
ges-0.078
 On-0.074
Token their
Token ID511
Feature activation-9.49e+00

Pos logit contributions
 This+0.004
ore+0.003
 late+0.003
 Today+0.003
ires+0.003
Neg logit contributions
 forgot-0.007
 promise-0.006
ode-0.005
 forget-0.005
 stayed-0.005
Token numbers
Token ID3146
Feature activation+2.48e+00

Pos logit contributions
 forgot+0.178
 promise+0.142
 stayed+0.142
 forget+0.137
ode+0.136
Neg logit contributions
 This-0.178
ore-0.149
 Today-0.146
ires-0.145
 late-0.140
Token to
Token ID284
Feature activation-2.34e+00

Pos logit contributions
 This+0.035
ore+0.030
ires+0.027
 Today+0.027
 late+0.027
Neg logit contributions
 forgot-0.056
 promise-0.048
 stayed-0.047
 way-0.047
 forget-0.046
Token try
Token ID1949
Feature activation+4.65e+00

Pos logit contributions
 forgot+0.040
 regretted+0.030
 stayed+0.030
 promise+0.030
ode+0.029
Neg logit contributions
 This-0.048
ore-0.041
 Today-0.040
 late-0.039
ires-0.039
Token and
Token ID290
Feature activation-3.48e+00

Pos logit contributions
 This+0.080
ore+0.074
uttering+0.071
 Today+0.069
ires+0.069
Neg logit contributions
 forgot-0.082
 way-0.076
 promise-0.069
 stayed-0.066
 scar-0.066
Token make
Token ID787
Feature activation+2.91e+00

Pos logit contributions
 forgot+0.057
 promise+0.045
 regretted+0.043
ode+0.043
 stayed+0.043
Neg logit contributions
 This-0.070
 late-0.058
ore-0.057
 Today-0.056
ires-0.055
Token be
Token ID307
Feature activation-2.62e+00

Pos logit contributions
 forgot+0.017
 scar+0.013
 passengers+0.013
 sighed+0.013
 regretted+0.013
Neg logit contributions
 This-0.025
 Today-0.021
ore-0.021
 late-0.021
ires-0.020
Token careful
Token ID8161
Feature activation+5.55e+00

Pos logit contributions
 forgot+0.041
 promise+0.033
ode+0.033
 forget+0.032
 way+0.031
Neg logit contributions
 late-0.051
 This-0.051
uttering-0.045
ore-0.044
ires-0.043
Token with
Token ID351
Feature activation+2.07e-01

Pos logit contributions
 This+0.082
ore+0.071
 Today+0.066
+0.066
ires+0.064
Neg logit contributions
 forgot-0.121
 way-0.104
 stayed-0.104
 promise-0.102
 forget-0.098
Token the
Token ID262
Feature activation-6.80e+00

Pos logit contributions
 This+0.003
ore+0.002
ires+0.002
 late+0.002
ges+0.002
Neg logit contributions
 forgot-0.005
 promise-0.004
 forget-0.004
 stayed-0.004
ode-0.004
Token things
Token ID1243
Feature activation+2.07e+00

Pos logit contributions
 forgot+0.128
 stayed+0.102
 promise+0.097
 forget+0.096
ode+0.096
Neg logit contributions
 This-0.123
 late-0.105
 Today-0.105
ore-0.104
ires-0.103
Token she
Token ID673
Feature activation-9.49e+00

Pos logit contributions
 This+0.025
ore+0.020
 late+0.019
ires+0.018
 Today+0.017
Neg logit contributions
 forgot-0.051
 promise-0.044
ode-0.043
 way-0.043
 stayed-0.042
Token cut
Token ID2005
Feature activation+5.17e+00

Pos logit contributions
 forgot+0.110
 way+0.104
 promise+0.103
 passengers+0.099
 captain+0.098
Neg logit contributions
 This-0.200
ore-0.183
-0.181
 late-0.180
 Playing-0.171
Token.
Token ID13
Feature activation+3.20e+00

Pos logit contributions
 This+0.075
ore+0.065
 late+0.059
ires+0.059
 Today+0.058
Neg logit contributions
 forgot-0.117
 promise-0.098
 stayed-0.095
 forget-0.095
 way-0.094
Token<|endoftext|>
Token ID50256
Feature activation+6.44e+00

Pos logit contributions
ore+0.033
uttering+0.032
 This+0.031
ires+0.030
ach+0.030
Neg logit contributions
 forgot-0.077
 learned-0.067
 way-0.067
 forget-0.065
 promise-0.064
TokenOnce
Token ID7454
Feature activation+4.71e-01

Pos logit contributions
ires+0.101
uttering+0.101
ocol+0.092
 This+0.087
anging+0.085
Neg logit contributions
 way-0.109
 forgot-0.107
 learned-0.101
 had-0.098
 felt-0.097
Token upon
Token ID2402
Feature activation+1.92e+00

Pos logit contributions
 This+0.007
ore+0.006
 late+0.006
uttering+0.006
 Playing+0.006
Neg logit contributions
 forgot-0.010
 way-0.009
 promise-0.009
 forget-0.008
 stayed-0.008
Token it
Token ID340
Feature activation-3.86e+00

Pos logit contributions
 forgot+0.001
 promise+0.001
 stayed+0.001
 way+0.001
 forget+0.001
Neg logit contributions
 This-0.001
ore-0.001
 Today-0.000
ires-0.000
 late-0.000
Token wasn
Token ID2492
Feature activation+9.82e-01

Pos logit contributions
 forgot+0.055
 promise+0.047
ode+0.046
 passengers+0.045
 scar+0.043
Neg logit contributions
 This-0.082
ore-0.072
 late-0.069
-0.068
ires-0.067
Token't
Token ID470
Feature activation-5.09e+00

Pos logit contributions
 This+0.013
ires+0.013
ore+0.012
 Playing+0.012
uttering+0.012
Neg logit contributions
 forgot-0.020
 forget-0.018
 promise-0.018
 stayed-0.018
 way-0.017
Token the
Token ID262
Feature activation-5.97e+00

Pos logit contributions
 forgot+0.098
 promise+0.083
ode+0.079
 stayed+0.079
 forget+0.078
Neg logit contributions
 This-0.086
 late-0.076
ore-0.073
uttering-0.070
ires-0.069
Token flowers
Token ID12734
Feature activation-1.22e+00

Pos logit contributions
 forgot+0.115
 sighed+0.090
 stayed+0.088
 learned+0.086
ode+0.085
Neg logit contributions
 This-0.102
-0.085
ore-0.084
 Today-0.084
 late-0.084
Token she
Token ID673
Feature activation-9.48e+00

Pos logit contributions
 forgot+0.029
 promise+0.025
 stayed+0.025
 way+0.025
 forget+0.024
Neg logit contributions
 This-0.016
ore-0.013
 Today-0.012
ires-0.012
 late-0.012
Token was
Token ID373
Feature activation-4.02e+00

Pos logit contributions
 forgot+0.113
 promise+0.097
 passengers+0.095
 scar+0.095
ode+0.094
Neg logit contributions
 This-0.215
ore-0.192
 late-0.185
-0.183
ires-0.179
Token looking
Token ID2045
Feature activation+1.28e+00

Pos logit contributions
 forgot+0.080
 promise+0.066
 stayed+0.064
 way+0.064
 forget+0.063
Neg logit contributions
 This-0.070
ore-0.061
 Today-0.057
ires-0.057
 late-0.057
Token for
Token ID329
Feature activation+8.35e-01

Pos logit contributions
 This+0.019
ore+0.016
 Today+0.015
ires+0.015
 late+0.015
Neg logit contributions
 forgot-0.028
 promise-0.024
 way-0.024
 stayed-0.024
 forget-0.023
Token.
Token ID13
Feature activation+3.60e+00

Pos logit contributions
 This+0.011
ore+0.009
 Today+0.008
ires+0.008
 late+0.008
Neg logit contributions
 forgot-0.020
 promise-0.017
 way-0.017
 stayed-0.017
 forget-0.017
Token
Token ID198
Feature activation+4.20e+00

Pos logit contributions
uttering+0.039
ore+0.038
 This+0.037
ires+0.036
ithering+0.035
Neg logit contributions
 forgot-0.087
 way-0.074
 learned-0.074
 promise-0.072
 stayed-0.072
Token branches
Token ID13737
Feature activation+3.73e+00

Pos logit contributions
 This+0.048
ore+0.043
 late+0.041
ires+0.040
 Today+0.040
Neg logit contributions
 forgot-0.042
 promise-0.034
 forget-0.032
 stayed-0.032
ode-0.030
Token.
Token ID13
Feature activation+4.49e+00

Pos logit contributions
 This+0.047
ore+0.039
 late+0.035
 Today+0.035
ires+0.035
Neg logit contributions
 forgot-0.091
 promise-0.078
 stayed-0.077
 way-0.076
 forget-0.075
Token The
Token ID383
Feature activation-6.21e+00

Pos logit contributions
 This+0.049
ore+0.044
uttering+0.039
ires+0.039
 late+0.039
Neg logit contributions
 forgot-0.111
 way-0.095
 stayed-0.095
 promise-0.094
 forget-0.091
Token bears
Token ID13062
Feature activation-5.54e+00

Pos logit contributions
 forgot+0.127
 promise+0.105
 hoped+0.101
 stayed+0.099
 regretted+0.098
Neg logit contributions
-0.086
 This-0.083
 late-0.077
 Today-0.075
ires-0.075
Token used
Token ID973
Feature activation+6.59e-01

Pos logit contributions
 forgot+0.080
ode+0.078
 passengers+0.076
 scar+0.075
 promise+0.075
Neg logit contributions
 This-0.089
ore-0.087
uttering-0.083
ges-0.082
overed-0.079
Token their
Token ID511
Feature activation-9.46e+00

Pos logit contributions
 This+0.009
ore+0.007
 late+0.007
uttering+0.006
ges+0.006
Neg logit contributions
 forgot-0.016
 promise-0.014
 forget-0.013
ode-0.013
 stayed-0.013
Token strong
Token ID1913
Feature activation-2.63e+00

Pos logit contributions
 forgot+0.160
 forget+0.116
ode+0.114
 regretted+0.108
 captain+0.107
Neg logit contributions
 This-0.186
ore-0.157
 Today-0.157
ires-0.152
-0.150
Token arms
Token ID5101
Feature activation+4.86e+00

Pos logit contributions
 forgot+0.041
 forget+0.028
 promise+0.028
 stayed+0.027
ode+0.026
Neg logit contributions
 This-0.058
 Today-0.052
ore-0.049
ires-0.047
 late-0.047
Token to
Token ID284
Feature activation-2.07e+00

Pos logit contributions
 This+0.069
ore+0.058
ires+0.054
 Today+0.053
 late+0.053
Neg logit contributions
 forgot-0.111
 promise-0.094
 stayed-0.093
 way-0.092
 forget-0.090
Token clear
Token ID1598
Feature activation+2.15e+00

Pos logit contributions
 forgot+0.037
 regretted+0.028
ode+0.027
 promise+0.027
 stayed+0.026
Neg logit contributions
 This-0.040
ore-0.035
 late-0.033
ges-0.032
 Today-0.032
Token away
Token ID1497
Feature activation+2.67e+00

Pos logit contributions
 This+0.035
ore+0.030
ires+0.028
 Today+0.028
 late+0.028
Neg logit contributions
 forgot-0.045
 promise-0.038
 stayed-0.036
 forget-0.036
 way-0.035
Token't
Token ID470
Feature activation-4.97e+00

Pos logit contributions
 forgot+0.014
 way+0.012
 stayed+0.012
 forget+0.012
 promise+0.011
Neg logit contributions
ires-0.007
 This-0.007
uttering-0.007
ore-0.006
 Today-0.006
Token known
Token ID1900
Feature activation+9.91e-01

Pos logit contributions
 forgot+0.062
ode+0.060
 promise+0.055
 scar+0.053
 heads+0.051
Neg logit contributions
 This-0.106
 late-0.099
ore-0.091
-0.087
ges-0.086
Token that
Token ID326
Feature activation-6.87e-01

Pos logit contributions
 This+0.016
ires+0.013
ore+0.013
 late+0.013
ges+0.012
Neg logit contributions
 forgot-0.021
 stayed-0.017
ode-0.017
 promise-0.017
 learned-0.016
Token the
Token ID262
Feature activation-5.58e+00

Pos logit contributions
 forgot+0.014
 promise+0.012
 stayed+0.012
ode+0.012
 way+0.012
Neg logit contributions
 This-0.011
ore-0.009
 late-0.009
 Today-0.009
ires-0.009
Token dish
Token ID9433
Feature activation-1.05e+00

Pos logit contributions
 forgot+0.107
 stayed+0.088
ode+0.082
 promise+0.081
 forget+0.080
Neg logit contributions
 This-0.102
ore-0.087
 late-0.086
 Today-0.085
ires-0.082
Token she
Token ID673
Feature activation-9.43e+00

Pos logit contributions
 forgot+0.019
 promise+0.015
 stayed+0.015
 way+0.015
 forget+0.015
Neg logit contributions
 This-0.020
ore-0.018
 late-0.017
ires-0.017
 Today-0.016
Token had
Token ID550
Feature activation-2.77e+00

Pos logit contributions
 forgot+0.109
ode+0.101
 scar+0.100
 promise+0.099
 passengers+0.096
Neg logit contributions
 This-0.212
ore-0.184
 late-0.181
-0.174
ires-0.171
Token chosen
Token ID7147
Feature activation+1.49e+00

Pos logit contributions
 forgot+0.050
 promise+0.044
ode+0.044
 forget+0.041
 scar+0.040
Neg logit contributions
 This-0.048
ore-0.041
 late-0.041
ges-0.038
-0.037
Token was
Token ID373
Feature activation-3.98e+00

Pos logit contributions
 This+0.020
ore+0.017
 Today+0.016
ires+0.016
 late+0.016
Neg logit contributions
 forgot-0.035
 promise-0.030
 way-0.029
 stayed-0.029
 forget-0.028
Token meant
Token ID4001
Feature activation+1.12e+00

Pos logit contributions
 forgot+0.078
 promise+0.065
 stayed+0.063
 way+0.063
 forget+0.062
Neg logit contributions
 This-0.068
ore-0.059
 late-0.056
ires-0.055
 Today-0.055
Token for
Token ID329
Feature activation+1.96e+00

Pos logit contributions
 This+0.014
ore+0.012
ires+0.011
 Today+0.011
uttering+0.011
Neg logit contributions
 forgot-0.027
 promise-0.023
 way-0.023
 stayed-0.023
 forget-0.022
Token bad
Token ID2089
Feature activation+2.42e+00

Pos logit contributions
 forgot+0.068
 promise+0.057
ode+0.055
 stayed+0.054
 forget+0.054
Neg logit contributions
 This-0.063
 late-0.057
ore-0.053
ires-0.052
uttering-0.050
Token!
Token ID0
Feature activation+2.96e+00

Pos logit contributions
 This+0.040
uttering+0.034
ore+0.033
ires+0.033
 Today+0.033
Neg logit contributions
 forgot-0.049
 stayed-0.041
 way-0.041
 promise-0.040
 bit-0.039
Token The
Token ID383
Feature activation-6.93e+00

Pos logit contributions
uttering+0.051
ires+0.040
overed+0.040
 atop+0.039
itting+0.039
Neg logit contributions
 forgot-0.056
 head-0.047
 bit-0.047
 promise-0.046
 stayed-0.045
Token dog
Token ID3290
Feature activation-3.24e+00

Pos logit contributions
 forgot+0.123
 stayed+0.099
ode+0.093
 promise+0.090
 regretted+0.089
Neg logit contributions
 This-0.132
 late-0.118
 Today-0.114
ires-0.114
ore-0.113
Token ruined
Token ID20484
Feature activation+3.10e+00

Pos logit contributions
 forgot+0.069
ode+0.060
 passengers+0.059
 promise+0.057
 stayed+0.057
Neg logit contributions
 This-0.048
ore-0.042
 late-0.038
-0.037
ires-0.034
Token our
Token ID674
Feature activation-9.43e+00

Pos logit contributions
 This+0.047
ore+0.040
 late+0.037
ires+0.037
 Today+0.037
Neg logit contributions
 forgot-0.069
 promise-0.058
 stayed-0.057
 way-0.056
 forget-0.056
Token work
Token ID670
Feature activation+2.97e+00

Pos logit contributions
 forgot+0.152
 stayed+0.118
 regretted+0.110
ode+0.110
 promise+0.109
Neg logit contributions
 This-0.199
ires-0.174
ore-0.171
 Today-0.167
 late-0.167
Token!"
Token ID2474
Feature activation+4.55e+00

Pos logit contributions
 This+0.036
ore+0.030
 late+0.027
 Today+0.026
ires+0.026
Neg logit contributions
 forgot-0.074
 promise-0.064
 stayed-0.063
 forget-0.061
ode-0.061
Token The
Token ID383
Feature activation-6.07e+00

Pos logit contributions
 This+0.050
ore+0.044
uttering+0.043
ires+0.041
ges+0.038
Neg logit contributions
 forgot-0.114
 way-0.097
 stayed-0.097
 promise-0.096
 learned-0.096
Token dog
Token ID3290
Feature activation-3.76e+00

Pos logit contributions
 forgot+0.100
 promise+0.077
 stayed+0.077
 way+0.074
ode+0.073
Neg logit contributions
 This-0.126
ore-0.113
 late-0.108
 Today-0.108
ires-0.108
Token bar
Token ID2318
Feature activation+6.71e-01

Pos logit contributions
 forgot+0.075
ode+0.065
 passengers+0.063
 forget+0.060
 crew+0.060
Neg logit contributions
 This-0.064
ore-0.053
-0.051
iffs-0.049
 Today-0.048
Token warm
Token ID5814
Feature activation+1.86e+00

Pos logit contributions
 forgot+0.042
 promise+0.036
 forget+0.033
 stayed+0.033
ode+0.033
Neg logit contributions
 This-0.036
ore-0.031
 late-0.030
 Today-0.029
uttering-0.028
Token and
Token ID290
Feature activation-3.38e+00

Pos logit contributions
 This+0.032
ore+0.028
ires+0.028
 Playing+0.026
uttering+0.026
Neg logit contributions
 forgot-0.035
 way-0.031
 stayed-0.030
 head-0.028
 bit-0.028
Token bright
Token ID6016
Feature activation-5.63e-03

Pos logit contributions
 forgot+0.063
 promise+0.056
ode+0.055
 stayed+0.050
 forget+0.050
Neg logit contributions
 This-0.057
 late-0.050
ore-0.047
 Today-0.046
ires-0.045
Token.
Token ID13
Feature activation+4.43e+00

Pos logit contributions
 forgot+0.000
 way+0.000
 stayed+0.000
 bit+0.000
 promise+0.000
Neg logit contributions
 This-0.000
ore-0.000
ires-0.000
 Today-0.000
iffs-0.000
Token Everywhere
Token ID48201
Feature activation+1.83e+00

Pos logit contributions
 This+0.063
ore+0.058
uttering+0.057
ires+0.056
 late+0.054
Neg logit contributions
 forgot-0.092
 way-0.076
 learned-0.073
 stayed-0.073
 promise-0.073
Token Molly
Token ID30236
Feature activation-9.42e+00

Pos logit contributions
 This+0.025
ore+0.021
 late+0.020
 Today+0.019
ires+0.019
Neg logit contributions
 forgot-0.042
 promise-0.036
 stayed-0.036
 way-0.035
 forget-0.035
Token looked
Token ID3114
Feature activation+7.83e-01

Pos logit contributions
 promise+0.153
ode+0.141
 forgot+0.133
 forget+0.123
 funn+0.123
Neg logit contributions
-0.144
 This-0.143
ore-0.132
 On-0.127
 at-0.121
Token,
Token ID11
Feature activation-4.38e-01

Pos logit contributions
 This+0.012
ore+0.010
ires+0.009
 Today+0.009
uttering+0.009
Neg logit contributions
 forgot-0.018
 stayed-0.015
 way-0.015
 promise-0.014
 forget-0.014
Token she
Token ID673
Feature activation-7.09e+00

Pos logit contributions
 forgot+0.011
 promise+0.010
ode+0.010
 stayed+0.009
 bit+0.009
Neg logit contributions
 This-0.005
 late-0.004
ore-0.004
-0.003
ires-0.003
Token saw
Token ID2497
Feature activation+1.84e+00

Pos logit contributions
 promise+0.104
ode+0.100
 forgot+0.095
 way+0.091
 passengers+0.086
Neg logit contributions
 This-0.120
-0.118
ore-0.112
 late-0.104
 Playing-0.104
Token new
Token ID649
Feature activation-1.86e+00

Pos logit contributions
 This+0.027
ore+0.022
+0.021
ires+0.021
 late+0.021
Neg logit contributions
 forgot-0.042
 promise-0.037
 forget-0.035
ode-0.034
 bit-0.033
Token.
Token ID13
Feature activation+3.93e+00

Pos logit contributions
 This+0.050
ore+0.041
ires+0.038
 Today+0.037
uttering+0.036
Neg logit contributions
 forgot-0.096
 promise-0.084
 stayed-0.082
 way-0.081
 forget-0.080
Token "
Token ID366
Feature activation+1.17e+00

Pos logit contributions
 This+0.044
ore+0.036
ires+0.033
 Today+0.032
uttering+0.032
Neg logit contributions
 forgot-0.101
 promise-0.086
 stayed-0.086
 way-0.086
 forget-0.083
TokenThe
Token ID464
Feature activation-6.85e+00

Pos logit contributions
 This+0.018
ore+0.015
 late+0.014
ires+0.014
 Today+0.014
Neg logit contributions
 forgot-0.025
 promise-0.022
 stayed-0.021
 way-0.021
 forget-0.021
Token cat
Token ID3797
Feature activation-3.78e+00

Pos logit contributions
 forgot+0.125
 stayed+0.097
ode+0.097
 hoped+0.091
 regretted+0.090
Neg logit contributions
 This-0.125
 late-0.115
 Today-0.108
-0.105
ore-0.105
Token ruined
Token ID20484
Feature activation+2.08e+00

Pos logit contributions
 forgot+0.072
 passengers+0.066
ode+0.065
 scar+0.064
 captain+0.062
Neg logit contributions
 This-0.060
ore-0.051
-0.048
 late-0.046
 That-0.043
Token our
Token ID674
Feature activation-9.41e+00

Pos logit contributions
 This+0.030
ore+0.025
 late+0.023
ires+0.023
 Today+0.023
Neg logit contributions
 forgot-0.047
 promise-0.040
 stayed-0.039
 way-0.039
 forget-0.039
Token chair
Token ID5118
Feature activation+3.42e+00

Pos logit contributions
 forgot+0.178
 stayed+0.138
 forget+0.133
ode+0.132
 regretted+0.131
Neg logit contributions
 This-0.168
ore-0.143
 late-0.141
ires-0.141
 Today-0.137
Token!"
Token ID2474
Feature activation+3.67e+00

Pos logit contributions
 This+0.039
ore+0.032
 late+0.031
 Today+0.027
ires+0.025
Neg logit contributions
 forgot-0.086
 promise-0.074
 stayed-0.074
ode-0.072
 forget-0.072
Token
Token ID198
Feature activation+5.11e+00

Pos logit contributions
 This+0.033
 late+0.023
ore+0.022
+0.019
 Today+0.018
Neg logit contributions
 forgot-0.105
ode-0.098
 promise-0.097
 forget-0.093
 stayed-0.093
Token
Token ID198
Feature activation+4.18e+00

Pos logit contributions
 This+0.067
uttering+0.062
 Today+0.057
ires+0.057
avored+0.055
Neg logit contributions
 forgot-0.110
 learned-0.096
 promise-0.094
 stayed-0.091
 way-0.091
TokenThey
Token ID2990
Feature activation-6.70e+00

Pos logit contributions
 This+0.063
ore+0.053
 late+0.050
ires+0.049
 Today+0.049
Neg logit contributions
 forgot-0.093
 promise-0.079
 way-0.077
 stayed-0.077
 forget-0.076
Token and
Token ID290
Feature activation-2.64e+00

Pos logit contributions
 This+0.049
ore+0.044
ires+0.042
iffs+0.042
 Today+0.042
Neg logit contributions
 forgot-0.072
 way-0.060
 stayed-0.060
 promise-0.060
 learned-0.059
Token sugar
Token ID7543
Feature activation+1.04e+00

Pos logit contributions
 forgot+0.047
ode+0.045
 captain+0.038
 promise+0.037
 sleeves+0.037
Neg logit contributions
 This-0.046
ore-0.036
 late-0.035
ires-0.035
 Do-0.034
Token.
Token ID13
Feature activation+3.51e+00

Pos logit contributions
 This+0.013
ore+0.011
 late+0.010
ires+0.010
ges+0.009
Neg logit contributions
 forgot-0.025
 promise-0.021
 forget-0.021
 way-0.021
ode-0.021
Token Even
Token ID3412
Feature activation-1.71e+00

Pos logit contributions
 This+0.046
ore+0.041
uttering+0.039
 late+0.038
ires+0.038
Neg logit contributions
 forgot-0.080
 promise-0.068
 way-0.068
 stayed-0.068
 forget-0.066
Token though
Token ID996
Feature activation+1.07e+00

Pos logit contributions
 forgot+0.039
 promise+0.033
 stayed+0.032
 way+0.032
 forget+0.031
Neg logit contributions
 This-0.025
ore-0.021
 Today-0.020
ires-0.020
 late-0.019
Token she
Token ID673
Feature activation-9.41e+00

Pos logit contributions
 This+0.016
ore+0.013
ires+0.013
 Today+0.013
 late+0.013
Neg logit contributions
 forgot-0.024
 promise-0.020
ode-0.020
 stayed-0.019
 forget-0.019
Token was
Token ID373
Feature activation-4.16e+00

Pos logit contributions
 passengers+0.133
 forgot+0.125
ode+0.123
 scar+0.122
 promise+0.121
Neg logit contributions
 This-0.179
-0.160
ore-0.160
 late-0.147
ires-0.147
Token only
Token ID691
Feature activation-5.24e+00

Pos logit contributions
 forgot+0.074
 promise+0.061
 stayed+0.059
 way+0.058
ode+0.058
Neg logit contributions
 This-0.078
ore-0.068
 late-0.067
ires-0.065
 Today-0.064
Token three
Token ID1115
Feature activation-2.29e+00

Pos logit contributions
 forgot+0.100
 promise+0.085
ode+0.084
 stayed+0.081
 forget+0.080
Neg logit contributions
 This-0.091
 late-0.079
ore-0.076
uttering-0.073
ires-0.072
Token years
Token ID812
Feature activation+6.80e-01

Pos logit contributions
 forgot+0.044
ode+0.038
 promise+0.037
 stayed+0.036
 forget+0.036
Neg logit contributions
 This-0.037
ore-0.032
ires-0.030
 late-0.030
ges-0.029
Token old
Token ID1468
Feature activation-1.92e+00

Pos logit contributions
 This+0.013
ore+0.011
 Today+0.011
ires+0.011
uttering+0.011
Neg logit contributions
 forgot-0.012
 promise-0.010
 way-0.010
 stayed-0.010
 forget-0.009
TokenS
Token ID50
Feature activation-2.53e+00

Pos logit contributions
 This+0.065
ore+0.059
ires+0.054
 Today+0.052
uttering+0.052
Neg logit contributions
 forgot-0.087
 stayed-0.072
 promise-0.071
 way-0.070
 forget-0.070
Tokenue
Token ID518
Feature activation-6.46e+00

Pos logit contributions
 forgot+0.040
 promise+0.033
 stayed+0.031
 way+0.031
 forget+0.030
Neg logit contributions
 This-0.053
ore-0.048
 late-0.046
 Today-0.045
ires-0.045
Token felt
Token ID2936
Feature activation-1.26e+00

Pos logit contributions
 passengers+0.100
ode+0.098
 promise+0.093
 captain+0.093
 crew+0.092
Neg logit contributions
 This-0.109
ore-0.101
-0.100
 late-0.090
ges-0.089
Token guilty
Token ID6717
Feature activation+3.69e+00

Pos logit contributions
 forgot+0.020
 promise+0.015
 stayed+0.015
 way+0.014
 forget+0.014
Neg logit contributions
 This-0.028
ore-0.025
 Today-0.024
ires-0.024
uttering-0.024
Token because
Token ID780
Feature activation-1.23e+00

Pos logit contributions
 This+0.063
uttering+0.054
ires+0.053
ore+0.053
iffs+0.053
Neg logit contributions
 forgot-0.069
 way-0.058
 stayed-0.057
 promise-0.057
 bit-0.055
Token she
Token ID673
Feature activation-9.40e+00

Pos logit contributions
 forgot+0.028
 stayed+0.024
 promise+0.024
 way+0.024
 forget+0.023
Neg logit contributions
 This-0.018
ore-0.015
 Today-0.014
uttering-0.014
ires-0.014
Token made
Token ID925
Feature activation+3.21e+00

Pos logit contributions
ode+0.115
 way+0.113
 passengers+0.111
 promise+0.109
 scar+0.103
Neg logit contributions
 This-0.189
 late-0.179
-0.169
ore-0.169
 Playing-0.165
Token the
Token ID262
Feature activation-5.81e+00

Pos logit contributions
 This+0.039
ore+0.031
 late+0.030
ires+0.029
 Today+0.027
Neg logit contributions
 forgot-0.081
 promise-0.070
ode-0.069
 stayed-0.068
 forget-0.068
Token calendar
Token ID11845
Feature activation+2.28e+00

Pos logit contributions
 forgot+0.107
 stayed+0.088
ode+0.087
 promise+0.084
 scar+0.081
Neg logit contributions
 This-0.110
ore-0.094
ires-0.092
 late-0.092
 Today-0.091
Token messy
Token ID24097
Feature activation+4.19e+00

Pos logit contributions
 This+0.039
 late+0.036
ore+0.034
 Today+0.031
uttering+0.031
Neg logit contributions
 forgot-0.042
ode-0.035
 passengers-0.034
 regretted-0.033
 stayed-0.033
Token.
Token ID13
Feature activation+3.49e+00

Pos logit contributions
 This+0.055
ore+0.045
 Today+0.042
uttering+0.042
ires+0.041
Neg logit contributions
 forgot-0.100
 way-0.086
 promise-0.086
 stayed-0.086
 forget-0.082
Token the
Token ID262
Feature activation-5.95e+00

Pos logit contributions
 forgot+0.039
 promise+0.033
 stayed+0.032
ode+0.032
 forget+0.032
Neg logit contributions
 This-0.024
ore-0.020
 late-0.019
ires-0.019
 Today-0.018
Token p
Token ID279
Feature activation-2.89e+00

Pos logit contributions
 forgot+0.098
 stayed+0.077
 hoped+0.074
 promise+0.073
ode+0.072
Neg logit contributions
 This-0.105
ore-0.099
 late-0.096
-0.095
uttering-0.087
Tokenuddle
Token ID24500
Feature activation+6.17e+00

Pos logit contributions
 forgot+0.047
 promise+0.037
 stayed+0.037
 way+0.036
 forget+0.036
Neg logit contributions
 This-0.059
ore-0.054
ires-0.051
 late-0.050
 Today-0.050
Token.
Token ID13
Feature activation+4.15e+00

Pos logit contributions
 This+0.072
ore+0.059
 Today+0.053
 late+0.053
ires+0.053
Neg logit contributions
 forgot-0.156
 promise-0.135
 stayed-0.133
 way-0.132
 forget-0.130
Token Although
Token ID4900
Feature activation+1.33e+00

Pos logit contributions
 This+0.046
uttering+0.045
ore+0.045
ires+0.042
 late+0.040
Neg logit contributions
 forgot-0.092
 way-0.079
 learned-0.077
 hoped-0.076
 stayed-0.076
Token she
Token ID673
Feature activation-9.40e+00

Pos logit contributions
 This+0.016
ore+0.013
 late+0.012
ires+0.012
+0.012
Neg logit contributions
 forgot-0.032
ode-0.028
 promise-0.028
 stayed-0.027
 forget-0.027
Token couldn
Token ID3521
Feature activation+2.78e+00

Pos logit contributions
ode+0.145
 passengers+0.144
 way+0.140
 scar+0.136
 conductor+0.132
Neg logit contributions
ore-0.129
-0.127
 This-0.117
 late-0.111
?-0.106
Token't
Token ID470
Feature activation-4.34e+00

Pos logit contributions
uttering+0.035
ires+0.035
 This+0.032
elly+0.030
ges+0.029
Neg logit contributions
 forgot-0.059
 way-0.053
 stayed-0.053
 forget-0.051
 promise-0.051
Token go
Token ID467
Feature activation+1.47e+00

Pos logit contributions
 forgot+0.078
 scar+0.069
 regretted+0.068
ode+0.067
 way+0.064
Neg logit contributions
 This-0.073
ore-0.065
 Today-0.059
ges-0.056
 late-0.055
Token for
Token ID329
Feature activation+1.95e+00

Pos logit contributions
 This+0.025
ore+0.021
ires+0.020
 Today+0.020
 Playing+0.019
Neg logit contributions
 forgot-0.030
 way-0.025
 stayed-0.025
 promise-0.025
 forget-0.024
Token a
Token ID257
Feature activation-4.59e+00

Pos logit contributions
 This+0.027
ore+0.022
 late+0.021
 Today+0.020
ires+0.020
Neg logit contributions
 forgot-0.046
 promise-0.039
 stayed-0.038
 way-0.038
 forget-0.038
Token.
Token ID13
Feature activation+3.54e+00

Pos logit contributions
 This+0.062
ore+0.051
ires+0.047
 Today+0.047
 late+0.046
Neg logit contributions
 forgot-0.112
 promise-0.096
 way-0.095
 stayed-0.095
 forget-0.092
Token Sam
Token ID3409
Feature activation-7.15e+00

Pos logit contributions
 This+0.039
ore+0.031
 Today+0.027
 late+0.027
ires+0.027
Neg logit contributions
 forgot-0.093
 promise-0.081
 stayed-0.080
 way-0.079
 forget-0.078
Token and
Token ID290
Feature activation-3.71e+00

Pos logit contributions
ode+0.109
 promise+0.098
 passengers+0.091
 forgot+0.091
 forget+0.088
Neg logit contributions
 This-0.129
ore-0.112
-0.107
 late-0.102
ges-0.102
Token Sara
Token ID24799
Feature activation-7.99e+00

Pos logit contributions
 forgot+0.090
 promise+0.082
ode+0.081
 stayed+0.076
 forget+0.075
Neg logit contributions
 This-0.048
ges-0.034
 Today-0.033
ore-0.033
 late-0.033
Token used
Token ID973
Feature activation-2.74e-01

Pos logit contributions
ode+0.118
 captain+0.102
 passengers+0.100
 way+0.096
 crew+0.096
Neg logit contributions
 This-0.133
ore-0.124
ges-0.123
-0.113
 at-0.113
Token their
Token ID511
Feature activation-9.38e+00

Pos logit contributions
 forgot+0.007
 promise+0.006
 forget+0.006
ode+0.006
 stayed+0.006
Neg logit contributions
 This-0.004
ore-0.003
 late-0.003
 Today-0.003
ires-0.003
Token creative
Token ID7325
Feature activation-4.89e+00

Pos logit contributions
 forgot+0.168
ode+0.143
 stayed+0.132
 promise+0.130
 regretted+0.130
Neg logit contributions
 This-0.175
ore-0.151
 Today-0.146
ires-0.143
uttering-0.141
Token minds
Token ID9017
Feature activation+2.40e+00

Pos logit contributions
 forgot+0.090
ode+0.073
 regretted+0.069
 stayed+0.068
 hoped+0.066
Neg logit contributions
 This-0.092
 Today-0.080
ore-0.076
uttering-0.071
ires-0.071
Token and
Token ID290
Feature activation-4.68e+00

Pos logit contributions
 This+0.029
ore+0.024
ires+0.022
 Today+0.022
 late+0.022
Neg logit contributions
 forgot-0.059
 promise-0.051
 stayed-0.050
 way-0.050
 forget-0.049
Token made
Token ID925
Feature activation+2.82e+00

Pos logit contributions
ode+0.076
 promise+0.066
 forgot+0.063
 regretted+0.056
ppa+0.053
Neg logit contributions
 This-0.082
 late-0.073
ges-0.070
ore-0.065
 Playing-0.064
Token up
Token ID510
Feature activation+8.00e-01

Pos logit contributions
 This+0.040
ore+0.033
 late+0.031
ires+0.031
uttering+0.029
Neg logit contributions
 forgot-0.066
 promise-0.056
ode-0.056
 forget-0.055
 stayed-0.054
Token take
Token ID1011
Feature activation+3.24e+00

Pos logit contributions
 forgot+0.002
ode+0.002
 regretted+0.002
 promise+0.002
 stayed+0.002
Neg logit contributions
 This-0.002
 late-0.002
ore-0.002
 Today-0.002
-0.002
Token out
Token ID503
Feature activation+4.46e+00

Pos logit contributions
 This+0.048
ore+0.040
 late+0.037
 Today+0.036
ires+0.036
Neg logit contributions
 forgot-0.074
 promise-0.062
 stayed-0.061
 forget-0.060
 way-0.060
Token the
Token ID262
Feature activation-4.50e+00

Pos logit contributions
 This+0.060
ore+0.051
 late+0.050
 Today+0.045
ires+0.044
Neg logit contributions
 forgot-0.105
ode-0.088
 promise-0.087
 stayed-0.087
 forget-0.086
Token journal
Token ID3989
Feature activation+6.98e+00

Pos logit contributions
 forgot+0.080
 stayed+0.059
 forget+0.056
 hoped+0.056
 learned+0.056
Neg logit contributions
 This-0.088
ore-0.082
 late-0.078
 Today-0.075
-0.075
Token and
Token ID290
Feature activation-2.79e+00

Pos logit contributions
 This+0.082
ore+0.068
 late+0.066
 Today+0.060
ires+0.056
Neg logit contributions
 forgot-0.174
 stayed-0.148
 promise-0.148
ode-0.145
 forget-0.144
Token write
Token ID3551
Feature activation+7.95e+00

Pos logit contributions
 forgot+0.045
ode+0.041
 regretted+0.036
 promise+0.036
 passengers+0.035
Neg logit contributions
 This-0.053
 late-0.044
ore-0.042
-0.040
 Today-0.040
Token something
Token ID1223
Feature activation+1.48e+00

Pos logit contributions
 This+0.118
ore+0.102
 Today+0.095
ires+0.094
 late+0.093
Neg logit contributions
 forgot-0.174
 promise-0.148
 stayed-0.145
 way-0.145
 forget-0.140
Token down
Token ID866
Feature activation+2.82e+00

Pos logit contributions
 This+0.026
ore+0.022
 late+0.021
ires+0.021
 Today+0.021
Neg logit contributions
 forgot-0.029
 promise-0.024
 stayed-0.024
 way-0.024
 forget-0.023
Token.
Token ID13
Feature activation+4.10e+00

Pos logit contributions
 This+0.038
ore+0.032
ires+0.030
uttering+0.030
 Today+0.030
Neg logit contributions
 forgot-0.065
 way-0.056
 promise-0.056
 stayed-0.055
 forget-0.054
Token Every
Token ID3887
Feature activation+2.40e-01

Pos logit contributions
 This+0.047
ore+0.041
uttering+0.040
ires+0.039
 late+0.036
Neg logit contributions
 forgot-0.100
 promise-0.086
 way-0.085
 stayed-0.084
 forget-0.083
Token time
Token ID640
Feature activation+4.02e+00

Pos logit contributions
 This+0.004
ore+0.003
 late+0.003
 Today+0.003
+0.003
Neg logit contributions
 forgot-0.005
ode-0.004
 promise-0.004
 forget-0.004
 stayed-0.004
Token She
Token ID1375
Feature activation-7.03e+00

Pos logit contributions
ore+0.052
uttering+0.048
ging+0.046
ach+0.045
ges+0.045
Neg logit contributions
 forgot-0.074
 way-0.062
 learned-0.062
 stayed-0.060
 hoped-0.060
Token put
Token ID1234
Feature activation+2.11e+00

Pos logit contributions
ode+0.121
 way+0.108
 passengers+0.108
 plank+0.098
 sandbox+0.097
Neg logit contributions
:-0.098
-0.091
-0.085
 at-0.085
 This-0.084
Token Anna
Token ID11735
Feature activation-4.47e+00

Pos logit contributions
 This+0.027
ore+0.023
 late+0.021
ires+0.020
 Today+0.020
Neg logit contributions
 forgot-0.052
 promise-0.045
 forget-0.043
 stayed-0.043
 way-0.043
Token on
Token ID319
Feature activation+2.29e+00

Pos logit contributions
 forgot+0.105
 promise+0.088
 way+0.087
 forget+0.086
ode+0.085
Neg logit contributions
 This-0.060
ore-0.050
 late-0.047
uttering-0.044
ges-0.044
Token her
Token ID607
Feature activation-5.30e+00

Pos logit contributions
 This+0.030
ore+0.024
 late+0.023
 Today+0.022
ires+0.022
Neg logit contributions
 forgot-0.056
 promise-0.048
 stayed-0.047
 forget-0.046
ode-0.046
Token bed
Token ID3996
Feature activation+7.77e+00

Pos logit contributions
 forgot+0.087
 stayed+0.062
 regretted+0.060
ode+0.059
 forget+0.059
Neg logit contributions
 This-0.115
ore-0.099
 Today-0.097
 late-0.094
ires-0.091
Token and
Token ID290
Feature activation-4.33e+00

Pos logit contributions
 This+0.118
ore+0.100
 late+0.098
 Today+0.092
ires+0.090
Neg logit contributions
 forgot-0.168
 promise-0.144
ode-0.140
 forget-0.140
 stayed-0.138
Token gave
Token ID2921
Feature activation+4.35e+00

Pos logit contributions
ode+0.068
 promise+0.054
chie+0.054
 passengers+0.053
 crew+0.051
Neg logit contributions
 late-0.073
 This-0.072
-0.064
 early-0.063
 with-0.063
Token her
Token ID607
Feature activation-2.94e+00

Pos logit contributions
 This+0.048
ore+0.037
 late+0.033
ires+0.032
+0.031
Neg logit contributions
 forgot-0.116
 promise-0.101
ode-0.099
 forget-0.098
 stayed-0.096
Token a
Token ID257
Feature activation-2.72e+00

Pos logit contributions
 forgot+0.071
 stayed+0.059
ode+0.058
 promise+0.058
 forget+0.058
Neg logit contributions
 This-0.039
ore-0.032
 late-0.030
 Today-0.029
-0.028
Token kiss
Token ID9245
Feature activation+4.11e+00

Pos logit contributions
 forgot+0.040
 stayed+0.031
ode+0.030
 forget+0.028
 passengers+0.027
Neg logit contributions
 This-0.061
ore-0.057
 late-0.053
 Today-0.051
-0.051
Token her
Token ID607
Feature activation-3.13e+00

Pos logit contributions
 This+0.074
ore+0.064
ires+0.062
uttering+0.062
 Today+0.061
Neg logit contributions
 forgot-0.100
 way-0.086
 promise-0.085
 stayed-0.084
 forget-0.081
Token neck
Token ID7393
Feature activation+6.50e+00

Pos logit contributions
 forgot+0.048
 stayed+0.035
 promise+0.034
ode+0.034
 forget+0.033
Neg logit contributions
 This-0.066
ore-0.059
 Today-0.056
 late-0.055
-0.055
Token and
Token ID290
Feature activation-4.11e+00

Pos logit contributions
 This+0.094
ore+0.080
 late+0.074
ires+0.074
 Today+0.074
Neg logit contributions
 forgot-0.145
 promise-0.124
 stayed-0.121
 way-0.120
 forget-0.119
Token started
Token ID2067
Feature activation+3.10e+00

Pos logit contributions
 forgot+0.057
ode+0.049
 promise+0.049
 passengers+0.044
 way+0.043
Neg logit contributions
 This-0.085
 late-0.072
ore-0.070
 Today-0.070
ires-0.069
Token to
Token ID284
Feature activation-1.32e+00

Pos logit contributions
 This+0.041
ore+0.035
ires+0.034
 Today+0.033
 late+0.031
Neg logit contributions
 forgot-0.073
 way-0.063
 stayed-0.062
 promise-0.061
 forget-0.060
Token rub
Token ID6437
Feature activation+8.37e+00

Pos logit contributions
 forgot+0.022
 promise+0.016
 regretted+0.016
 passengers+0.016
ode+0.016
Neg logit contributions
 This-0.026
 Today-0.022
ore-0.022
 late-0.021
-0.020
Token it
Token ID340
Feature activation+3.25e-01

Pos logit contributions
 This+0.140
ore+0.119
uttering+0.118
 Today+0.117
 late+0.117
Neg logit contributions
 forgot-0.165
 way-0.137
 stayed-0.137
 promise-0.136
 scar-0.133
Token.
Token ID13
Feature activation+4.43e+00

Pos logit contributions
 This+0.005
ore+0.004
ires+0.004
 late+0.004
 Today+0.004
Neg logit contributions
 forgot-0.007
 promise-0.006
 way-0.006
 stayed-0.006
 forget-0.006
Token
Token ID220
Feature activation+5.04e+00

Pos logit contributions
 This+0.051
ore+0.050
uttering+0.049
ires+0.047
 late+0.043
Neg logit contributions
 forgot-0.100
 way-0.085
 stayed-0.084
 promise-0.082
 learned-0.082
Token
Token ID198
Feature activation+4.97e+00

Pos logit contributions
 This+0.063
uttering+0.058
ore+0.058
 late+0.054
ires+0.053
Neg logit contributions
 forgot-0.101
 way-0.086
 learned-0.085
 promise-0.084
 stayed-0.083
Token
Token ID198
Feature activation+4.40e+00

Pos logit contributions
 This+0.059
ore+0.052
uttering+0.051
ires+0.051
ays+0.047
Neg logit contributions
 forgot-0.113
 learned-0.097
 way-0.096
 promise-0.096
 stayed-0.095
Token started
Token ID2067
Feature activation+2.04e+00

Pos logit contributions
 promise+0.058
ode+0.055
 forgot+0.053
 forget+0.047
 passengers+0.047
Neg logit contributions
 This-0.065
 late-0.058
ges-0.054
 selling-0.053
ore-0.052
Token to
Token ID284
Feature activation-1.75e+00

Pos logit contributions
 This+0.029
ires+0.025
ore+0.025
 Today+0.025
uttering+0.022
Neg logit contributions
 forgot-0.045
 way-0.039
 stayed-0.039
 promise-0.037
 bit-0.037
Token sort
Token ID3297
Feature activation+6.65e+00

Pos logit contributions
 forgot+0.030
 stayed+0.023
 promise+0.023
 passengers+0.023
 regretted+0.023
Neg logit contributions
 This-0.034
ore-0.028
 Today-0.027
 late-0.027
ges-0.025
Token them
Token ID606
Feature activation-1.11e+00

Pos logit contributions
 This+0.110
ore+0.096
 Today+0.091
ires+0.089
uttering+0.089
Neg logit contributions
 forgot-0.133
 promise-0.111
 way-0.111
 stayed-0.109
 forget-0.106
Token into
Token ID656
Feature activation+6.42e-01

Pos logit contributions
 forgot+0.026
 promise+0.023
 way+0.022
 stayed+0.022
 forget+0.022
Neg logit contributions
 This-0.015
ore-0.012
 Today-0.011
 late-0.011
ires-0.011
Token piles
Token ID30935
Feature activation+8.48e+00

Pos logit contributions
 This+0.012
ore+0.010
 late+0.010
ires+0.010
 Today+0.009
Neg logit contributions
 forgot-0.012
 promise-0.010
 stayed-0.010
 forget-0.009
ode-0.009
Token.
Token ID13
Feature activation+4.47e+00

Pos logit contributions
 This+0.117
ore+0.097
 Today+0.094
ires+0.090
 late+0.087
Neg logit contributions
 forgot-0.193
 way-0.166
 promise-0.166
 stayed-0.164
 forget-0.157
Token
Token ID220
Feature activation+5.10e+00

Pos logit contributions
 This+0.050
ore+0.046
ires+0.044
uttering+0.043
 late+0.041
Neg logit contributions
 forgot-0.105
 way-0.090
 stayed-0.089
 promise-0.089
 learned-0.087
Token
Token ID198
Feature activation+4.69e+00

Pos logit contributions
 This+0.059
ore+0.056
uttering+0.055
 Today+0.052
 late+0.052
Neg logit contributions
 forgot-0.107
 learned-0.089
 stayed-0.089
 way-0.088
 promise-0.087
Token
Token ID198
Feature activation+4.06e+00

Pos logit contributions
 This+0.056
ires+0.050
ore+0.050
uttering+0.047
ays+0.045
Neg logit contributions
 forgot-0.106
 learned-0.092
 stayed-0.089
 way-0.088
 promise-0.087
TokenThe
Token ID464
Feature activation-6.12e+00

Pos logit contributions
 This+0.069
ore+0.061
ires+0.058
 Today+0.057
uttering+0.055
Neg logit contributions
 forgot-0.080
 promise-0.066
 stayed-0.066
 forget-0.064
 way-0.063
Token day
Token ID1110
Feature activation+4.94e+00

Pos logit contributions
 forgot+0.024
 promise+0.020
 way+0.020
 stayed+0.020
 forget+0.019
Neg logit contributions
 This-0.024
ore-0.021
ires-0.020
 late-0.020
 Today-0.020
Token,
Token ID11
Feature activation+1.88e+00

Pos logit contributions
 This+0.083
ires+0.080
ore+0.079
uttering+0.077
ays+0.072
Neg logit contributions
 forgot-0.095
 way-0.077
 stayed-0.076
 bit-0.074
 h-0.073
Token she
Token ID673
Feature activation-6.79e+00

Pos logit contributions
 This+0.028
ore+0.023
 late+0.023
 Today+0.022
ires+0.022
Neg logit contributions
 forgot-0.041
 promise-0.036
 stayed-0.034
ode-0.034
 way-0.034
Token wanted
Token ID2227
Feature activation+3.84e+00

Pos logit contributions
 forgot+0.086
ode+0.085
 promise+0.082
 passengers+0.076
 scar+0.074
Neg logit contributions
 This-0.138
 late-0.127
-0.125
ore-0.123
 Today-0.114
Token to
Token ID284
Feature activation-5.14e-01

Pos logit contributions
 This+0.041
ore+0.033
 late+0.029
ires+0.029
 Today+0.028
Neg logit contributions
 forgot-0.102
 promise-0.089
 stayed-0.087
 way-0.086
 forget-0.086
Token write
Token ID3551
Feature activation+8.30e+00

Pos logit contributions
 forgot+0.009
 stayed+0.007
 regretted+0.007
ode+0.007
 promise+0.007
Neg logit contributions
 This-0.011
ore-0.009
 Today-0.009
 late-0.008
ires-0.008
Token more
Token ID517
Feature activation+4.81e-01

Pos logit contributions
 This+0.139
ore+0.128
uttering+0.116
ges+0.115
 Today+0.114
Neg logit contributions
 forgot-0.157
 promise-0.136
 stayed-0.136
 way-0.135
 scar-0.135
Token.
Token ID13
Feature activation+3.78e+00

Pos logit contributions
 This+0.009
ore+0.008
uttering+0.008
 late+0.008
 Today+0.008
Neg logit contributions
 forgot-0.008
 promise-0.007
 way-0.007
 stayed-0.007
 forget-0.007
Token She
Token ID1375
Feature activation-6.77e+00

Pos logit contributions
ore+0.036
uttering+0.034
 This+0.034
 late+0.033
ires+0.030
Neg logit contributions
 forgot-0.092
 way-0.083
 promise-0.081
 head-0.081
 stayed-0.079
Token looked
Token ID3114
Feature activation+2.15e+00

Pos logit contributions
ode+0.103
 forgot+0.101
 promise+0.100
 way+0.099
 forget+0.098
Neg logit contributions
 This-0.104
 late-0.096
-0.095
 On-0.090
ore-0.088
Token for
Token ID329
Feature activation+1.07e+00

Pos logit contributions
 This+0.025
ore+0.021
 late+0.019
ires+0.019
 Today+0.019
Neg logit contributions
 forgot-0.054
 promise-0.047
 stayed-0.046
 forget-0.046
 way-0.045
Token things
Token ID1243
Feature activation+2.71e+00

Pos logit contributions
 This+0.013
ore+0.011
ires+0.010
 late+0.010
ges+0.010
Neg logit contributions
 forgot-0.017
 promise-0.014
 forget-0.014
 stayed-0.014
ode-0.014
Token that
Token ID326
Feature activation-2.94e+00

Pos logit contributions
 This+0.039
ore+0.033
 Today+0.032
uttering+0.032
ires+0.031
Neg logit contributions
 forgot-0.061
 promise-0.052
 stayed-0.052
 way-0.051
 forget-0.050
Token are
Token ID389
Feature activation-1.80e+00

Pos logit contributions
 forgot+0.052
ode+0.047
 captain+0.046
 passengers+0.045
 crew+0.045
Neg logit contributions
 This-0.052
ore-0.043
-0.039
ires-0.038
 Do-0.038
Token not
Token ID407
Feature activation-3.44e+00

Pos logit contributions
 forgot+0.035
ode+0.029
 promise+0.029
 forget+0.028
 sighed+0.028
Neg logit contributions
 This-0.028
 late-0.026
ires-0.025
ore-0.022
 here-0.022
Token yours
Token ID12431
Feature activation+7.61e-01

Pos logit contributions
 forgot+0.088
 promise+0.076
ode+0.075
 forget+0.075
 sighed+0.073
Neg logit contributions
 This-0.038
 late-0.030
ires-0.027
ore-0.026
uttering-0.023
Token.
Token ID13
Feature activation+3.38e+00

Pos logit contributions
 This+0.011
uttering+0.010
ore+0.010
 late+0.010
 Today+0.009
Neg logit contributions
 forgot-0.017
 promise-0.015
 way-0.014
 stayed-0.014
 forget-0.013
Token The
Token ID383
Feature activation-6.18e+00

Pos logit contributions
uttering+0.032
ore+0.031
 This+0.031
ires+0.026
 late+0.026
Neg logit contributions
 forgot-0.083
 promise-0.073
 forget-0.071
 stayed-0.071
 learned-0.070
Token v
Token ID410
Feature activation-5.66e-01

Pos logit contributions
 forgot+0.110
ode+0.085
 stayed+0.084
 forget+0.079
 sighed+0.079
Neg logit contributions
 This-0.118
 late-0.101
-0.098
ore-0.098
 Today-0.097
Tokenase
Token ID589
Feature activation-1.64e+00

Pos logit contributions
 forgot+0.013
 promise+0.011
 way+0.011
 stayed+0.011
 forget+0.011
Neg logit contributions
 This-0.008
ore-0.007
ires-0.006
 late-0.006
 Today-0.006
Token was
Token ID373
Feature activation-1.65e+00

Pos logit contributions
 forgot+0.033
 passengers+0.033
 scar+0.032
ode+0.032
 captain+0.031
Neg logit contributions
 This-0.021
ore-0.019
 late-0.016
-0.015
?-0.015
Token very
Token ID845
Feature activation-2.45e+00

Pos logit contributions
 forgot+0.032
ode+0.027
 promise+0.026
 forget+0.026
 stayed+0.025
Neg logit contributions
 This-0.027
 late-0.026
ires-0.023
ore-0.022
 Today-0.021
Token a
Token ID257
Feature activation-3.25e+00

Pos logit contributions
 This+0.017
ore+0.014
 late+0.014
 Today+0.013
+0.013
Neg logit contributions
 forgot-0.032
 promise-0.029
ode-0.028
 stayed-0.028
 way-0.027
Token bee
Token ID20697
Feature activation-1.30e+00

Pos logit contributions
 forgot+0.068
ode+0.058
 stayed+0.057
 hoped+0.056
 promise+0.056
Neg logit contributions
 This-0.049
 late-0.042
ore-0.042
-0.039
 Today-0.039
Token flew
Token ID13112
Feature activation+3.42e+00

Pos logit contributions
 forgot+0.021
 promise+0.018
 way+0.017
 forget+0.016
ode+0.016
Neg logit contributions
 This-0.026
ore-0.023
-0.022
 late-0.022
ges-0.021
Token by
Token ID416
Feature activation+1.61e+00

Pos logit contributions
 This+0.054
ore+0.047
ires+0.045
 Today+0.044
 Playing+0.043
Neg logit contributions
 forgot-0.070
 stayed-0.060
 way-0.059
 promise-0.058
 bit-0.057
Token her
Token ID607
Feature activation-4.76e+00

Pos logit contributions
 This+0.032
ires+0.028
ore+0.027
 Today+0.027
 Playing+0.026
Neg logit contributions
 forgot-0.027
 way-0.023
 stayed-0.023
 promise-0.022
 bit-0.022
Token.
Token ID13
Feature activation+4.59e+00

Pos logit contributions
 forgot+0.070
 stayed+0.051
ode+0.047
 promise+0.047
 learned+0.046
Neg logit contributions
 This-0.109
ore-0.097
 Today-0.093
ires-0.093
ummy-0.090
Token Jenny
Token ID28437
Feature activation-6.47e+00

Pos logit contributions
ore+0.068
uttering+0.067
 This+0.066
ires+0.066
ithering+0.063
Neg logit contributions
 forgot-0.092
 way-0.074
 learned-0.073
 forget-0.071
 stayed-0.069
Token felt
Token ID2936
Feature activation-1.41e+00

Pos logit contributions
 promise+0.091
ode+0.085
 passengers+0.083
 forgot+0.083
 captain+0.078
Neg logit contributions
 This-0.125
ore-0.113
-0.111
ges-0.107
 late-0.100
Token a
Token ID257
Feature activation-3.06e+00

Pos logit contributions
 forgot+0.025
 promise+0.020
 stayed+0.020
 way+0.019
 forget+0.019
Neg logit contributions
 This-0.028
ore-0.025
ires-0.024
 Today-0.024
uttering-0.023
Token bit
Token ID1643
Feature activation+9.48e-01

Pos logit contributions
 forgot+0.043
ode+0.036
 passengers+0.034
 stayed+0.033
 hoped+0.031
Neg logit contributions
 This-0.062
ore-0.059
 late-0.056
uttering-0.055
 Today-0.053
Token scared
Token ID12008
Feature activation+4.75e+00

Pos logit contributions
 This+0.019
ore+0.017
 late+0.016
 Today+0.016
ires+0.015
Neg logit contributions
 forgot-0.016
 promise-0.013
 stayed-0.013
 way-0.013
ode-0.012
Token-
Token ID12
Feature activation+2.22e+00

Pos logit contributions
 This+0.097
ore+0.078
 Today+0.076
uttering+0.074
ires+0.074
Neg logit contributions
 forgot-0.158
 promise-0.134
 stayed-0.132
 way-0.132
 bit-0.128
Tokenof
Token ID1659
Feature activation+2.64e+00

Pos logit contributions
 This+0.038
 Today+0.033
ore+0.033
ires+0.033
 late+0.032
Neg logit contributions
 forgot-0.042
 stayed-0.034
 promise-0.034
 way-0.034
 forget-0.033
Token-
Token ID12
Feature activation+2.06e+00

Pos logit contributions
 This+0.041
ore+0.035
 late+0.034
 Today+0.034
uttering+0.033
Neg logit contributions
 forgot-0.055
 promise-0.047
 stayed-0.046
 way-0.046
 bit-0.044
Tokenwar
Token ID5767
Feature activation+1.01e+01

Pos logit contributions
 This+0.037
 Today+0.032
ore+0.032
ires+0.031
 late+0.031
Neg logit contributions
 forgot-0.039
 stayed-0.031
 promise-0.031
 way-0.031
 forget-0.030
Token!"
Token ID2474
Feature activation+4.05e+00

Pos logit contributions
 This+0.134
ore+0.114
ires+0.109
 Today+0.109
uttering+0.108
Neg logit contributions
 forgot-0.229
 stayed-0.195
 promise-0.194
 way-0.193
 bit-0.187
Token
Token ID198
Feature activation+5.59e+00

Pos logit contributions
 This+0.034
ore+0.022
 late+0.020
 Today+0.018
+0.018
Neg logit contributions
 forgot-0.120
 promise-0.108
ode-0.106
 stayed-0.105
 forget-0.104
Token
Token ID198
Feature activation+4.51e+00

Pos logit contributions
 This+0.069
uttering+0.065
ires+0.061
ore+0.057
ocol+0.056
Neg logit contributions
 forgot-0.125
 way-0.108
 promise-0.107
 learned-0.106
 stayed-0.103
TokenThe
Token ID464
Feature activation-6.00e+00

Pos logit contributions
 This+0.060
 late+0.049
ore+0.046
 Playing+0.043
 Today+0.043
Neg logit contributions
 forgot-0.106
 promise-0.092
 way-0.091
 stayed-0.089
ode-0.089
Token birds
Token ID10087
Feature activation-3.43e+00

Pos logit contributions
 forgot+0.103
ode+0.080
 promise+0.078
 regretted+0.075
 forget+0.075
Neg logit contributions
 This-0.117
-0.104
uttering-0.102
ires-0.101
 Today-0.101
Token agreed
Token ID4987
Feature activation+3.46e+00

Pos logit contributions
 forgot+0.048
ode+0.043
 way+0.043
 promise+0.039
 forget+0.039
Neg logit contributions
ges-0.061
 This-0.061
ore-0.060
uttering-0.059
overed-0.056
Token and
Token ID290
Feature activation-3.67e+00

Pos logit contributions
 This+0.050
ore+0.041
 late+0.039
 Today+0.038
ires+0.037
Neg logit contributions
 forgot-0.078
 promise-0.066
ode-0.065
 forget-0.064
 stayed-0.064
Token.
Token ID13
Feature activation+2.87e+00

Pos logit contributions
 This+0.081
ore+0.070
ires+0.067
 late+0.065
 Today+0.064
Neg logit contributions
 forgot-0.127
 stayed-0.111
 way-0.110
 promise-0.108
 head-0.104
Token She
Token ID1375
Feature activation-7.13e+00

Pos logit contributions
ore+0.039
uttering+0.038
ires+0.035
ithering+0.034
arling+0.034
Neg logit contributions
 forgot-0.059
 way-0.057
 stayed-0.052
 head-0.051
 forget-0.051
Token sang
Token ID25889
Feature activation+5.67e+00

Pos logit contributions
ode+0.105
 promise+0.092
 forgot+0.085
 captain+0.079
 forget+0.077
Neg logit contributions
 This-0.141
-0.126
ore-0.123
 Playing-0.119
 late-0.117
Token so
Token ID523
Feature activation+1.16e+00

Pos logit contributions
 This+0.108
ore+0.101
ires+0.094
 Today+0.092
uttering+0.092
Neg logit contributions
 forgot-0.095
 stayed-0.078
 way-0.077
 scar-0.075
 learned-0.074
Token many
Token ID867
Feature activation-1.38e+00

Pos logit contributions
 This+0.019
ore+0.016
 late+0.015
ires+0.015
 Today+0.015
Neg logit contributions
 forgot-0.024
 promise-0.020
 stayed-0.020
 way-0.020
 forget-0.019
Token songs
Token ID7259
Feature activation+4.57e+00

Pos logit contributions
 forgot+0.026
ode+0.022
 promise+0.021
 forget+0.020
 stayed+0.020
Neg logit contributions
 This-0.024
ore-0.022
ires-0.021
 late-0.020
 Playing-0.020
Token that
Token ID326
Feature activation-1.55e+00

Pos logit contributions
 This+0.064
ore+0.055
 late+0.051
ires+0.051
 Today+0.051
Neg logit contributions
 forgot-0.103
 stayed-0.088
 promise-0.087
 way-0.086
 forget-0.084
Token all
Token ID477
Feature activation-2.89e+00

Pos logit contributions
 forgot+0.034
 promise+0.030
ode+0.030
 forget+0.027
 way+0.027
Neg logit contributions
 This-0.023
ore-0.019
 late-0.018
 Today-0.017
-0.017
Token of
Token ID286
Feature activation-1.74e+00

Pos logit contributions
 forgot+0.061
 promise+0.053
ode+0.052
 stayed+0.050
 forget+0.049
Neg logit contributions
 This-0.046
ore-0.039
 late-0.037
 Today-0.036
ires-0.035
Token the
Token ID262
Feature activation-5.16e+00

Pos logit contributions
 forgot+0.042
 promise+0.036
 stayed+0.034
 forget+0.034
 way+0.034
Neg logit contributions
 This-0.023
ore-0.019
 late-0.018
ires-0.018
 Today-0.018
Token neighborhood
Token ID6232
Feature activation+7.31e-01

Pos logit contributions
 forgot+0.094
 promise+0.080
ode+0.079
 stayed+0.075
 hoped+0.071
Neg logit contributions
 This-0.087
 late-0.081
-0.078
 Today-0.075
ires-0.074
Token wondered
Token ID14028
Feature activation+3.32e+00

Pos logit contributions
ode+0.121
 way+0.106
 promise+0.104
 passengers+0.102
 crew+0.097
Neg logit contributions
-0.103
 This-0.101
-0.094
 She-0.091
?-0.089
Token what
Token ID644
Feature activation+1.30e+00

Pos logit contributions
 This+0.047
ore+0.039
 late+0.036
 Today+0.036
ires+0.036
Neg logit contributions
 forgot-0.076
 promise-0.065
 stayed-0.064
 way-0.063
 forget-0.062
Token he
Token ID339
Feature activation-6.56e+00

Pos logit contributions
 This+0.023
ore+0.020
 late+0.018
ires+0.018
 Today+0.018
Neg logit contributions
 forgot-0.025
 promise-0.021
ode-0.020
 forget-0.020
 stayed-0.020
Token was
Token ID373
Feature activation-3.12e+00

Pos logit contributions
 forgot+0.083
 promise+0.065
 way+0.064
ode+0.061
 forget+0.060
Neg logit contributions
 This-0.150
ore-0.137
-0.132
 Today-0.130
ires-0.130
Token dreaming
Token ID28368
Feature activation+3.82e+00

Pos logit contributions
 forgot+0.068
 way+0.058
 stayed+0.057
 promise+0.057
 forget+0.055
Neg logit contributions
 This-0.049
ore-0.044
ires-0.040
 Today-0.040
uttering-0.039
Token about
Token ID546
Feature activation+3.62e+00

Pos logit contributions
 This+0.055
ore+0.046
ires+0.043
uttering+0.043
 Today+0.043
Neg logit contributions
 forgot-0.085
 promise-0.073
 way-0.073
 stayed-0.072
 forget-0.069
Token.
Token ID13
Feature activation+4.47e+00

Pos logit contributions
 This+0.055
uttering+0.047
ore+0.047
 Today+0.046
 late+0.045
Neg logit contributions
 forgot-0.075
 way-0.065
 stayed-0.065
 promise-0.062
 scar-0.061
Token
Token ID198
Feature activation+4.89e+00

Pos logit contributions
uttering+0.061
ore+0.055
ires+0.052
ach+0.052
overed+0.051
Neg logit contributions
 forgot-0.090
 hoped-0.077
 learned-0.077
 way-0.076
 promise-0.073
Token
Token ID198
Feature activation+4.37e+00

Pos logit contributions
 This+0.072
uttering+0.064
avored+0.060
ires+0.060
ays+0.060
Neg logit contributions
 forgot-0.094
 learned-0.084
 promise-0.082
 way-0.080
 hoped-0.079
TokenOne
Token ID3198
Feature activation-1.27e+00

Pos logit contributions
 This+0.074
ore+0.064
ires+0.060
ays+0.060
uttering+0.058
Neg logit contributions
 forgot-0.085
 promise-0.072
 stayed-0.070
 learned-0.069
 forget-0.068
Token day
Token ID1110
Feature activation+4.60e+00

Pos logit contributions
 forgot+0.024
 promise+0.020
 way+0.019
 stayed+0.019
 forget+0.018
Neg logit contributions
 This-0.023
ore-0.020
ires-0.019
 late-0.019
 Today-0.019
Token after
Token ID706
Feature activation+3.59e+00

Pos logit contributions
 This+0.038
ore+0.032
ires+0.031
 Today+0.031
uttering+0.030
Neg logit contributions
 forgot-0.046
 promise-0.039
 way-0.038
 stayed-0.038
 forget-0.036
Token her
Token ID607
Feature activation-4.09e+00

Pos logit contributions
 This+0.065
ore+0.061
 Today+0.059
uttering+0.059
elly+0.057
Neg logit contributions
 forgot-0.062
 way-0.051
 stayed-0.051
 h-0.048
 learned-0.047
Token.
Token ID13
Feature activation+4.27e+00

Pos logit contributions
 forgot+0.103
 promise+0.090
 stayed+0.088
 way+0.088
 forget+0.086
Neg logit contributions
 This-0.049
ore-0.040
ires-0.036
 late-0.036
 Today-0.036
Token He
Token ID679
Feature activation-7.32e+00

Pos logit contributions
uttering+0.070
ore+0.064
used+0.060
ges+0.058
ging+0.058
Neg logit contributions
 forgot-0.081
 way-0.068
 hoped-0.068
 learned-0.067
 head-0.063
Token wanted
Token ID2227
Feature activation+2.86e+00

Pos logit contributions
ode+0.133
 passengers+0.115
 promise+0.113
 crew+0.111
 way+0.105
Neg logit contributions
 with-0.097
 at-0.085
-0.084
 late-0.083
 This-0.079
Token to
Token ID284
Feature activation-1.12e+00

Pos logit contributions
 This+0.032
ore+0.024
 late+0.023
 Today+0.020
ires+0.020
Neg logit contributions
 forgot-0.075
 promise-0.066
ode-0.064
 forget-0.064
 stayed-0.063
Token give
Token ID1577
Feature activation+4.83e+00

Pos logit contributions
 forgot+0.021
ode+0.019
 regretted+0.019
 sighed+0.018
 crew+0.017
Neg logit contributions
 This-0.019
ore-0.014
 Today-0.014
iffs-0.014
 late-0.013
Token it
Token ID340
Feature activation+3.00e-01

Pos logit contributions
 This+0.069
ore+0.058
 late+0.054
 Today+0.054
ires+0.054
Neg logit contributions
 forgot-0.110
 promise-0.094
 stayed-0.092
 way-0.092
 forget-0.090
Token back
Token ID736
Feature activation+2.30e+00

Pos logit contributions
 This+0.006
ore+0.005
 late+0.005
 Today+0.005
ires+0.005
Neg logit contributions
 forgot-0.005
 promise-0.004
 stayed-0.004
 way-0.004
 forget-0.004
Token to
Token ID284
Feature activation+8.77e-01

Pos logit contributions
 This+0.029
ore+0.024
 Today+0.022
ires+0.022
uttering+0.021
Neg logit contributions
 forgot-0.057
 promise-0.049
 way-0.049
 stayed-0.049
 forget-0.047
Token her
Token ID607
Feature activation-3.20e+00

Pos logit contributions
 This+0.014
ore+0.012
 late+0.012
 Today+0.012
ires+0.012
Neg logit contributions
 forgot-0.018
 promise-0.015
 stayed-0.015
 way-0.015
 forget-0.015
Token "
Token ID366
Feature activation+1.87e+00

Pos logit contributions
uttering+0.057
ore+0.057
 This+0.055
ires+0.054
ges+0.049
Neg logit contributions
 forgot-0.101
 way-0.087
 stayed-0.084
 learned-0.084
 head-0.084
TokenYou
Token ID1639
Feature activation-4.82e+00

Pos logit contributions
 This+0.030
ore+0.027
ires+0.026
 Today+0.026
uttering+0.025
Neg logit contributions
 forgot-0.037
 stayed-0.031
 forget-0.030
 promise-0.030
 learned-0.030
Token are
Token ID389
Feature activation-3.09e+00

Pos logit contributions
 forgot+0.087
ode+0.076
 scar+0.076
 way+0.075
 sighed+0.074
Neg logit contributions
 This-0.085
ore-0.066
-0.063
 That-0.062
 Today-0.058
Token too
Token ID1165
Feature activation-1.54e+00

Pos logit contributions
 forgot+0.063
 promise+0.056
ode+0.053
 regretted+0.051
 stayed+0.051
Neg logit contributions
 This-0.049
 late-0.043
 Do-0.037
ires-0.037
 Playing-0.036
Token loud
Token ID7812
Feature activation+5.62e+00

Pos logit contributions
 forgot+0.027
 way+0.022
 promise+0.021
 bit+0.021
 forget+0.021
Neg logit contributions
 This-0.030
ore-0.027
ires-0.026
 Today-0.026
uttering-0.025
Token and
Token ID290
Feature activation-3.17e+00

Pos logit contributions
 This+0.107
uttering+0.106
ires+0.103
ore+0.099
ithering+0.095
Neg logit contributions
 forgot-0.087
 way-0.074
 stayed-0.072
 h-0.071
 bit-0.069
Token messy
Token ID24097
Feature activation+4.62e+00

Pos logit contributions
 forgot+0.056
 promise+0.046
 way+0.045
 stayed+0.045
ode+0.044
Neg logit contributions
 This-0.060
ore-0.053
 late-0.051
ires-0.050
 Today-0.049
Token.
Token ID13
Feature activation+3.10e+00

Pos logit contributions
 This+0.077
uttering+0.071
ore+0.068
ires+0.064
 Today+0.064
Neg logit contributions
 forgot-0.085
 way-0.072
 stayed-0.072
 head-0.071
 h-0.070
Token Go
Token ID1514
Feature activation-5.99e-01

Pos logit contributions
 This+0.030
ore+0.028
uttering+0.027
 late+0.025
ires+0.025
Neg logit contributions
 forgot-0.078
 stayed-0.068
 promise-0.068
 forget-0.067
 way-0.066
Token play
Token ID711
Feature activation+4.37e+00

Pos logit contributions
 forgot+0.008
 promise+0.006
 stayed+0.006
 way+0.006
 forget+0.006
Neg logit contributions
 This-0.014
ore-0.012
ires-0.012
 Today-0.012
uttering-0.012
Token somewhere
Token ID7382
Feature activation+2.16e+00

Pos logit contributions
 This+0.059
ore+0.050
ires+0.048
uttering+0.047
 Today+0.047
Neg logit contributions
 forgot-0.099
 promise-0.088
 way-0.085
 stayed-0.085
 bit-0.082
Token fun
Token ID1257
Feature activation+1.96e+00

Pos logit contributions
 forgot+0.044
 promise+0.038
 forget+0.036
 stayed+0.036
ode+0.035
Neg logit contributions
 This-0.025
 late-0.020
ore-0.019
 Today-0.019
-0.018
Token playing
Token ID2712
Feature activation+5.25e+00

Pos logit contributions
 This+0.030
ore+0.027
ires+0.025
 Today+0.024
 late+0.024
Neg logit contributions
 forgot-0.042
 way-0.036
 stayed-0.035
 learned-0.034
 promise-0.034
Token with
Token ID351
Feature activation-1.56e-01

Pos logit contributions
 This+0.069
ore+0.057
 Today+0.053
ires+0.053
 late+0.052
Neg logit contributions
 forgot-0.124
 promise-0.106
 stayed-0.106
 way-0.106
 forget-0.102
Token clay
Token ID21558
Feature activation+3.74e+00

Pos logit contributions
 forgot+0.004
 promise+0.003
 forget+0.003
 stayed+0.003
 regretted+0.003
Neg logit contributions
 This-0.002
ore-0.002
-0.002
ires-0.002
ges-0.002
Token on
Token ID319
Feature activation+9.05e-01

Pos logit contributions
 This+0.041
ore+0.035
ires+0.031
+0.030
 late+0.029
Neg logit contributions
 forgot-0.097
 promise-0.085
 stayed-0.082
 forget-0.082
 way-0.079
Token the
Token ID262
Feature activation-3.21e+00

Pos logit contributions
 This+0.016
ore+0.015
uttering+0.015
ires+0.014
 Today+0.014
Neg logit contributions
 forgot-0.015
 way-0.014
 stayed-0.013
 bit-0.012
 promise-0.012
Token lawn
Token ID21133
Feature activation+4.93e+00

Pos logit contributions
 forgot+0.055
 promise+0.042
 stayed+0.041
 forget+0.039
 hoped+0.038
Neg logit contributions
 This-0.066
ore-0.058
ires-0.056
 late-0.056
 Today-0.055
Token.
Token ID13
Feature activation+3.91e+00

Pos logit contributions
 This+0.054
ore+0.043
 Today+0.038
 late+0.037
ires+0.037
Neg logit contributions
 forgot-0.130
 promise-0.113
 stayed-0.110
 way-0.109
 forget-0.109
Token
Token ID220
Feature activation+4.82e+00

Pos logit contributions
 This+0.047
ore+0.044
uttering+0.041
 late+0.040
ires+0.039
Neg logit contributions
 forgot-0.092
 way-0.080
 stayed-0.078
 promise-0.076
 forget-0.074
Token
Token ID198
Feature activation+4.65e+00

Pos logit contributions
 This+0.061
uttering+0.055
ore+0.055
ocol+0.053
used+0.051
Neg logit contributions
 forgot-0.099
 way-0.086
 promise-0.083
 stayed-0.082
 hoped-0.082
Token
Token ID198
Feature activation+4.23e+00

Pos logit contributions
 This+0.058
ore+0.053
ires+0.052
uttering+0.050
ocol+0.046
Neg logit contributions
 forgot-0.102
 way-0.089
 stayed-0.086
 passengers-0.085
 learned-0.085
Token great
Token ID1049
Feature activation-4.90e+00

Pos logit contributions
 forgot+0.124
ode+0.116
 heads+0.109
 stayed+0.107
 argued+0.103
Neg logit contributions
 This-0.077
 Today-0.060
 late-0.059
-0.058
ore-0.053
Token time
Token ID640
Feature activation+3.62e+00

Pos logit contributions
 forgot+0.105
ode+0.087
 stayed+0.085
 forget+0.082
 promise+0.081
Neg logit contributions
 This-0.080
 Today-0.067
ore-0.066
 late-0.062
uttering-0.060
Token picking
Token ID10868
Feature activation+3.65e+00

Pos logit contributions
 This+0.050
ore+0.042
ires+0.040
 Today+0.039
 late+0.037
Neg logit contributions
 forgot-0.083
 stayed-0.071
 promise-0.070
 way-0.070
 forget-0.069
Token out
Token ID503
Feature activation+2.53e+00

Pos logit contributions
 This+0.052
ore+0.044
 Today+0.042
 late+0.041
uttering+0.041
Neg logit contributions
 forgot-0.079
 way-0.070
 promise-0.069
 stayed-0.068
 scar-0.066
Token her
Token ID607
Feature activation-5.44e+00

Pos logit contributions
 This+0.035
ore+0.029
ires+0.027
 late+0.027
 Today+0.025
Neg logit contributions
 forgot-0.059
 promise-0.050
 stayed-0.049
ode-0.049
 forget-0.048
Token toy
Token ID13373
Feature activation-9.75e-02

Pos logit contributions
 forgot+0.089
 promise+0.069
 stayed+0.068
 forget+0.066
 way+0.066
Neg logit contributions
 This-0.112
ore-0.100
ires-0.096
 Today-0.095
 late-0.094
Token and
Token ID290
Feature activation-3.11e+00

Pos logit contributions
 forgot+0.002
 promise+0.002
 stayed+0.002
 forget+0.002
 way+0.002
Neg logit contributions
 This-0.001
ore-0.001
ires-0.001
 Today-0.001
 late-0.001
Token she
Token ID673
Feature activation-7.26e+00

Pos logit contributions
 forgot+0.063
 promise+0.057
ode+0.056
 scar+0.052
 way+0.052
Neg logit contributions
 This-0.048
ore-0.039
 late-0.039
ires-0.037
 Playing-0.036
Token couldn
Token ID3521
Feature activation+3.12e+00

Pos logit contributions
ode+0.114
 scar+0.101
 passengers+0.097
 captain+0.087
 forgot+0.087
Neg logit contributions
 This-0.131
ore-0.109
 late-0.108
-0.106
 That-0.101
Token't
Token ID470
Feature activation-3.85e+00

Pos logit contributions
uttering+0.042
ires+0.040
ore+0.037
ges+0.037
 This+0.036
Neg logit contributions
 forgot-0.066
 forget-0.059
 stayed-0.058
 way-0.058
 promise-0.057
Token wait
Token ID4043
Feature activation+2.40e+00

Pos logit contributions
 forgot+0.051
 scar+0.046
 way+0.042
 regretted+0.040
ode+0.040
Neg logit contributions
 This-0.086
 Today-0.074
ore-0.072
ges-0.068
 On-0.067
Token relieved
Token ID22598
Feature activation+3.76e+00

Pos logit contributions
 forgot+0.046
 promise+0.036
 stayed+0.035
 forget+0.033
 learned+0.032
Neg logit contributions
 This-0.064
ore-0.057
 Today-0.056
ires-0.055
uttering-0.053
Token,
Token ID11
Feature activation+1.08e+00

Pos logit contributions
 This+0.057
ore+0.050
ires+0.047
 Today+0.047
uttering+0.046
Neg logit contributions
 forgot-0.081
 stayed-0.068
 promise-0.067
 way-0.067
 forget-0.065
Token and
Token ID290
Feature activation-2.67e+00

Pos logit contributions
 This+0.012
 late+0.010
ore+0.008
 Today+0.008
 Do+0.008
Neg logit contributions
 forgot-0.027
ode-0.025
 promise-0.024
 stayed-0.023
 passengers-0.023
Token Sue
Token ID26089
Feature activation-6.84e+00

Pos logit contributions
ode+0.062
 forgot+0.057
 promise+0.055
 passengers+0.053
 scar+0.052
Neg logit contributions
 This-0.032
 late-0.028
ore-0.023
ires-0.020
 That-0.020
Token was
Token ID373
Feature activation-3.49e+00

Pos logit contributions
ode+0.090
 passengers+0.086
 scar+0.082
 way+0.079
 forgot+0.076
Neg logit contributions
 This-0.125
-0.116
:-0.110
ore-0.109
-0.109
Token feeling
Token ID4203
Feature activation-6.19e-01

Pos logit contributions
 forgot+0.063
ode+0.052
 promise+0.051
 scar+0.050
 way+0.050
Neg logit contributions
 This-0.064
 late-0.058
ore-0.055
uttering-0.052
 Today-0.050
Token much
Token ID881
Feature activation-3.23e+00

Pos logit contributions
 forgot+0.011
 promise+0.009
 stayed+0.008
 way+0.008
 forget+0.008
Neg logit contributions
 This-0.012
ore-0.011
 late-0.010
 Today-0.010
ires-0.010
Token better
Token ID1365
Feature activation+9.97e-01

Pos logit contributions
 forgot+0.054
ode+0.044
 stayed+0.043
 passengers+0.042
 way+0.041
Neg logit contributions
 This-0.061
 late-0.058
ore-0.055
 Today-0.052
-0.052
Token too
Token ID1165
Feature activation-1.19e-01

Pos logit contributions
 This+0.014
ore+0.011
ires+0.010
 Today+0.010
 Playing+0.010
Neg logit contributions
 forgot-0.024
 promise-0.021
 stayed-0.020
 forget-0.020
 way-0.020
Token!
Token ID0
Feature activation+3.40e+00

Pos logit contributions
 forgot+0.003
 way+0.002
 promise+0.002
 forget+0.002
 bit+0.002
Neg logit contributions
 This-0.002
ore-0.002
ires-0.002
iffs-0.002
uttering-0.001
Token They
Token ID1119
Feature activation-6.95e+00

Pos logit contributions
ore+0.034
uttering+0.034
 This+0.033
ires+0.031
ges+0.029
Neg logit contributions
 forgot-0.083
 way-0.070
 learned-0.070
 forget-0.068
 stayed-0.068
Token tide
Token ID20013
Feature activation+1.55e+00

Pos logit contributions
 forgot+0.097
 stayed+0.078
ode+0.072
 learned+0.071
 promise+0.071
Neg logit contributions
 This-0.103
ore-0.099
ires-0.098
 late-0.097
-0.093
Token.
Token ID13
Feature activation+3.79e+00

Pos logit contributions
 This+0.018
ore+0.015
 late+0.013
 Today+0.013
ires+0.013
Neg logit contributions
 forgot-0.039
 promise-0.034
 stayed-0.033
 way-0.032
 forget-0.032
Token The
Token ID383
Feature activation-5.58e+00

Pos logit contributions
uttering+0.051
ore+0.049
 This+0.045
ges+0.044
ires+0.044
Neg logit contributions
 forgot-0.078
 way-0.069
 promise-0.067
 learned-0.065
 forget-0.063
Token tide
Token ID20013
Feature activation-1.10e-01

Pos logit contributions
 forgot+0.113
ode+0.095
 stayed+0.092
 promise+0.091
 scar+0.090
Neg logit contributions
 This-0.076
ore-0.075
 late-0.075
-0.073
ires-0.072
Token was
Token ID373
Feature activation-1.69e+00

Pos logit contributions
ode+0.002
 forgot+0.002
 promise+0.002
 scar+0.002
 passengers+0.002
Neg logit contributions
 This-0.002
ore-0.002
-0.001
ges-0.001
 late-0.001
Token the
Token ID262
Feature activation-4.43e+00

Pos logit contributions
 forgot+0.033
 promise+0.027
 forget+0.026
ode+0.026
 stayed+0.026
Neg logit contributions
 This-0.029
 late-0.026
ore-0.026
ires-0.024
uttering-0.024
Token water
Token ID1660
Feature activation+7.97e-01

Pos logit contributions
 forgot+0.084
 sighed+0.065
 learned+0.064
 stayed+0.063
 hugged+0.062
Neg logit contributions
 late-0.072
uttering-0.065
 This-0.065
ires-0.064
ore-0.062
Token that
Token ID326
Feature activation-2.22e+00

Pos logit contributions
 This+0.013
ore+0.011
 late+0.010
 Today+0.010
ires+0.010
Neg logit contributions
 forgot-0.017
 promise-0.014
 stayed-0.014
 way-0.014
 forget-0.014
Token came
Token ID1625
Feature activation+1.87e+00

Pos logit contributions
ode+0.041
 forgot+0.040
 promise+0.039
 scar+0.035
 passengers+0.034
Neg logit contributions
 This-0.035
ore-0.030
 late-0.030
-0.028
ges-0.026
Token and
Token ID290
Feature activation-2.96e+00

Pos logit contributions
 This+0.031
ore+0.027
ires+0.025
 Today+0.025
 Playing+0.025
Neg logit contributions
 forgot-0.038
 way-0.033
 stayed-0.033
 promise-0.031
 head-0.031
Token went
Token ID1816
Feature activation+1.44e+00

Pos logit contributions
 forgot+0.055
 promise+0.050
ode+0.050
 way+0.046
 forget+0.045
Neg logit contributions
 This-0.049
 late-0.044
ore-0.043
-0.040
ges-0.039
Token from
Token ID422
Feature activation-7.60e-01

Pos logit contributions
 This+0.078
ore+0.069
 late+0.064
 Today+0.063
ires+0.062
Neg logit contributions
 forgot-0.102
 promise-0.084
 stayed-0.083
 way-0.082
 forget-0.081
Token the
Token ID262
Feature activation-4.82e+00

Pos logit contributions
 forgot+0.016
 way+0.014
 stayed+0.013
 promise+0.013
 forget+0.013
Neg logit contributions
 This-0.012
ore-0.010
 Today-0.010
ires-0.010
uttering-0.009
Token ground
Token ID2323
Feature activation+4.98e+00

Pos logit contributions
 forgot+0.080
 promise+0.061
 stayed+0.058
 passengers+0.057
 scar+0.056
Neg logit contributions
 This-0.101
-0.087
ore-0.083
 late-0.083
 Today-0.079
Token and
Token ID290
Feature activation-3.85e+00

Pos logit contributions
 This+0.068
ore+0.056
ires+0.052
 Today+0.052
 late+0.051
Neg logit contributions
 forgot-0.117
 promise-0.100
 stayed-0.098
 way-0.098
 forget-0.096
Token opened
Token ID4721
Feature activation+2.43e+00

Pos logit contributions
 promise+0.056
ode+0.051
 passengers+0.049
 forgot+0.048
 crew+0.044
Neg logit contributions
 This-0.074
 late-0.066
ges-0.064
-0.063
ore-0.063
Token the
Token ID262
Feature activation-5.26e+00

Pos logit contributions
 This+0.045
ore+0.043
 Playing+0.041
uttering+0.041
 Today+0.041
Neg logit contributions
 forgot-0.038
 way-0.034
 stayed-0.031
 bit-0.031
 hoped-0.031
Token cherry
Token ID23612
Feature activation+3.50e-01

Pos logit contributions
 forgot+0.084
 promise+0.063
 stayed+0.063
 forget+0.060
 way+0.059
Neg logit contributions
 This-0.114
ore-0.100
 Today-0.096
 late-0.095
-0.095
Token by
Token ID416
Feature activation+3.19e-01

Pos logit contributions
 This+0.009
ore+0.008
 Today+0.008
ires+0.008
 late+0.008
Neg logit contributions
 forgot-0.004
 promise-0.003
 way-0.003
 stayed-0.003
 forget-0.003
Token smashing
Token ID35233
Feature activation+3.47e+00

Pos logit contributions
 This+0.005
ore+0.005
ires+0.004
 Playing+0.004
 late+0.004
Neg logit contributions
 forgot-0.007
 way-0.006
 promise-0.006
 stayed-0.006
 head-0.005
Token the
Token ID262
Feature activation-4.40e+00

Pos logit contributions
 This+0.054
ore+0.047
 Today+0.044
ires+0.044
 late+0.044
Neg logit contributions
 forgot-0.073
 promise-0.061
 way-0.061
 stayed-0.061
 forget-0.059
Token rock
Token ID3881
Feature activation+2.83e+00

Pos logit contributions
 forgot+0.071
 promise+0.053
 stayed+0.052
 passengers+0.050
 forget+0.049
Neg logit contributions
 This-0.094
ore-0.081
-0.080
 late-0.079
 Today-0.078
Token
Token ID198
Feature activation+4.10e+00

Pos logit contributions
 This+0.066
uttering+0.063
ires+0.057
used+0.056
 late+0.055
Neg logit contributions
 forgot-0.093
 learned-0.082
 way-0.079
 promise-0.077
 knew-0.077
Token"
Token ID1
Feature activation+9.48e-01

Pos logit contributions
 This+0.060
ore+0.051
 Today+0.050
ires+0.049
uttering+0.046
Neg logit contributions
 forgot-0.091
 stayed-0.077
 learned-0.075
 promise-0.074
 forget-0.073
TokenNow
Token ID3844
Feature activation+7.64e-01

Pos logit contributions
 This+0.015
ore+0.013
ires+0.012
 Today+0.012
 late+0.011
Neg logit contributions
 forgot-0.021
 stayed-0.017
 promise-0.017
 forget-0.017
 way-0.017
Token you
Token ID345
Feature activation-4.64e+00

Pos logit contributions
 This+0.011
ore+0.009
 Today+0.009
 late+0.008
ires+0.008
Neg logit contributions
 forgot-0.017
 promise-0.014
ode-0.014
 stayed-0.014
 way-0.014
Token have
Token ID423
Feature activation-2.02e+00

Pos logit contributions
 forgot+0.087
 way+0.079
 heads+0.076
 regretted+0.075
 passengers+0.075
Neg logit contributions
 This-0.071
ore-0.061
 Today-0.059
-0.056
 late-0.052
Token a
Token ID257
Feature activation-5.63e+00

Pos logit contributions
 forgot+0.049
 promise+0.044
ode+0.043
 forget+0.042
 stayed+0.041
Neg logit contributions
 This-0.025
 late-0.019
ore-0.018
-0.017
 Today-0.016
Token fairy
Token ID25607
Feature activation-1.72e+00

Pos logit contributions
 forgot+0.103
 stayed+0.082
ode+0.082
 heads+0.076
 forget+0.075
Neg logit contributions
 This-0.104
ore-0.092
 Today-0.088
 late-0.086
-0.083
Token mark
Token ID1317
Feature activation+5.43e+00

Pos logit contributions
 forgot+0.037
 promise+0.031
 way+0.031
 stayed+0.031
 forget+0.030
Neg logit contributions
 This-0.026
ore-0.022
 late-0.021
 Today-0.021
ires-0.020
Token,"
Token ID553
Feature activation+2.49e+00

Pos logit contributions
 This+0.076
ore+0.063
ires+0.060
uttering+0.060
 Today+0.060
Neg logit contributions
 forgot-0.122
 promise-0.106
 stayed-0.106
 way-0.102
 forget-0.100
Token Fay
Token ID35136
Feature activation-4.96e+00

Pos logit contributions
 This+0.047
ore+0.042
 Today+0.039
 late+0.039
ires+0.039
Neg logit contributions
 forgot-0.045
 promise-0.037
 stayed-0.036
 way-0.036
 forget-0.035
Tokene
Token ID68
Feature activation-4.37e-01

Pos logit contributions
 forgot+0.095
 way+0.080
 promise+0.079
 forget+0.079
ode+0.078
Neg logit contributions
 This-0.087
ore-0.079
ges-0.071
-0.071
 Today-0.070
Token named
Token ID3706
Feature activation-4.55e-01

Pos logit contributions
 forgot+0.040
 promise+0.031
 stayed+0.030
 way+0.029
 forget+0.029
Neg logit contributions
 This-0.064
ore-0.058
ires-0.056
 Today-0.056
 late-0.055
Token Lily
Token ID20037
Feature activation-2.80e+00

Pos logit contributions
 forgot+0.008
 way+0.006
 promise+0.006
 stayed+0.006
 forget+0.006
Neg logit contributions
 This-0.009
ore-0.008
ires-0.008
uttering-0.008
 late-0.008
Token.
Token ID13
Feature activation+2.53e+00

Pos logit contributions
 forgot+0.065
 stayed+0.055
 promise+0.055
 way+0.054
 learned+0.053
Neg logit contributions
 This-0.039
ore-0.033
ires-0.033
uttering-0.031
 Today-0.031
Token She
Token ID1375
Feature activation-7.17e+00

Pos logit contributions
ore+0.036
uttering+0.033
ires+0.032
ach+0.031
 aboard+0.031
Neg logit contributions
 forgot-0.055
 way-0.046
 forget-0.046
 learned-0.045
 stayed-0.044
Token had
Token ID550
Feature activation-2.44e+00

Pos logit contributions
 forgot+0.103
 promise+0.082
 way+0.077
 stayed+0.076
 forget+0.076
Neg logit contributions
 This-0.161
ore-0.144
 late-0.138
 Today-0.137
ires-0.136
Token a
Token ID257
Feature activation-4.92e+00

Pos logit contributions
 forgot+0.061
 promise+0.055
 stayed+0.051
 forget+0.051
ode+0.051
Neg logit contributions
 This-0.030
 late-0.023
ore-0.022
 Today-0.021
uttering-0.020
Token cute
Token ID13779
Feature activation-3.92e+00

Pos logit contributions
 forgot+0.098
ode+0.082
 stayed+0.081
 passengers+0.076
 forget+0.076
Neg logit contributions
 This-0.083
 Today-0.068
 late-0.067
ore-0.067
uttering-0.066
Token puppy
Token ID26188
Feature activation-2.69e-01

Pos logit contributions
 forgot+0.059
 stayed+0.043
 promise+0.042
ode+0.042
 forget+0.041
Neg logit contributions
 This-0.088
ore-0.077
 Today-0.077
 late-0.074
uttering-0.073
Token named
Token ID3706
Feature activation-1.54e-01

Pos logit contributions
 forgot+0.005
 promise+0.004
 way+0.004
 stayed+0.003
 forget+0.003
Neg logit contributions
 This-0.005
ore-0.005
 Today-0.005
 late-0.005
ires-0.004
Token Max
Token ID5436
Feature activation-2.06e+00

Pos logit contributions
 forgot+0.002
 way+0.002
 stayed+0.002
 forget+0.002
 scar+0.002
Neg logit contributions
ore-0.003
uttering-0.003
 This-0.003
ires-0.003
ays-0.003
Token.
Token ID13
Feature activation+2.97e+00

Pos logit contributions
 forgot+0.044
 stayed+0.038
 promise+0.037
 way+0.036
 learned+0.036
Neg logit contributions
 This-0.031
ore-0.028
ires-0.028
uttering-0.027
 late-0.026
Token so
Token ID523
Feature activation-2.74e+00

Pos logit contributions
 forgot+0.064
ode+0.053
 promise+0.052
 way+0.050
 forget+0.050
Neg logit contributions
 This-0.063
 late-0.056
ore-0.053
uttering-0.052
 Today-0.050
Token proud
Token ID6613
Feature activation+4.37e+00

Pos logit contributions
 forgot+0.048
 promise+0.039
 stayed+0.038
 way+0.037
 forget+0.037
Neg logit contributions
 This-0.054
ore-0.048
 Today-0.045
ires-0.045
 late-0.044
Token of
Token ID286
Feature activation+2.24e+00

Pos logit contributions
 This+0.061
ore+0.052
 late+0.048
ires+0.047
 Today+0.047
Neg logit contributions
 forgot-0.101
 promise-0.086
 stayed-0.084
 way-0.084
 forget-0.083
Token how
Token ID703
Feature activation+3.13e+00

Pos logit contributions
 This+0.034
ore+0.030
 Today+0.027
uttering+0.027
 late+0.027
Neg logit contributions
 forgot-0.049
 promise-0.041
 stayed-0.041
 way-0.040
 forget-0.040
Token brave
Token ID14802
Feature activation+3.67e+00

Pos logit contributions
 This+0.056
ore+0.050
 Today+0.049
ires+0.048
uttering+0.046
Neg logit contributions
 forgot-0.061
 promise-0.048
 stayed-0.048
 way-0.047
 forget-0.046
Token she
Token ID673
Feature activation-7.79e+00

Pos logit contributions
 This+0.052
ore+0.043
 late+0.041
ires+0.039
 Today+0.039
Neg logit contributions
 forgot-0.084
 promise-0.074
ode-0.071
 way-0.070
 stayed-0.070
Token had
Token ID550
Feature activation-1.78e+00

Pos logit contributions
 forgot+0.106
ode+0.103
 promise+0.102
 way+0.096
 scar+0.095
Neg logit contributions
 This-0.154
ore-0.138
-0.138
 late-0.136
 Playing-0.131
Token been
Token ID587
Feature activation-3.18e+00

Pos logit contributions
 forgot+0.023
 promise+0.020
ode+0.019
 scar+0.018
 forget+0.017
Neg logit contributions
 This-0.040
 late-0.036
ore-0.035
-0.034
uttering-0.033
Token.
Token ID13
Feature activation+3.65e+00

Pos logit contributions
 forgot+0.067
 promise+0.056
 stayed+0.055
 way+0.055
 forget+0.054
Neg logit contributions
 This-0.051
ore-0.044
 Today-0.041
ires-0.041
 late-0.041
Token
Token ID220
Feature activation+4.86e+00

Pos logit contributions
 This+0.044
ore+0.039
uttering+0.036
ires+0.035
 late+0.034
Neg logit contributions
 forgot-0.088
 promise-0.074
 way-0.074
 stayed-0.074
 forget-0.072
Token
Token ID198
Feature activation+4.32e+00

Pos logit contributions
ore+0.057
 This+0.057
uttering+0.056
elly+0.053
ocol+0.053
Neg logit contributions
 forgot-0.097
 stayed-0.080
 learned-0.079
 way-0.077
 hugged-0.076