INDEX
Explanations
references to locations and settings within narratives
New Auto-Interp
Negative Logits
enthal
-0.18
enis
-0.14
325
-0.14
otal
-0.14
(al
-0.14
turnstile
-0.13
IF
-0.13
:|
-0.13
rec
-0.13
Psychological
-0.13
POSITIVE LOGITS
achten
0.15
cimal
0.15
/thumb
0.15
AIM
0.14
ync
0.14
scape
0.14
iami
0.14
tog
0.14
abin
0.13
iac
0.13
Activations Density 0.140%