INDEX
Explanations
references to aliens and alien-related themes
New Auto-Interp
Negative Logits
eah
-0.18
iban
-0.16
ÑĴ
-0.15
oger
-0.15
Santos
-0.15
ohan
-0.14
gers
-0.14
iba
-0.14
xic
-0.14
sinks
-0.14
POSITIVE LOGITS
isper
0.20
SSF
0.19
wheel
0.18
morph
0.17
inis
0.15
Ŀ
0.15
QUIRED
0.15
üb
0.14
whispers
0.14
REEN
0.14
Activations Density 0.010%