INDEX
Explanations
references to physical contact or emotional connections
New Auto-Interp
Negative Logits
MainAxisAlignment
-0.16
ernet
-0.15
.scalablytyped
-0.15
šit
-0.15
horse
-0.14
stav
-0.14
enor
-0.14
Subview
-0.14
thag
-0.14
quo
-0.14
POSITIVE LOGITS
-touch
0.17
Touch
0.17
touch
0.17
TOUCH
0.16
erson
0.15
(es
0.15
OOK
0.15
ively
0.15
olley
0.15
beck
0.15
Activations Density 0.032%