INDEX
Explanations
references to specific events or occasions
New Auto-Interp
Negative Logits
ansom
-0.17
alth
-0.16
важа
-0.16
achs
-0.15
enet
-0.15
άζ
-0.15
æħ
-0.15
arih
-0.15
588
-0.14
824
-0.14
POSITIVE LOGITS
completion
0.19
ergus
0.16
offer
0.16
completion
0.15
Completion
0.15
Completion
0.14
arrival
0.14
reflection
0.14
pitch
0.14
YSIS
0.14
Activations Density 0.100%