INDEX
Explanations
D-dimensional
The neuron activates on mentions of one-dimensional (1D) contexts in technical or scientific descriptions.
New Auto-Interp
Negative Logits
purchase
-0.07
Lady
-0.07
.Ui
-0.06
Sir
-0.06
Archbishop
-0.06
Borough
-0.06
religion
-0.06
Bruce
-0.06
Guild
-0.06
bekommen
-0.06
POSITIVE LOGITS
isha
0.06
-xs
0.06
ğine
0.06
扎
0.06
liğ
0.06
OMET
0.06
.Health
0.06
ΔE
0.06
alg
0.06
ợ
0.06
Activations Density 0.004%