INDEX
Explanations
historical references related to architecture and cultural transformations
New Auto-Interp
Negative Logits
189
-0.18
193
-0.17
190
-0.17
191
-0.16
à¤Ńà¤Ĺ
-0.15
theid
-0.15
drivers
-0.15
192
-0.15
Victorian
-0.15
194
-0.15
POSITIVE LOGITS
166
0.52
163
0.49
164
0.47
165
0.47
167
0.47
162
0.41
168
0.41
161
0.40
169
0.39
160
0.34
Activations Density 0.070%