INDEX
    Explanations

    This neuron fires on explicit, forceful sexual action descriptions—especially verbs and phrases depicting violent penetration.

    New Auto-Interp
    Negative Logits
     tests
    -0.07
     znam
    -0.07
     test
    -0.07
     basement
    -0.07
    Button
    -0.07
    ona
    -0.06
    883
    -0.06
    632
    -0.06
    440
    -0.06
    _utf
    -0.06
    POSITIVE LOGITS
    ahrain
    0.07
     piyas
    0.06
     قاب
    0.06
    (scroll
    0.06
     biçim
    0.06
     поє
    0.06
     آلة
    0.06
    (CON
    0.06
     переход
    0.06
    0.06
    Act Density 0.036%

    No Known Activations