Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     epile
    -0.07
     exposed
    -0.06
     grabbing
    -0.06
    можно
    -0.06
    mah
    -0.06
    OSE
    -0.06
     kr
    -0.06
    handles
    -0.06
    越来越
    -0.06
    mé
    -0.06
    POSITIVE LOGITS
     hairstyles
    0.07
    跷
    0.07
    �
    0.07
     soda
    0.07
    Heart
    0.07
    ῖ
    0.07
     экс
    0.07
    容貌
    0.07
    五金
    0.06
    _cert
    0.06
    Act Density 0.003%

    No Known Activations