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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    hess
    -0.77
    nian
    -0.71
    ãĥīãĥ©
    -0.68
    icative
    -0.67
    olkien
    -0.64
    ivia
    -0.63
    aceutical
    -0.61
    issance
    -0.61
    7601
    -0.60
    ãĤµ
    -0.60
    POSITIVE LOGITS
    FK
    0.79
     Mous
    0.76
    itiz
    0.64
    asks
    0.63
    oteric
    0.62
    isf
    0.62
     Cuba
    0.59
     impressions
    0.58
    ULTS
    0.57
    Snake
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.