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

    Neuronpedia

    INDEX
    Explanations

    exact numerical values or specific counts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.75
    Crunch
    -0.65
    GenerationType
    -0.64
    phòng
    -0.62
    UrlResolution
    -0.61
    RTLI
    -0.60
    SceneManagement
    -0.60
    AxisAlignment
    -0.59
    protoimpl
    -0.59
    Filmografie
    -0.59
    POSITIVE LOGITS
     >=",
    0.63
    &__
    0.54
    Rhestr
    0.53
     intervening
    0.52
    EditorBrowsable
    0.51
    conia
    0.48
    VolleyError
    0.48
     Consig
    0.48
    torem
    0.47
     Elmo
    0.47
    Act Density 0.000%

    No Known Activations