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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating leadership or prominence in a specific industry or field

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    fanart
    -0.53
    IContainer
    -0.52
    TextBoxColumn
    -0.51
    HandlerContext
    -0.50
    ună
    -0.50
    fromUtf
    -0.50
    críbete
    -0.49
    قایناق‌لار
    -0.49
    jiga
    -0.49
     cam
    -0.48
    POSITIVE LOGITS
     houſe
    0.73
     référence
    0.71
    دانشنامهٔ
    0.71
     riferimento
    0.69
     lenker
    0.69
     pleaſure
    0.69
    IntoConstraints
    0.67
     purpoſe
    0.65
     ſtate
    0.64
    Notae
    0.64
    Act Density 0.069%

    No Known Activations