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

    Neuronpedia

    INDEX
    Explanations

    references to thematic elements in a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Vaata
    -0.73
    SPS
    -0.68
     Brito
    -0.65
    Tikang
    -0.64
    mographie
    -0.63
    getMethod
    -0.60
     SPS
    -0.60
    intahan
    -0.60
     rhestr
    -0.59
     noqa
    -0.59
    POSITIVE LOGITS
     Theme
    1.73
     themes
    1.73
     theme
    1.68
     Themes
    1.64
    THEME
    1.57
     THEME
    1.56
    Theme
    1.55
    themes
    1.54
    Themes
    1.52
    theme
    1.49
    Act Density 0.007%

    No Known Activations