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

    Neuronpedia

    INDEX
    Explanations

    words related to coding or programming languages

    oai_token-act-pair · gpt-3.5-turbo

    emotional tones and references in media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.80
     Bengal
    -0.73
    creen
    -0.72
     Marble
    -0.71
     Squirrel
    -0.69
     scramble
    -0.67
    ulkan
    -0.66
     Klaus
    -0.64
     guiActiveUnfocused
    -0.63
     Berlin
    -0.63
    POSITIVE LOGITS
    ł
    1.18
    ¹
    1.06
    IJ
    0.92
    ª
    0.91
    Ĵ
    0.90
    Ķ
    0.89
    sure
    0.84
    ittal
    0.84
    ĵ
    0.83
    ı
    0.83
    Act Density 0.171%

    No Known Activations