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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to technical aspects or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ktop
    -0.74
    velt
    -0.74
     Sheen
    -0.71
    KI
    -0.69
    hyde
    -0.68
    lein
    -0.67
     largeDownload
    -0.67
     Twain
    -0.67
    xon
    -0.67
    stellar
    -0.65
    POSITIVE LOGITS
     specifications
    0.98
     glitches
    0.95
     jargon
    0.94
     difficulties
    0.91
     considerations
    0.88
    idad
    0.86
    technical
    0.86
    iencies
    0.86
     technical
    0.83
     specs
    0.81
    Act Density 0.009%

    No Known Activations