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

    Neuronpedia

    INDEX
    Explanations

    shortened URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs or web links in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Frankfurt
    -0.80
     Mirage
    -0.75
     Dent
    -0.74
     Provincial
    -0.73
    OLOGY
    -0.69
    =-=-=-=-
    -0.69
     principals
    -0.68
     Barber
    -0.67
     Semin
    -0.67
     Rahman
    -0.65
    POSITIVE LOGITS
    oche
    0.86
     appre
    0.86
    cdn
    0.85
    img
    0.80
    utenberg
    0.79
    gallery
    0.78
    ua
    0.76
    ecd
    0.72
    biz
    0.72
    emb
    0.71
    Act Density 0.022%

    No Known Activations