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

    Neuronpedia

    INDEX
    Explanations

    mentions of commas followed by a single capital letter C with a diacritic mark above it

    oai_token-act-pair · gpt-3.5-turbo

    various forms of quotations or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ò
    -0.89
    aditional
    -0.81
    ñ
    -0.79
     eleph
    -0.77
     oun
    -0.76
     tremend
    -0.76
    ą
    -0.73
     hemor
    -0.73
    Þ
    -0.73
     exting
    -0.73
    POSITIVE LOGITS
    thinkable
    0.68
    rou
    0.68
    ↵
    0.67
    BBC
    0.67
    rave
    0.65
    ixture
    0.64
    gex
    0.63
    abulary
    0.62
    1016
    0.62
    Image
    0.62
    Act Density 0.137%

    No Known Activations