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

    Neuronpedia

    INDEX
    Explanations

    line breaks or new paragraphs denoted by "Ċ"

    oai_token-act-pair · gpt-4-turbo

    certain types of symbols or characters that are repeated, possibly for emphasis or formatting purposes

    oai_token-act-pair · gpt-3.5-turbo

    instances of political suppression or coercion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dissu
    -0.74
    ionage
    -0.71
     detract
    -0.66
    awei
    -0.66
    byss
    -0.66
    xual
    -0.65
    igi
    -0.64
    ertodd
    -0.64
    ulkan
    -0.64
    aterasu
    -0.64
    POSITIVE LOGITS
    ccording
    0.98
    ³³³³³³³³³³³³³³³³
    0.94
    Contents
    0.92
    ³³³³
    0.92
    Recent
    0.86
    SPONSORED
    0.85
    Posted
    0.84
    ³³
    0.82
    ³³³
    0.82
    During
    0.81
    Act Density 0.536%

    No Known Activations