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

    Neuronpedia

    INDEX
    Explanations

    content related to technical information and warnings

    oai_token-act-pair · gpt-3.5-turbo

    content related to timelines and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    naire
    -0.77
    ariat
    -0.77
    etts
    -0.74
    naires
    -0.72
    forth
    -0.71
    tein
    -0.69
    hop
    -0.68
    ctors
    -0.66
    ivas
    -0.66
    iewicz
    -0.66
    POSITIVE LOGITS
    Movie
    0.86
     Manga
    0.71
     Seller
    0.68
    Title
    0.68
    iframe
    0.67
    Ble
    0.64
     DISTRICT
    0.63
    Runtime
    0.63
    Drug
    0.62
    cloneembedreportprint
    0.62
    Act Density 0.616%

    No Known Activations