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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or surnames

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and their roles or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.75
    EED
    -0.74
    mail
    -0.72
    flies
    -0.72
    OTAL
    -0.71
    200000
    -0.69
    dress
    -0.67
    mails
    -0.67
    cade
    -0.66
    ãĥ¼ãĥ³
    -0.65
    POSITIVE LOGITS
     Luk
    1.14
    uania
    0.87
    rils
    0.86
    ijn
    0.78
    inated
    0.76
    owitz
    0.75
    inate
    0.74
    ifer
    0.74
    itsch
    0.73
    lihood
    0.73
    Act Density 0.032%

    No Known Activations