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

    Neuronpedia

    INDEX
    Explanations

    words related to time units and numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letters "ar" or "AR" within words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.88
    ĨĴ
    -0.82
    assetsadobe
    -0.72
    ¬¼
    -0.70
    代
    -0.69
    éĹĺ
    -0.69
     Nicotine
    -0.69
     Nug
    -0.67
    erker
    -0.65
    EStream
    -0.62
    POSITIVE LOGITS
    riage
    1.12
    acters
    1.08
    acter
    1.01
    thur
    1.01
    ithmetic
    1.01
    allel
    0.93
    riors
    0.92
    bor
    0.91
    beit
    0.90
    riages
    0.86
    Act Density 0.036%

    No Known Activations