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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and symbols likely related to coding or technical data

    oai_token-act-pair · gpt-3.5-turbo

    numerical patterns and sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tions
    -0.74
    ername
    -0.70
    @#&
    -0.69
    oleon
    -0.66
    ================================================================
    -0.66
     Forth
    -0.65
    theless
    -0.65
     Username
    -0.65
     Mental
    -0.64
    nostic
    -0.64
    POSITIVE LOGITS
    crop
    0.79
    icons
    0.75
    chrom
    0.75
    azo
    0.72
    )=(
    0.71
    usercontent
    0.69
    cdn
    0.65
    original
    0.65
    bleacher
    0.64
    "><
    0.64
    Act Density 0.049%

    No Known Activations