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

    Neuronpedia

    INDEX
    Explanations

    words related to mathematical concepts or measurements, specifically focusing on numerical values or fractions expressed as <number>-<ordinals>

    oai_token-act-pair · gpt-3.5-turbo

    numerical representations or values associated with measurements and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    shall
    -0.63
    REDACTED
    -0.57
    ModLoader
    -0.54
     PUBLIC
    -0.54
    ships
    -0.53
    wolves
    -0.53
     virginity
    -0.53
    MORE
    -0.52
    Priv
    -0.52
    maid
    -0.52
    POSITIVE LOGITS
    ousand
    1.08
    undred
    1.01
    otted
    0.90
    imester
    0.89
    iece
    0.87
    velength
    0.85
    ared
    0.84
    enger
    0.84
    enth
    0.83
    ayer
    0.83
    Act Density 0.093%

    No Known Activations