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

    Neuronpedia

    INDEX
    Explanations

    percentages

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number "100" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rift
    -0.88
    mare
    -0.76
    achi
    -0.71
    vati
    -0.68
    colm
    -0.67
    Fram
    -0.67
    ake
    -0.66
     Sands
    -0.66
    mares
    -0.65
    letal
    -0.65
    POSITIVE LOGITS
    00000
    1.10
    %"
    0.94
    Percent
    0.94
    644
    0.90
    %]
    0.88
    %;
    0.88
    Mbps
    0.84
    %
    0.84
    Hz
    0.84
    percent
    0.83
    Act Density 0.038%

    No Known Activations