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

    Neuronpedia

    INDEX
    Explanations

    numbers related to quantity or ranking

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "100 percent" or complete certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rift
    -0.88
    mare
    -0.78
    achi
    -0.74
    mares
    -0.72
    olas
    -0.69
    worldly
    -0.68
    vati
    -0.68
    hold
    -0.67
    colm
    -0.67
    ake
    -0.67
    POSITIVE LOGITS
    00000
    1.14
    Percent
    0.97
    %;
    0.92
    Hz
    0.92
    %"
    0.91
    %
    0.90
    %]
    0.88
    644
    0.86
    percent
    0.86
    Mbps
    0.84
    Act Density 0.053%

    No Known Activations