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

    Neuronpedia

    INDEX
    Explanations

    numeric values representing quantities or amounts

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igham
    -0.66
     Caption
    -0.65
    cipled
    -0.64
     Changed
    -0.63
    iculture
    -0.62
    igslist
    -0.61
     Lover
    -0.61
    orig
    -0.61
     Correspond
    -0.61
    TextColor
    -0.60
    POSITIVE LOGITS
    %.
    0.85
     months
    0.85
    %:
    0.80
    %-
    0.78
     percent
    0.77
    %"
    0.77
     billion
    0.74
    ½
    0.72
    %
    0.72
    th
    0.71
    Act Density 0.080%

    No Known Activations