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

    Neuronpedia

    INDEX
    Explanations

    numbers and percentages related to statistical data

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eus
    -0.67
     Lank
    -0.66
    Reviewer
    -0.64
     Mahar
    -0.63
     Dish
    -0.63
     Scotch
    -0.61
     Aging
    -0.59
     Titus
    -0.59
     logic
    -0.59
     grate
    -0.58
    POSITIVE LOGITS
    %.
    0.90
    fps
    0.88
    %,
    0.84
    %
    0.78
    %;
    0.78
    cm
    0.76
     percent
    0.75
    Mbps
    0.74
    fif
    0.72
    bps
    0.72
    Act Density 0.191%

    No Known Activations