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

    Neuronpedia

    INDEX
    Explanations

    large numbers with specific formatting, possibly related to statistics or data sets

    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
     Bots
    -0.62
    igans
    -0.62
    houses
    -0.58
    isters
    -0.57
     Peb
    -0.57
    aries
    -0.56
    assetsadobe
    -0.55
    sters
    -0.54
    stars
    -0.53
    strings
    -0.53
    POSITIVE LOGITS
    46
    1.15
    71
    1.07
    38
    1.07
    37
    1.07
    39
    1.06
    59
    1.06
    31
    1.06
    43
    1.05
    41
    1.05
    79
    1.04
    Act Density 0.054%

    No Known Activations