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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to statistics or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to various metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palest
    -0.66
     simplest
    -0.61
     Pros
    -0.58
     Painter
    -0.56
    avascript
    -0.55
     harmless
    -0.55
    imaru
    -0.55
    orc
    -0.54
    akeru
    -0.53
    mitter
    -0.53
    POSITIVE LOGITS
    %,
    1.18
    %-
    1.12
    %.
    1.08
    %;
    1.07
    %
    1.07
     percent
    1.04
    %),
    1.00
    %).
    0.97
    %)
    0.97
     cents
    0.95
    Act Density 0.182%

    No Known Activations