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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions and measurements

    oai_token-act-pair · gpt-3.5-turbo

    elements related to visual representation and color coding in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reincarn
    -0.78
     Loving
    -0.68
    advertising
    -0.67
    ndum
    -0.63
     Fiat
    -0.62
    ecast
    -0.62
    ESCO
    -0.62
     Ambrose
    -0.62
    gil
    -0.61
     Timothy
    -0.61
    POSITIVE LOGITS
     dashed
    1.56
     plotted
    1.52
     arrows
    1.36
     axis
    1.34
     dotted
    1.32
     graphs
    1.31
     dots
    1.30
     aster
    1.26
     graph
    1.25
     plots
    1.23
    Act Density 0.218%

    No Known Activations