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

    Neuronpedia

    INDEX
    Explanations

    markup language or programming syntax

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ledged
    -0.98
     Tycoon
    -0.96
    owers
    -0.90
    itsch
    -0.84
    edom
    -0.83
    ommel
    -0.83
    ateurs
    -0.82
    oleon
    -0.81
    imately
    -0.81
    olls
    -0.80
    POSITIVE LOGITS
    english
    1.04
    ...]
    1.02
    !--
    1.01
    ordering
    1.01
    param
    0.89
    channelAvailability
    0.86
    ItemImage
    0.86
    ··
    0.85
    report
    0.85
    -|
    0.85
    Act Density 0.332%

    No Known Activations