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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of normalcy and deviations from it

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hani
    -0.88
    iosyncr
    -0.82
    Sov
    -0.78
    haw
    -0.78
    NRS
    -0.75
    Lens
    -0.75
    otle
    -0.74
    artisan
    -0.74
    hire
    -0.73
    Winged
    -0.73
    POSITIVE LOGITS
    cy
    1.41
    ization
    1.41
    izes
    1.40
    izing
    1.36
    isation
    1.33
    ised
    1.31
    ize
    1.27
    izers
    1.27
    ized
    1.18
    ises
    1.15
    Act Density 4.604%

    No Known Activations