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

    Neuronpedia

    INDEX
    Explanations

    HTML formatting elements such as tags

    oai_token-act-pair · gpt-3.5-turbo

    patterns related to digital media file formats and references to photos or images

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Galile
    -0.71
     Cov
    -0.71
     tenants
    -0.65
     reunion
    -0.64
     Reeves
    -0.63
     Rivals
    -0.63
     enterprise
    -0.63
     Lanka
    -0.63
     Expend
    -0.62
     Tenn
    -0.61
    POSITIVE LOGITS
    processing
    1.11
    gallery
    1.09
    writing
    1.04
    writer
    1.01
    format
    1.01
    named
    0.98
    dump
    0.97
    reading
    0.97
    spl
    0.96
    visual
    0.96
    Act Density 0.097%

    No Known Activations