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

    Neuronpedia

    INDEX
    Explanations

    words related to the external appearance or behavior of something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to external and internal aspects or appearances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.93
    ENCY
    -0.73
    kson
    -0.72
    grave
    -0.71
    uzz
    -0.69
    rams
    -0.67
    mobile
    -0.67
    haus
    -0.67
    rss
    -0.66
    rosis
    -0.66
    POSITIVE LOGITS
    worldly
    0.88
     manifestations
    0.87
     appearances
    0.80
     worldly
    0.75
     appearance
    0.75
     manifestation
    0.71
     outward
    0.71
     resemblance
    0.70
     dimensions
    0.69
    isms
    0.68
    Act Density 0.031%

    No Known Activations