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

    Neuronpedia

    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    attributes related to individuals and their affiliations or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     checks
    -0.76
     reviewers
    -0.64
     selection
    -0.63
    enton
    -0.62
    erence
    -0.62
     indexes
    -0.62
     supplemental
    -0.61
     descriptor
    -0.61
     liner
    -0.60
     coaster
    -0.60
    POSITIVE LOGITS
    Äĩ
    1.06
    Downloadha
    0.99
    pora
    0.92
    rahim
    0.89
    oÄŁ
    0.87
    ÄŁ
    0.86
    sbm
    0.86
    qqa
    0.86
    aram
    0.85
     Sheikh
    0.84
    Act Density 0.548%

    No Known Activations