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

    Neuronpedia

    INDEX
    Explanations

    names or surnames with common endings or patterns

    oai_token-act-pair · gpt-3.5-turbo

    identifiers related to people or entities, particularly in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plunge
    -0.61
     annex
    -0.61
     independ
    -0.60
     unpre
    -0.60
     comparable
    -0.59
     tem
    -0.57
     apprentices
    -0.56
     bargain
    -0.56
     deduction
    -0.56
     quake
    -0.56
    POSITIVE LOGITS
    chel
    1.02
    beck
    0.97
    zik
    0.96
    ler
    0.95
    sey
    0.95
    ey
    0.93
    mann
    0.92
    combe
    0.91
    nick
    0.90
    sche
    0.90
    Act Density 0.218%

    No Known Activations