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

    Neuronpedia

    INDEX
    Explanations

    locations or place names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ghai
    -0.65
     Berk
    -0.61
    hex
    -0.61
    jet
    -0.60
    sect
    -0.59
    staff
    -0.59
    coord
    -0.58
    paying
    -0.57
    artz
    -0.56
    vention
    -0.55
    POSITIVE LOGITS
    OUS
    1.43
    URA
    1.40
     EDITION
    1.40
    HEAD
    1.39
    VILLE
    1.35
    IAN
    1.35
    ING
    1.34
    SHIP
    1.32
    ISH
    1.31
    OOD
    1.30
    Act Density 0.190%

    No Known Activations