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

    Neuronpedia

    INDEX
    Explanations

    the word "town" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "town."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    positive
    -0.76
    cean
    -0.71
    acterial
    -0.70
    inguished
    -0.69
    argon
    -0.68
    Dom
    -0.68
    iferation
    -0.67
    uberty
    -0.66
    zek
    -0.66
    fen
    -0.66
    POSITIVE LOGITS
    folk
    1.12
    spe
    1.10
    houses
    1.07
     hall
    0.98
    house
    0.98
     halls
    0.97
    ships
    0.90
    wide
    0.88
    area
    0.84
    itas
    0.83
    Act Density 0.022%

    No Known Activations