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

    Neuronpedia

    INDEX
    Explanations

    mentions of town hall meetings

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "town" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    positive
    -0.72
    uberty
    -0.69
    fen
    -0.68
    xual
    -0.66
    utic
    -0.66
    bian
    -0.66
    Wan
    -0.66
    nces
    -0.65
    argon
    -0.65
    hetic
    -0.64
    POSITIVE LOGITS
    folk
    1.22
    spe
    1.11
    houses
    1.10
    house
    1.02
    ships
    1.01
     halls
    0.97
     hall
    0.94
    scape
    0.91
    square
    0.89
    area
    0.88
    Act Density 0.032%

    No Known Activations