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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific town names

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the word "Town."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utic
    -0.88
    aunder
    -0.84
    terday
    -0.82
    uberty
    -0.79
    ances
    -0.79
    ulously
    -0.79
    utics
    -0.78
    Downloadha
    -0.75
    ibilities
    -0.70
    uckland
    -0.70
    POSITIVE LOGITS
    spe
    1.15
    folk
    1.12
    ships
    1.06
    house
    1.00
    houses
    0.99
     Halls
    0.97
    scape
    0.90
    she
    0.87
    send
    0.86
    wide
    0.83
    Act Density 0.011%

    No Known Activations