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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "town" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "town"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    positive
    -0.64
    ulously
    -0.64
    ught
    -0.61
    utic
    -0.60
     chore
    -0.60
    argon
    -0.59
    avier
    -0.59
    aphael
    -0.59
    gotten
    -0.58
     Rodgers
    -0.58
    POSITIVE LOGITS
    spe
    1.36
    folk
    1.35
    ships
    1.31
    houses
    1.21
    house
    1.14
     halls
    1.10
    square
    1.06
     hall
    1.04
    ship
    1.01
    send
    0.96
    Act Density 0.042%

    No Known Activations