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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of hometowns

    oai_token-act-pair · gpt-3.5-turbo

    references to "hometown."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONS
    -0.87
    err
    -0.86
    asse
    -0.83
    assic
    -0.81
    ression
    -0.81
    ements
    -0.80
    chnology
    -0.77
    aton
    -0.77
    andum
    -0.75
    eng
    -0.74
    POSITIVE LOGITS
     hometown
    0.75
     Huck
    0.73
     turf
    0.73
     haunt
    0.71
     Borough
    0.71
     haun
    0.69
     favorite
    0.69
     favourite
    0.69
     hero
    0.68
     homeland
    0.68
    Act Density 0.032%

    No Known Activations