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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations containing the word "Cape"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Cape" or related variations, indicating a focus on geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arial
    -0.76
    agi
    -0.73
    amine
    -0.72
    mble
    -0.70
    naires
    -0.69
    omen
    -0.69
    atically
    -0.68
    swer
    -0.68
    perse
    -0.66
    orno
    -0.66
    POSITIVE LOGITS
    llan
    1.14
     Cod
    1.05
    lla
    0.97
     Canaveral
    0.95
     Coral
    0.85
     Coast
    0.81
    reon
    0.81
     Nam
    0.77
     Crusade
    0.77
     Colony
    0.76
    Act Density 0.022%

    No Known Activations