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

    Neuronpedia

    INDEX
    Explanations

    mentions of the Japanese city "Kratatoa"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ato" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     HH
    -0.78
    mable
    -0.70
    Ö¼
    -0.69
    gling
    -0.65
     mathemat
    -0.65
    ership
    -0.65
    igators
    -0.64
    stones
    -0.64
     availability
    -0.63
     vacancies
    -0.62
    POSITIVE LOGITS
    ichi
    1.24
    zzi
    1.14
    zzo
    1.03
    hea
    0.91
    chet
    0.90
    chi
    0.89
    ppa
    0.87
    eca
    0.87
    oga
    0.86
    vernment
    0.83
    Act Density 0.021%

    No Known Activations