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

    Neuronpedia

    INDEX
    Explanations

    the word "beast" at varying levels of intensity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and variations of the word "beast."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arters
    -0.82
    bered
    -0.76
    pai
    -0.75
    enza
    -0.73
    idential
    -0.72
    licted
    -0.71
    monds
    -0.69
     polymer
    -0.67
    mit
    -0.67
    encing
    -0.66
    POSITIVE LOGITS
     beasts
    1.23
     beast
    1.10
     Beasts
    0.97
    buster
    0.87
     carc
    0.85
     Beast
    0.82
    Beast
    0.80
    osaurs
    0.79
    zilla
    0.77
    busters
    0.76
    Act Density 0.010%

    No Known Activations