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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to being or acting foolish

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fool" or its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parenthood
    -0.76
    Delivery
    -0.67
     uneven
    -0.63
    EV
    -0.61
    foreseen
    -0.61
    itals
    -0.61
     contraction
    -0.59
    Oct
    -0.59
    orney
    -0.59
    apers
    -0.59
    POSITIVE LOGITS
    hard
    0.95
    proof
    0.91
    sonian
    0.85
     pas
    0.82
    ingly
    0.81
    found
    0.80
    ery
    0.80
    ument
    0.80
    ible
    0.75
    ibility
    0.75
    Act Density 0.023%

    No Known Activations