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

    Neuronpedia

    INDEX
    Explanations

    technical details related to cooking or photography

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to health risks and safety concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Nap
    -0.67
    AU
    -0.66
    bucks
    -0.64
    Ber
    -0.64
     brut
    -0.64
    deen
    -0.64
    Barn
    -0.64
    emale
    -0.63
    Word
    -0.62
    kj
    -0.60
    POSITIVE LOGITS
    abouts
    0.69
     modifiers
    0.66
    shed
    0.57
    isec
    0.56
     sheds
    0.56
    utterstock
    0.54
     accompanying
    0.54
     transplant
    0.53
     inheritance
    0.53
     Travels
    0.52
    Act Density 0.167%

    No Known Activations