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

    Neuronpedia

    INDEX
    Explanations

    words related to absurdity, madness, and hypocrisy

    oai_token-act-pair · gpt-3.5-turbo

    themes related to absurdity and irrationality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ergy
    -0.80
    ellar
    -0.70
    iable
    -0.66
    vals
    -0.65
     Scientist
    -0.65
    amins
    -0.64
    arters
    -0.63
    vice
    -0.63
    eric
    -0.62
    izations
    -0.62
    POSITIVE LOGITS
     inflicted
    0.86
    fulness
    0.86
     tremend
    0.81
     abound
    0.81
    ulence
    0.80
    iness
    0.79
     awaiting
    0.79
     perpetrated
    0.77
     imaginable
    0.73
    ously
    0.72
    Act Density 0.080%

    No Known Activations