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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to debunking myths and misconceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inger
    -0.14
    ird
    -0.14
     Dysfunction
    -0.14
    ãĥ¼ãĤº
    -0.14
    ìĿĮ
    -0.14
    ết
    -0.14
    cef
    -0.13
     foresee
    -0.13
     retrospect
    -0.13
     Wikispecies
    -0.13
    POSITIVE LOGITS
     myth
    0.60
     myths
    0.59
     Myth
    0.55
     mythology
    0.41
     legend
    0.37
     falsehood
    0.37
     legends
    0.36
     false
    0.35
     mythical
    0.34
     Legend
    0.33
    Act Density 0.363%

    No Known Activations