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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    instances of repetition of the word "also" and other descriptors of participation or involvement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opter
    -0.62
     Corpus
    -0.60
     Humanity
    -0.60
    aten
    -0.59
    amen
    -0.59
    click
    -0.58
     notwithstanding
    -0.57
    turn
    -0.56
    Tonight
    -0.56
     Scorpion
    -0.56
    POSITIVE LOGITS
    oug
    0.72
    andals
    0.71
     Marketable
    0.70
    ractive
    0.70
    vertisement
    0.68
    agonists
    0.68
    è¦ļéĨĴ
    0.66
    ilitary
    0.66
    icipated
    0.65
    nesses
    0.64
    Act Density 0.513%

    No Known Activations