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

    Neuronpedia

    INDEX
    Explanations

    comma punctuation

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases and conversational transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Discuss
    -0.73
    è¦ļéĨĴ
    -0.72
    OWN
    -0.66
    Sold
    -0.66
    lean
    -0.65
    catentry
    -0.65
    idas
    -0.65
    cffffcc
    -0.61
     Commun
    -0.60
    ¥µ
    -0.58
    POSITIVE LOGITS
    wagen
    0.73
    tsky
    0.73
    chery
    0.72
     understatement
    0.69
     Parenthood
    0.65
    chio
    0.63
     Tycoon
    0.63
     Nikol
    0.63
    uracy
    0.63
     Eliot
    0.60
    Act Density 0.070%

    No Known Activations