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

    Neuronpedia

    INDEX
    Explanations

    the word "Con" or variations of it in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific person's name, "Con."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffffcc
    -0.79
     ank
    -0.75
    hap
    -0.70
    iped
    -0.67
     trillions
    -0.66
    hands
    -0.64
    eday
    -0.64
    ãĥ©ãĥ³
    -0.64
     swear
    -0.64
    NR
    -0.63
    POSITIVE LOGITS
     Con
    3.55
    Con
    2.14
    con
    1.75
     CON
    1.63
     con
    1.57
    CON
    1.41
     Cons
    1.35
     Com
    1.32
     Convention
    1.28
     Conc
    1.27
    Act Density 0.009%

    No Known Activations