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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "out"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odore
    -0.63
     Brach
    -0.58
     Emin
    -0.54
    ĻĤ
    -0.53
    itor
    -0.52
    oreal
    -0.52
     Book
    -0.52
     Arrows
    -0.51
     twilight
    -0.51
     Coin
    -0.51
    POSITIVE LOGITS
    fitted
    1.19
    lived
    1.10
    stri
    1.09
    smart
    1.09
    crop
    1.06
    number
    1.06
    fitting
    1.06
    lasting
    1.04
    ta
    1.04
    rage
    1.04
    Act Density 0.060%

    No Known Activations