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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the words "no" and "fly"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restrictions or prohibitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alian
    -0.70
    ridor
    -0.69
    ãĥ¼ãĥĨ
    -0.66
    erella
    -0.64
    andise
    -0.63
    gypt
    -0.61
     Perspect
    -0.60
    aspers
    -0.60
    abeth
    -0.60
    Ļ½
    -0.59
    POSITIVE LOGITS
     whatsoever
    1.16
    brainer
    0.78
    ody
    0.73
     nor
    0.69
    hawk
    0.69
     hesitation
    0.67
     dime
    0.66
    ilings
    0.64
    oway
    0.61
    repeat
    0.61
    Act Density 0.101%

    No Known Activations