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

    Neuronpedia

    INDEX
    Explanations

    contractions of "cannot"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "couldn't."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     protected
    -0.68
     Published
    -0.66
     Mechdragon
    -0.66
     friendly
    -0.64
    raviolet
    -0.64
     populated
    -0.64
     couch
    -0.63
     PU
    -0.60
     fav
    -0.60
     deprecated
    -0.60
    POSITIVE LOGITS
    't
    1.82
    ÃŃ
    1.02
    \'
    0.94
    kered
    0.93
    ÃĥÃĤ
    0.92
    itely
    0.92
    fortunately
    0.89
    ´
    0.88
    isexual
    0.88
    iting
    0.88
    Act Density 0.015%

    No Known Activations