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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating no alternative options or decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to lack of alternatives or forced decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    govtrack
    -0.66
    RFC
    -0.64
    ciating
    -0.59
     bloom
    -0.57
     blat
    -0.55
    Interstitial
    -0.54
     Roose
    -0.54
    urdy
    -0.54
    olid
    -0.53
     mock
    -0.53
    POSITIVE LOGITS
    llor
    0.84
     whatsoever
    0.80
    BIL
    0.72
    ices
    0.72
     recourse
    0.70
    perty
    0.69
    options
    0.68
     but
    0.67
     options
    0.66
    essors
    0.65
    Act Density 0.065%

    No Known Activations