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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "could not" appears

    oai_token-act-pair · gpt-3.5-turbo

    negation phrases and forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artifacts
    -0.74
    hyde
    -0.72
    interstitial
    -0.72
    amous
    -0.70
    soDeliveryDate
    -0.70
    govtrack
    -0.65
     Notting
    -0.63
    cases
    -0.62
    entin
    -0.61
    notation
    -0.60
    POSITIVE LOGITS
     foresee
    0.89
     afford
    0.84
    athom
    0.78
     conce
    0.75
     feas
    0.73
     imagine
    0.73
     cope
    0.72
     conceive
    0.71
     parse
    0.70
     discern
    0.68
    Act Density 0.124%

    No Known Activations