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

    Neuronpedia

    INDEX
    Explanations

    contractions and negations

    oai_token-act-pair · gpt-3.5-turbo

    negations and phrases indicating inability or lack of certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esting
    -0.63
    farious
    -0.63
     Appears
    -0.62
    nis
    -0.61
     Matters
    -0.61
     Called
    -0.60
    isible
    -0.59
     STATS
    -0.59
    plates
    -0.58
    amy
    -0.58
    POSITIVE LOGITS
     afford
    1.02
     conce
    0.81
     foresee
    0.79
     feas
    0.78
    cffffcc
    0.77
     convince
    0.76
     possibly
    0.76
     muster
    0.75
     conceive
    0.75
     predict
    0.74
    Act Density 0.103%

    No Known Activations