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

    Neuronpedia

    INDEX
    Explanations

    superlatives such as "most," "best," and "safest."

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives and phrases indicating extremes or best/worst rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aucuses
    -0.84
    rils
    -0.84
    ãĤ¦ãĤ¹
    -0.83
    appings
    -0.82
     Cosponsors
    -0.80
    é¾į
    -0.79
    ravings
    -0.79
    IGHTS
    -0.78
    Ô
    -0.75
    rahim
    -0.74
    POSITIVE LOGITS
     thing
    1.00
     ever
    0.93
     imaginable
    0.92
     bidder
    0.91
     piece
    0.90
     conceivable
    0.90
     foreigner
    0.87
     performer
    0.86
     applicant
    0.85
     single
    0.85
    Act Density 0.136%

    No Known Activations