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

    Neuronpedia

    INDEX
    Explanations

    words related to uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    references to uncertainty and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovie
    -0.84
    gdala
    -0.83
    artist
    -0.82
    utsche
    -0.78
    olphins
    -0.78
    tha
    -0.77
    gression
    -0.77
    waukee
    -0.76
    audi
    -0.76
    ermanent
    -0.74
    POSITIVE LOGITS
     surrounds
    0.89
     uncertainty
    0.89
     fallout
    0.85
     shorth
    0.84
     uncertainties
    0.81
     surrounding
    0.79
    lessly
    0.76
     horizon
    0.73
     conting
    0.72
     arising
    0.72
    Act Density 0.025%

    No Known Activations