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

    Neuronpedia

    INDEX
    Explanations

    references to uncertainty and risk in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eda
    -0.17
    eder
    -0.15
    ulu
    -0.14
    strup
    -0.14
     ingr
    -0.14
    nnen
    -0.13
    465
    -0.13
    -Sah
    -0.13
     bon
    -0.13
    çĹ
    -0.13
    POSITIVE LOGITS
     uncertainty
    0.54
     uncertainties
    0.46
     Unc
    0.45
     uncertain
    0.41
    unc
    0.39
    Unc
    0.38
     uncert
    0.34
    _unc
    0.33
     unsure
    0.31
    ertainty
    0.27
    Act Density 0.145%

    No Known Activations