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

    Neuronpedia

    INDEX
    Explanations

    uncertainty or lack of clarity in statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gall
    -0.75
    ocard
    -0.75
    endar
    -0.74
    anders
    -0.70
    glas
    -0.69
    INT
    -0.69
    die
    -0.68
    ingo
    -0.68
    trak
    -0.67
    uilding
    -0.67
    POSITIVE LOGITS
    comings
    0.74
    wcs
    0.74
     ambiguous
    0.70
    icably
    0.67
     chronological
    0.65
    ly
    0.64
     detectable
    0.64
     unclear
    0.63
    iary
    0.63
     ambiguity
    0.62
    Act Density 0.009%

    No Known Activations