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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.89
    LabelTagHelper
    -0.70
    DeleteBehavior
    -0.66
    Viitteet
    -0.63
    AutoScaleMode
    -0.58
    setVerticalGroup
    -0.58
    TintMode
    -0.57
    RenderAtEndOf
    -0.56
     годом
    -0.52
    ädie
    -0.50
    POSITIVE LOGITS
     sure
    0.69
     joaat
    0.54
     allowed
    0.53
     above
    0.53
     alone
    0.52
     phased
    0.52
     opposed
    0.52
    above
    0.51
     /\.(
    0.50
     stupid
    0.50
    Act Density 0.212%

    No Known Activations