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

    Neuronpedia

    INDEX
    Explanations

    expressions of disgust or negative reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    disgusting / repulsive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.79
    ChromeDriver
    -0.74
    IntoConstraints
    -0.73
    expandindo
    -0.71
     ivelany
    -0.69
    featureID
    -0.68
     AssemblyVersion
    -0.68
     MainAxisSize
    -0.68
     ویکی‌پدی
    -0.68
    rungsseite
    -0.66
    POSITIVE LOGITS
     disgusting
    0.75
     disgust
    0.70
    gusting
    0.60
     disgusted
    0.59
     repul
    0.57
    🤮
    0.55
    🤢
    0.51
    gusted
    0.50
     dirty
    0.50
     distaste
    0.50
    Act Density 0.024%

    No Known Activations