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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating statistical significance or nonsignificance in research findings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    eficent
    -0.56
    maries
    -0.53
     tiết
    -0.52
    hock
    -0.52
    aktor
    -0.52
    hew
    -0.51
    hoot
    -0.50
    värr
    -0.50
    hadow
    -0.49
    shed
    -0.49
    POSITIVE LOGITS
     ModelExpression
    0.66
     tartalomajánló
    0.66
     AssemblyProduct
    0.61
    pushFollow
    0.61
    تقاوى
    0.60
     himo
    0.57
    Спасылкі
    0.56
     McKnight
    0.55
    IBOutlet
    0.55
    ruptedException
    0.53
    Act Density 0.024%

    No Known Activations