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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate duty or expectation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     հղումներ
    -0.67
     Aitken
    -0.64
    ImageContext
    -0.62
     craindre
    -0.61
     mergeFrom
    -0.61
    NewUrlParser
    -0.61
    Risks
    -0.60
    SearchTree
    -0.60
    withOpacity
    -0.60
     MenuView
    -0.60
    POSITIVE LOGITS
    SSSS
    0.75
     ویکی‌پدیای
    0.75
    abetes
    0.72
      
    0.69
    supposed
    0.67
     supposed
    0.62
     UIImageView
    0.62
     WPS
    0.60
     trick
    0.59
     Wand
    0.59
    Act Density 0.006%

    No Known Activations