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

    Neuronpedia

    INDEX
    Explanations

    expressions related to confusion and understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ImageContext
    -0.67
     समीक्षक
    -0.60
    λευτα
    -0.56
    DoubleQuotes
    -0.56
    المشاركات
    -0.52
     VIDEOTAPE
    -0.51
    findpost
    -0.50
    Бахар
    -0.48
     initComponents
    -0.48
     lenker
    -0.47
    POSITIVE LOGITS
     strange
    1.05
     inexplicable
    1.04
     puzzling
    1.01
     bizarre
    0.98
     perplexing
    0.94
     unexplained
    0.92
    strange
    0.90
     baffling
    0.90
     puzzled
    0.88
    Strange
    0.87
    Act Density 0.283%

    No Known Activations