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

    Neuronpedia

    INDEX
    Explanations

    exclamatory phrases expressing surprise or strong emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.75
     المعيارى
    -0.72
     layui
    -0.63
    extAlignment
    -0.63
     propOrder
    -0.60
    TAWA
    -0.59
    RectangleBorder
    -0.59
    omitempty
    -0.58
    glMatrixMode
    -0.56
    তথ্যসূত্র
    -0.56
    POSITIVE LOGITS
     what
    0.73
     how
    0.72
     why
    0.69
     these
    0.69
    what
    0.57
     there
    0.56
    !
    0.55
    why
    0.55
     These
    0.54
     this
    0.54
    Act Density 0.072%

    No Known Activations