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

    Neuronpedia

    INDEX
    Explanations

    issues related to errors and malfunctions in processes or systems

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

    words or phrases related to performing and achieving tasks or actions.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.81
     <<<<<<<<<<<<<<
    -0.67
    lgari
    -0.62
    antaranya
    -0.59
    glClear
    -0.58
     biling
    -0.57
    liau
    -0.57
     ***!
    -0.56
     onlyOwner
    -0.55
     ब्रेकडाउन
    -0.55
    POSITIVE LOGITS
     anymore
    1.13
     nor
    1.01
     unless
    0.85
     nemmeno
    0.81
     due
    0.78
     yet
    0.73
    unless
    0.68
     because
    0.68
     even
    0.68
     alcun
    0.68
    Act Density 1.256%

    No Known Activations