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

    Neuronpedia

    INDEX
    Explanations

    instances of violent actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estekak
    -0.70
    ')['
    -0.67
    oredCriteria
    -0.67
     utafitiHapana
    -0.63
    ).
    -0.61
    [toxicity=0]
    -0.61
    ↵
    -0.61
    .*/
    -0.59
    .…
    -0.58
     المعيارى
    -0.57
    POSITIVE LOGITS
     ***!
    0.80
     AssemblyCompany
    0.74
     initComponents
    0.71
    تقاوى
    0.70
    Hentet
    0.65
    millimeters
    0.64
    ﹍﹍﹍
    0.63
    SourceChecksum
    0.63
    AndEndTag
    0.62
    tagHelperRunner
    0.62
    Act Density 25.488%

    No Known Activations