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

    Neuronpedia

    INDEX
    Explanations

    references to specific instances or things in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     препратки
    -0.83
     their
    -0.63
     the
    -0.62
    PyExc
    -0.55
    깐
    -0.54
    ]<<"
    -0.52
    ภัณฑ์
    -0.52
    égalité
    -0.49
    完
    -0.49
    ريل
    -0.48
    POSITIVE LOGITS
    ConstraintMaker
    0.94
    IntoConstraints
    0.83
    CloseOperation
    0.78
    ionView
    0.70
    DockStyle
    0.66
     at
    0.65
    HomeAsUpEnabled
    0.63
     المعيارى
    0.63
    itrine
    0.60
    ArrowToggle
    0.60
    Act Density 0.357%

    No Known Activations