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

    Neuronpedia

    INDEX
    Explanations

    elements related to user interface components and their properties in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -1.03
    TintMode
    -1.00
    #+#
    -0.96
    principalTable
    -0.94
     Савезне
    -0.92
     kaarangay
    -0.92
     Roskov
    -0.91
    astéroïdes
    -0.90
     виправивши
    -0.88
     AssemblyCulture
    -0.85
    POSITIVE LOGITS
     mostly
    0.61
     therefore
    0.55
     will
    0.52
     mainly
    0.52
     also
    0.50
     sometimes
    0.49
     included
    0.49
     mind
    0.49
     generally
    0.49
     primarily
    0.48
    Act Density 0.154%

    No Known Activations