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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence boundaries indicating ends or separations in thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -1.02
    rungsseite
    -0.94
    AddHtmlAttribute
    -0.87
    تقاوى
    -0.81
    ReusableCell
    -0.78
     AssemblyCulture
    -0.76
    addCriterion
    -0.76
    homonymie
    -0.74
     transfieras
    -0.72
    Personendaten
    -0.72
    POSITIVE LOGITS
     Alternatively
    0.48
     then
    0.47
    ٱ
    0.46
    WEBPACK
    0.46
     cos
    0.45
     facult
    0.44
     FRANCISCO
    0.43
    Alternatively
    0.43
     andata
    0.43
    cmdline
    0.42
    Act Density 0.554%

    No Known Activations