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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or statements

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

    wonder if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.62
     للاسماء
    -0.62
    PerformLayout
    -0.59
    AutoScaleMode
    -0.57
     AssemblyCompany
    -0.57
     ſte
    -0.56
    jsxFileName
    -0.54
     Houſe
    -0.52
    LookAnd
    -0.50
    ArrowToggle
    -0.49
    POSITIVE LOGITS
     perhaps
    0.54
     možná
    0.49
    perhaps
    0.47
     possibly
    0.46
     quizás
    0.46
    也許
    0.45
     quizá
    0.45
     might
    0.44
     may
    0.44
    也许
    0.44
    Act Density 0.010%

    No Known Activations