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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "on" and its variations, indicating a focus on descriptions or actions that are contextually relevant to a topic

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

    drawing on or from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.50
     beginnetje
    -0.49
     مرئيه
    -0.47
    contentLoaded
    -0.46
     nothwendig
    -0.46
     дописавши
    -0.45
     abomination
    -0.45
    /**
    -0.44
     ſich
    -0.44
     Verſ
    -0.44
    POSITIVE LOGITS
     Draw
    0.77
     draw
    0.75
     draws
    0.70
     Drawing
    0.69
     drawing
    0.68
    Draw
    0.68
     Draws
    0.66
    Draws
    0.65
    draw
    0.63
    drawing
    0.63
    Act Density 0.008%

    No Known Activations