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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "draw" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inoxydable
    -1.10
     /\.(
    -0.90
    ContentAsync
    -0.90
    enderror
    -0.89
    ParallelGroup
    -0.87
    lepší
    -0.85
     hâte
    -0.84
    EndInit
    -0.84
    EndGlobalSection
    -0.83
     modalités
    -0.83
    POSITIVE LOGITS
     drawn
    1.67
     draw
    1.52
     draws
    1.50
    Draw
    1.49
     Draws
    1.48
     Draw
    1.46
     drawing
    1.45
     DRAW
    1.44
    draw
    1.42
    drawn
    1.41
    Act Density 0.062%

    No Known Activations