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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "draw" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inoxydable
    -1.02
    ContentAsync
    -0.89
    ptonshire
    -0.81
    enderror
    -0.80
     Schulte
    -0.79
     Bote
    -0.78
     modalités
    -0.77
     espirituales
    -0.76
    ilene
    -0.76
    Bism
    -0.75
    POSITIVE LOGITS
     drawn
    1.53
     draw
    1.40
     draws
    1.40
     Draws
    1.39
     drawing
    1.34
    draw
    1.34
     Drawn
    1.33
    Draw
    1.33
     DRAW
    1.30
     Draw
    1.30
    Act Density 0.056%

    No Known Activations