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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "drawn" in various contexts

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

    drawn by, from, into, in, by, towards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijani
    -0.77
    pidou
    -0.75
     dieſer
    -0.75
    Personensuche
    -0.75
    <unused23>
    -0.71
    <unused28>
    -0.71
    <unused41>
    -0.70
    [@BOS@]
    -0.70
    <unused43>
    -0.70
    <unused7>
    -0.70
    POSITIVE LOGITS
     drawn
    1.98
     Drawn
    1.69
    drawn
    1.56
    Drawn
    1.56
    rawn
    0.90
     Draw
    0.84
     drew
    0.82
    Draw
    0.79
     draw
    0.78
     Drew
    0.71
    Act Density 0.004%

    No Known Activations