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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "with" in various contexts

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

    with common compound words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zeigen
    -0.36
    勢
    -0.36
     solid
    -0.36
    ActionEvent
    -0.35
    право
    -0.35
     Ek
    -0.35
    感
    -0.34
     revel
    -0.34
    felde
    -0.34
     effective
    -0.34
    POSITIVE LOGITS
    drawing
    0.76
    draw
    0.74
    stand
    0.68
    drawal
    0.63
    Draw
    0.63
    drawn
    0.62
    DRAW
    0.59
    held
    0.57
    STAND
    0.56
    WITH
    0.56
    Act Density 0.065%

    No Known Activations