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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and concepts related to court rulings and procedural matters

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

    defendants'

    np_acts-logits-general · gemini-2.5-flash-lite

    paragraph breaks or empty lines that mark a new paragraph/section boundary.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ſſung
    -1.70
    ロウィン
    -1.68
    <unused41>
    -1.68
    <unused79>
    -1.67
    <unused74>
    -1.67
    <unused68>
    -1.67
    <unused52>
    -1.67
    <unused8>
    -1.66
    <unused3>
    -1.66
    [@BOS@]
    -1.66
    POSITIVE LOGITS
    I
    0.65
    The
    0.60
    But
    0.57
    1
    0.56
    By
    0.53
    2
    0.53
    (
    0.53
    In
    0.53
    For
    0.52
    If
    0.50
    Act Density 0.881%

    No Known Activations