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

    Neuronpedia

    INDEX
    Explanations

    references to legislative or policy changes

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

    reform and reforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Có
    -0.47
    eye
    -0.47
    an
    -0.47
    Number
    -0.46
    ===============
    -0.45
     Buckley
    -0.45
    (
    -0.44
    The
    -0.43
    Gesellschaft
    -0.42
    Single
    -0.42
    POSITIVE LOGITS
     reform
    1.90
     reforms
    1.84
    reform
    1.76
     Reform
    1.74
    Reform
    1.70
     Reforms
    1.59
     reforming
    1.29
     reformers
    1.29
     reformas
    1.27
    改革
    1.25
    Act Density 0.002%

    No Known Activations