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

    Neuronpedia

    INDEX
    Explanations

    references to monetary value or wealth

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

    words ending in worth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sik
    -0.47
     Geheim
    -0.45
    Drag
    -0.45
     drag
    -0.44
    setupUi
    -0.44
     testGet
    -0.43
    Api
    -0.42
    DRAG
    -0.42
    Sik
    -0.42
    drag
    -0.41
    POSITIVE LOGITS
    worth
    3.11
    WORTH
    2.77
    Worth
    2.19
    worths
    2.08
     Worth
    2.06
     WORTH
    1.93
     worth
    1.91
    sworth
    1.80
    wort
    1.38
    worthy
    1.30
    Act Density 0.003%

    No Known Activations