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

    Neuronpedia

    INDEX
    Explanations

    references to baths or bathing-related terms

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

    bath and related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gregor
    -0.56
    Gregor
    -0.55
    emen
    -0.50
     Howie
    -0.50
     Willy
    -0.49
     eventId
    -0.49
    Willy
    -0.47
     Kui
    -0.46
     עלי
    -0.46
     Miki
    -0.46
    POSITIVE LOGITS
     bath
    2.08
    Bath
    1.81
     Bath
    1.78
    bath
    1.77
     BATH
    1.70
     baths
    1.63
     Baths
    1.50
    BATH
    1.47
     bathe
    1.11
     bathing
    1.03
    Act Density 0.004%

    No Known Activations