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

    Neuronpedia

    INDEX
    Explanations

    references to baths and bathing experiences

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

    bath and bathing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gregor
    -0.53
    Willy
    -0.52
     Gregor
    -0.51
     eventId
    -0.49
    UnsafeEnabled
    -0.49
    miguel
    -0.49
     jacobs
    -0.49
    elar
    -0.48
     Howie
    -0.48
    oneofs
    -0.47
    POSITIVE LOGITS
     bath
    1.07
     Bath
    1.05
    Bath
    1.04
     BATH
    1.02
    bath
    0.85
     Bathing
    0.85
     Baths
    0.83
     bathing
    0.83
    BATH
    0.81
     bathe
    0.79
    Act Density 0.009%

    No Known Activations