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

    Neuronpedia

    INDEX
    Explanations

    mentions of shower-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to showers and shower-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rian
    -0.76
    ravel
    -0.70
    folios
    -0.62
    KNOWN
    -0.62
    ourke
    -0.61
    */(
    -0.61
     Dominion
    -0.60
    sup
    -0.60
    REDACTED
    -0.60
    sem
    -0.59
    POSITIVE LOGITS
    robe
    0.98
     showers
    0.95
    ysis
    0.92
     curtain
    0.90
    ing
    0.85
     shower
    0.85
    bed
    0.82
    tub
    0.81
     ashore
    0.81
    issance
    0.81
    Act Density 0.011%

    No Known Activations