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

    Neuronpedia

    INDEX
    Explanations

    phrases related to removing clothing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to urgent actions or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.70
    maxwell
    -0.67
    REDACTED
    -0.67
     OD
    -0.64
    女
    -0.61
     overlapping
    -0.61
     Enhanced
    -0.60
    Closure
    -0.59
     interstate
    -0.58
    Balt
    -0.57
    POSITIVE LOGITS
     trou
    1.59
    ¬
    0.89
    mentation
    0.84
    ¨
    0.84
    pants
    0.84
    pter
    0.81
    nces
    0.79
    stration
    0.79
    ments
    0.79
    ©¶æ
    0.79
    Act Density 0.009%

    No Known Activations