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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recognition or acknowledgment of individuals, typically in a context of capability or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -1.01
     lèvres
    -0.98
     pouvoirs
    -0.95
     épaules
    -0.86
     négociations
    -0.85
     vœux
    -0.85
     démocr
    -0.84
     attentes
    -0.81
     intérêts
    -0.79
     côtés
    -0.79
    POSITIVE LOGITS
     themselves
    1.08
    themselves
    0.91
     những
    0.72
     are
    0.67
     ones
    0.66
     members
    0.62
     mga
    0.60
     veritable
    0.59
     examples
    0.59
     They
    0.56
    Act Density 0.838%

    No Known Activations