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

    Neuronpedia

    INDEX
    Explanations

    unique qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    the term "unique" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apers
    -0.82
    Ö¼
    -0.66
     Rae
    -0.64
    docs
    -0.63
    EEE
    -0.63
    aper
    -0.63
    vation
    -0.63
    WARD
    -0.62
    onest
    -0.61
    arer
    -0.60
    POSITIVE LOGITS
    ively
    0.98
     identifier
    0.97
     identifiers
    0.86
    isable
    0.81
    iveness
    0.81
    iates
    0.80
    iqueness
    0.79
     insight
    0.78
     identity
    0.77
     blend
    0.76
    Act Density 0.026%

    No Known Activations