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

    Neuronpedia

    INDEX
    Explanations

    unique or distinctive characteristics within a context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unique."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apers
    -0.75
    vation
    -0.66
    Ö¼
    -0.66
    aper
    -0.64
     Rae
    -0.62
     Alive
    -0.61
    rollers
    -0.60
     PRESS
    -0.60
    onest
    -0.59
    docs
    -0.59
    POSITIVE LOGITS
    ively
    1.01
     identifier
    0.93
     identifiers
    0.86
    iveness
    0.84
    isable
    0.84
    iates
    0.82
    ulkan
    0.80
    Magikarp
    0.79
     unique
    0.78
    tymology
    0.78
    Act Density 0.020%

    No Known Activations