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

    Neuronpedia

    INDEX
    Explanations

    important or notable individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals with specific societal roles or professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernels
    -0.79
    rams
    -0.72
     Monsters
    -0.71
    arus
    -0.71
     Pieces
    -0.71
     Tags
    -0.70
    ippers
    -0.70
    Beer
    -0.67
     Reps
    -0.67
    iencies
    -0.67
    POSITIVE LOGITS
     who
    1.12
     named
    1.03
     whose
    0.94
     whom
    0.91
    who
    0.86
    whose
    0.79
    ess
    0.77
     specializing
    0.76
     nicknamed
    0.75
    friend
    0.75
    Act Density 0.337%

    No Known Activations