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

    Neuronpedia

    INDEX
    Explanations

    medical conditions and treatment terms

    oai_token-act-pair · gpt-3.5-turbo

    names of classical literature and prominent historical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.68
    ratom
    -0.62
    20439
    -0.60
    Picture
    -0.58
     Berkshire
    -0.55
     âĢº
    -0.53
    PRE
    -0.52
     NBN
    -0.52
     Canaver
    -0.51
     Wick
    -0.50
    POSITIVE LOGITS
    ).[
    0.99
    )."
    0.94
    ]."
    0.94
     respectively
    0.94
    )).
    0.89
    anwhile
    0.88
    ))))
    0.86
    .).
    0.83
     etc
    0.78
    ).
    0.75
    Act Density 2.192%

    No Known Activations