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

    Neuronpedia

    INDEX
    Explanations

    numbers within sentences alongside various forms of punctuation

    oai_token-act-pair · gpt-3.5-turbo

    references to research and inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.57
     aerobic
    -0.55
     Lyons
    -0.54
     Guatem
    -0.54
     Mous
    -0.54
     laboratory
    -0.53
     PowerPoint
    -0.53
     Osc
    -0.53
     Huntington
    -0.52
     mathemat
    -0.52
    POSITIVE LOGITS
    âĢ
    1.30
    îĢ
    1.26
    [/
    1.20
    âĶ
    1.18
     âĶĤ
    1.17
    âĸł
    1.15
     âĢ
    1.12
     **
    1.09
    âĺ
    1.08
     ðŁij
    1.08
    Act Density 2.998%

    No Known Activations