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

    Neuronpedia

    INDEX
    Explanations

    references to change and development over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aires
    -0.15
    .toolbox
    -0.15
    ANNOT
    -0.14
    į¨
    -0.14
    .GraphicsUnit
    -0.14
    ptom
    -0.13
    Ral
    -0.13
    rogen
    -0.13
    anged
    -0.13
    apel
    -0.13
    POSITIVE LOGITS
    orent
    0.16
    inou
    0.15
    ox
    0.15
    IRROR
    0.14
     thrott
    0.14
     diplom
    0.13
    ayi
    0.13
    SWG
    0.13
    ziej
    0.13
    NEY
    0.13
    Act Density 0.613%

    No Known Activations