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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and sources in a research context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.16
    ritten
    -0.16
    егÑĢа
    -0.15
     Gri
    -0.15
    ltra
    -0.15
    Acts
    -0.14
     ç±
    -0.14
    464
    -0.13
    ôme
    -0.13
    264
    -0.13
    POSITIVE LOGITS
    squ
    0.16
     squat
    0.16
    lys
    0.16
     squ
    0.16
    atat
    0.15
    ÅĤad
    0.14
    edes
    0.14
     IMessage
    0.14
     Squ
    0.14
    etto
    0.14
    Act Density 0.011%

    No Known Activations