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

    Neuronpedia

    INDEX
    Explanations

    key terms related to facilities and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rani
    -0.16
    çļ®
    -0.15
     cup
    -0.14
    wort
    -0.14
    endor
    -0.14
    éłĤ
    -0.14
     midd
    -0.14
     misc
    -0.14
    -fold
    -0.14
    osph
    -0.14
    POSITIVE LOGITS
    /examples
    0.16
    otron
    0.16
    imore
    0.15
    ikel
    0.15
     Hatch
    0.14
    umba
    0.14
    udeau
    0.14
    ilion
    0.14
     Grimm
    0.14
    .lon
    0.14
    Act Density 0.531%

    No Known Activations