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

    Neuronpedia

    INDEX
    Explanations

    references to notes and citations in scholarly or formal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    posium
    -0.15
     Geh
    -0.14
    iki
    -0.14
    166
    -0.14
    ÑĢав
    -0.14
     brick
    -0.14
    bedo
    -0.13
    aroo
    -0.13
    ANGED
    -0.13
    ero
    -0.13
    POSITIVE LOGITS
    egend
    0.15
    pain
    0.14
     meille
    0.14
    è°±
    0.14
     ActionTypes
    0.14
    xdd
    0.14
    hoff
    0.14
    éªĮ
    0.14
    stk
    0.13
    è²Į
    0.13
    Act Density 0.001%

    No Known Activations