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

    Neuronpedia

    INDEX
    Explanations

    references to titles or forms of identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upy
    -0.07
    lez
    -0.07
    è¡Ĺ
    -0.07
    embre
    -0.06
    urch
    -0.06
    irit
    -0.06
    ارا
    -0.06
    vailability
    -0.06
    rag
    -0.06
    vy
    -0.06
    POSITIVE LOGITS
    ateria
    0.07
    itzer
    0.07
     puss
    0.06
    LOUR
    0.06
    apesh
    0.06
    utable
    0.06
     Guard
    0.06
    rams
    0.06
     Dyn
    0.06
     ni
    0.06
    Act Density 0.010%

    No Known Activations