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

    Neuronpedia

    INDEX
    Explanations

    names and terms related to specific individuals or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nez
    -0.17
    ULE
    -0.17
    ARM
    -0.16
    окÑĥ
    -0.16
    IPP
    -0.15
    kur
    -0.15
    ROTO
    -0.15
    air
    -0.14
    atsu
    -0.13
    AIR
    -0.13
    POSITIVE LOGITS
    ieten
    0.17
    put
    0.16
    ivos
    0.16
    endra
    0.15
     pylint
    0.15
    ãĥªãĥ¼ãĤº
    0.15
    inder
    0.14
    adian
    0.14
    ìĨį
    0.14
    idian
    0.14
    Act Density 0.107%

    No Known Activations