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

    Neuronpedia

    INDEX
    Explanations

    terms related to learning and educational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ural
    -0.17
    è¨
    -0.16
    aji
    -0.16
    ewater
    -0.15
    uro
    -0.14
    sy
    -0.14
    ims
    -0.14
    jes
    -0.13
    bis
    -0.13
    reh
    -0.13
    POSITIVE LOGITS
    andest
    0.17
    .Meta
    0.16
    Wunused
    0.16
    /Instruction
    0.16
    nez
    0.15
    quan
    0.15
    mite
    0.15
    ضاء
    0.15
    _utilities
    0.15
    ÑĤаб
    0.14
    Act Density 0.041%

    No Known Activations