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

    Neuronpedia

    INDEX
    Explanations

    terms related to methods and frameworks in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Core
    -0.15
    /we
    -0.15
    inton
    -0.15
    eldo
    -0.15
    irus
    -0.14
    akan
    -0.14
    pard
    -0.14
    rol
    -0.14
    udi
    -0.14
     physical
    -0.13
    POSITIVE LOGITS
    /legal
    0.21
    -cultural
    0.20
    -economic
    0.19
    ä¸ĬçļĦ
    0.18
     açı
    0.17
    dimension
    0.17
     dimension
    0.16
    /pol
    0.16
    /material
    0.15
    .experimental
    0.15
    Act Density 0.220%

    No Known Activations