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

    Neuronpedia

    INDEX
    Explanations

    references to relevance and its relation to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rav
    -0.17
    urr
    -0.17
    gb
    -0.16
    eln
    -0.16
    orman
    -0.15
    sm
    -0.15
    ald
    -0.14
    FIXME
    -0.14
    ìĪł
    -0.14
    asley
    -0.14
    POSITIVE LOGITS
    äºİ
    0.20
    ly
    0.19
    entin
    0.17
     äºİ
    0.17
     ÄijÃŃch
    0.16
     ìĤ¬íķŃ
    0.15
    ucas
    0.15
    unittest
    0.15
    iable
    0.15
    mente
    0.15
    Act Density 0.018%

    No Known Activations