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

    Neuronpedia

    INDEX
    Explanations

    references to research studies and academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    athi
    -0.14
    emi
    -0.14
    raph
    -0.14
     Miscellaneous
    -0.14
     cush
    -0.13
    Ø·ÙĨ
    -0.13
     adet
    -0.13
    credible
    -0.13
     Ing
    -0.13
    ắn
    -0.13
    POSITIVE LOGITS
    201
    0.17
    200
    0.17
    ">//
    0.16
    seys
    0.15
    198
    0.14
     mk
    0.14
    ãĤ²
    0.14
    mk
    0.13
    ió
    0.13
    readcr
    0.13
    Act Density 0.026%

    No Known Activations