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

    Neuronpedia

    INDEX
    Explanations

    tokens with high-frequency single letters or abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lage
    -0.18
    ãĥ£
    -0.18
    itori
    -0.17
    i
    -0.16
    ProcAddress
    -0.15
    obao
    -0.14
    icao
    -0.14
    alytics
    -0.14
     Cah
    -0.14
    583
    -0.14
    POSITIVE LOGITS
     Jenner
    0.13
    toa
    0.13
    ÂĢÂĻ
    0.13
    aurus
    0.13
     Aure
    0.13
     Jasper
    0.13
    xis
    0.13
    affer
    0.12
    umlu
    0.12
     unpack
    0.12
    Act Density 0.209%

    No Known Activations