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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     def
    -0.17
    isch
    -0.16
    rab
    -0.16
     Wig
    -0.15
    647
    -0.15
     express
    -0.15
     hip
    -0.14
    -
    -0.14
    ulan
    -0.14
     fast
    -0.14
    POSITIVE LOGITS
    IRST
    0.16
    oret
    0.15
    avra
    0.14
     eskort
    0.14
    folio
    0.14
    ulk
    0.14
    xCD
    0.14
    اصÙĦ
    0.14
    .Utc
    0.14
     å¦
    0.13
    Act Density 0.006%

    No Known Activations