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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negotiation or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .dk
    -0.15
    견
    -0.14
    Ñįн
    -0.14
    iew
    -0.14
     konu
    -0.14
    icket
    -0.14
     Protective
    -0.14
     creep
    -0.14
    lec
    -0.13
    WA
    -0.13
    POSITIVE LOGITS
    ContentLoaded
    0.17
    NOP
    0.16
    eah
    0.15
    .fp
    0.15
    quarter
    0.15
    боÑĤ
    0.14
    [section
    0.14
    SPATH
    0.14
     Seal
    0.14
    qli
    0.14
    Act Density 0.315%

    No Known Activations