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

    Neuronpedia

    INDEX
    Explanations

    topics related to political divisions and social commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    standen
    -0.15
    venes
    -0.15
    iesen
    -0.15
    iren
    -0.14
     çī©
    -0.14
     sÆ°
    -0.14
    haven
    -0.14
    ãĥ³ãĥĢ
    -0.14
    isco
    -0.14
    ¤ij
    -0.13
    POSITIVE LOGITS
     Oper
    0.17
    agi
    0.15
    iteli
    0.14
    OLUME
    0.14
    quarter
    0.14
     Mah
    0.14
    .yy
    0.14
     Sect
    0.14
    .bt
    0.13
    unar
    0.13
    Act Density 0.660%

    No Known Activations