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

    Neuronpedia

    INDEX
    Explanations

    references to specific actors and their roles within a television series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    жд
    -0.16
     ÙħÙĤد
    -0.15
    ihad
    -0.15
     Kut
    -0.15
    ãģĦãģĭ
    -0.15
     laser
    -0.14
    EqualityComparer
    -0.14
    isas
    -0.14
    ppe
    -0.14
    OrNil
    -0.14
    POSITIVE LOGITS
     Park
    0.43
    Park
    0.38
     Lee
    0.38
     Lim
    0.34
     Kim
    0.32
    Lee
    0.31
     PARK
    0.31
     lee
    0.31
     Cho
    0.30
     park
    0.30
    Act Density 0.018%

    No Known Activations