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

    Neuronpedia

    INDEX
    Explanations

    linguistic structures related to drama and theater concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ätze
    -0.27
     Jahre
    -0.19
     Produkte
    -0.18
    bilder
    -0.17
    reste
    -0.17
    ände
    -0.17
     Filme
    -0.16
    uhe
    -0.16
     кÑĢаÑĹн
    -0.15
    ÙĬÙĦÙĬ
    -0.15
    POSITIVE LOGITS
    üssen
    0.28
     Jahren
    0.28
    ibus
    0.24
     ÑĥÑĢовнÑı
    0.23
    ern
    0.22
    ügen
    0.22
    каÑħ
    0.22
     днÑı
    0.21
    еÑĢаÑħ
    0.20
     ÑĤемпеÑĢаÑĤÑĥ
    0.20
    Act Density 0.067%

    No Known Activations