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

    Neuronpedia

    INDEX
    Explanations

    references to film directors and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambda
    -0.18
    asca
    -0.15
    uster
    -0.15
    atif
    -0.15
    еко
    -0.14
     Characters
    -0.14
     fictional
    -0.14
     Dra
    -0.14
    ournals
    -0.14
     transcripts
    -0.13
    POSITIVE LOGITS
     director
    0.28
     directors
    0.26
     ÑĢеж
    0.25
    çĽ£çĿ£
    0.23
    director
    0.23
    -direct
    0.23
     Äijạo
    0.23
     ê°IJëıħ
    0.23
     directing
    0.22
    dir
    0.22
    Act Density 0.091%

    No Known Activations