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

    Neuronpedia

    INDEX
    Explanations

    references to film directors and characteristics of their movies, especially in the crime and romance genres

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cott
    -0.15
     attendance
    -0.15
    throp
    -0.15
    logan
    -0.15
     Sequ
    -0.15
    ctest
    -0.14
     prank
    -0.14
     hedge
    -0.14
     Strauss
    -0.14
     Pars
    -0.13
    POSITIVE LOGITS
     noir
    0.31
     Noir
    0.29
     Femme
    0.24
     pulp
    0.24
     femme
    0.24
     dames
    0.21
     femmes
    0.19
     crime
    0.18
     private
    0.18
     HARD
    0.18
    Act Density 0.034%

    No Known Activations