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

    Films directed/produced by someone

    np_acts-logits-general · gemini-2.0-flash

    creative authorship attribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dostęp
    -0.55
    mona
    -0.50
     esist
    -0.48
    held
    -0.47
    stool
    -0.46
     held
    -0.46
     conciertos
    -0.44
     bär
    -0.43
     example
    -0.43
    Model
    -0.42
    POSITIVE LOGITS
     authorship
    0.83
     auteur
    0.82
     choreographer
    0.82
     screenwriter
    0.75
     auteurs
    0.73
    songwriter
    0.73
    #+#
    0.72
    :✨
    0.72
    InjectAttribute
    0.71
    Geplaatst
    0.71
    Act Density 0.159%

    No Known Activations