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

    Neuronpedia

    INDEX
    Explanations

    titles and references to specific literary works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xygen
    -0.17
     books
    -0.17
     soundtrack
    -0.15
     quoting
    -0.15
     personality
    -0.15
     Books
    -0.15
     reserved
    -0.15
    studio
    -0.15
    -books
    -0.15
     libros
    -0.14
    POSITIVE LOGITS
     essay
    0.23
     essays
    0.22
     stories
    0.22
     short
    0.22
     nov
    0.21
    çŁŃ
    0.20
     shorter
    0.20
     anth
    0.19
    short
    0.19
    æĶ¶å½ķ
    0.19
    Act Density 0.136%

    No Known Activations