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

    Neuronpedia

    INDEX
    Explanations

    titles and references related to TV shows and movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ·ãĥªãĥ¼ãĤº
    -0.16
     Presents
    -0.14
    ola
    -0.14
    lain
    -0.13
    .future
    -0.13
    roi
    -0.13
    bff
    -0.13
    ipes
    -0.13
     degrees
    -0.13
    ents
    -0.13
    POSITIVE LOGITS
     trailer
    0.26
     review
    0.26
     Review
    0.22
     coming
    0.22
    -review
    0.21
     delayed
    0.20
     Trailer
    0.20
     REVIEW
    0.20
     Lands
    0.19
     arriving
    0.19
    Act Density 0.180%

    No Known Activations