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

    Neuronpedia

    INDEX
    Explanations

    references to specific movies or film titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĸ
    -0.14
    ichel
    -0.14
     (~(
    -0.14
    serter
    -0.14
    ãĥ¯ãĥ¼
    -0.14
    bler
    -0.14
     Rarity
    -0.13
     deeds
    -0.13
    malink
    -0.13
    illard
    -0.13
    POSITIVE LOGITS
     movie
    0.17
     Movie
    0.16
    _hooks
    0.15
     franchise
    0.14
     Skin
    0.14
     Incorporated
    0.14
    onga
    0.14
     Shock
    0.14
    Cop
    0.14
    isodes
    0.14
    Act Density 0.254%

    No Known Activations