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

    Neuronpedia

    INDEX
    Explanations

    titles of films or reviews related to movies and their analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gould
    -0.15
    ManagerInterface
    -0.15
     UIBar
    -0.15
    æķħäºĭ
    -0.14
     Setter
    -0.13
     SET
    -0.13
     Vogue
    -0.13
     Flake
    -0.13
    .story
    -0.13
    _deps
    -0.13
    POSITIVE LOGITS
     reviews
    0.19
     podcast
    0.19
    reviews
    0.18
     podcasts
    0.18
     Reviews
    0.17
     Doctor
    0.16
     licensors
    0.16
     Podcast
    0.16
     Movies
    0.15
    ListNode
    0.15
    Act Density 0.219%

    No Known Activations