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

    Neuronpedia

    INDEX
    Explanations

    references to media announcements, such as trailers and release information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovy
    -0.15
    ilage
    -0.15
     Jong
    -0.15
    пеÑĩ
    -0.14
    _trampoline
    -0.14
    ĵåIJį
    -0.13
    ëĵ¯
    -0.13
    /effects
    -0.13
    .CustomButton
    -0.13
    UIAlert
    -0.13
    POSITIVE LOGITS
     interview
    0.23
     review
    0.21
     preview
    0.20
     REVIEW
    0.20
     Review
    0.19
     Interview
    0.18
     exclusive
    0.18
    -review
    0.17
    preview
    0.17
     exclus
    0.17
    Act Density 0.091%

    No Known Activations