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

    Neuronpedia

    INDEX
    Explanations

    references to different types or structures of frames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rgan
    -0.19
    serie
    -0.17
    :CGPoint
    -0.17
    swagen
    -0.16
    ä¼´
    -0.16
    /problems
    -0.15
    room
    -0.15
    ive
    -0.15
    fos
    -0.15
    istic
    -0.14
    POSITIVE LOGITS
    hift
    0.28
    (Frame
    0.23
    ìĽĮíģ¬
    0.23
    buffers
    0.23
    æŀ¶
    0.22
    less
    0.22
    (frame
    0.21
    [frame
    0.20
     Frame
    0.20
     frame
    0.19
    Act Density 0.027%

    No Known Activations