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

    Neuronpedia

    INDEX
    Explanations

    expressions of predictability and repetitiveness in humor and content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gid
    -0.17
     unlike
    -0.15
     sty
    -0.14
    ophy
    -0.14
     authService
    -0.14
     Sew
    -0.14
     seperate
    -0.14
    raph
    -0.13
    onaut
    -0.13
     Inline
    -0.13
    POSITIVE LOGITS
     predictable
    0.18
     repet
    0.18
     repetition
    0.18
     repetitive
    0.18
     unins
    0.18
    predict
    0.17
     identical
    0.17
    affer
    0.16
     repetitions
    0.15
     generic
    0.15
    Act Density 0.191%

    No Known Activations