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

    Neuronpedia

    INDEX
    Explanations

    references to audience engagement and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rement
    -0.17
    978
    -0.15
    umper
    -0.14
    iek
    -0.14
    ÑĨей
    -0.14
    åģ
    -0.14
     tane
    -0.14
    æĮ
    -0.14
    828
    -0.14
    848
    -0.14
    POSITIVE LOGITS
     Ñģвоим
    0.19
    les
    0.18
     capt
    0.16
     Ñģвоими
    0.15
    eah
    0.15
    posit
    0.14
    eyi
    0.14
    Ļ
    0.14
    imb
    0.14
     headlines
    0.14
    Act Density 0.127%

    No Known Activations