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

    Neuronpedia

    INDEX
    Explanations

    headline text in bold indicating that the reader MUST watch a particular video

    oai_token-act-pair · gpt-3.5-turbo

    references to video content and pleas to watch more videos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bably
    -0.64
    è¦ļéĨĴ
    -0.63
    \\\\\\\\
    -0.61
     interchange
    -0.61
    naires
    -0.60
    channelAvailability
    -0.58
     nurs
    -0.58
     congr
    -0.56
     horm
    -0.56
    DragonMagazine
    -0.56
    POSITIVE LOGITS
     Videos
    1.09
     Thumbnails
    0.89
     Replay
    0.83
    emort
    0.73
    elight
    0.68
    clips
    0.65
    amera
    0.64
    Video
    0.63
     Error
    0.61
    olitics
    0.60
    Act Density 0.024%

    No Known Activations