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

    Neuronpedia

    INDEX
    Explanations

    text related to JavaScript video content

    oai_token-act-pair · gpt-3.5-turbo

    content related to video playback instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewed
    -0.64
     brow
    -0.58
     remem
    -0.58
    Else
    -0.57
    alach
    -0.56
    manship
    -0.55
     sciences
    -0.55
     onward
    -0.54
    :]
    -0.54
     Nights
    -0.54
    POSITIVE LOGITS
     Advertisement
    0.64
    qus
    0.63
    videos
    0.62
    IFF
    0.61
     LAR
    0.61
    interstitial
    0.60
    erer
    0.58
    ERY
    0.58
     Sha
    0.56
    URE
    0.56
    Act Density 0.029%

    No Known Activations