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

    Neuronpedia

    INDEX
    Explanations

    keywords related to watching, reading, and consuming content such as "watch," "read," "video," "story," "interview."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of multimedia content such as videos or episodes, particularly with instructions to "watch" or "read."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeda
    -0.81
    ylum
    -0.74
    bably
    -0.73
    akery
    -0.68
    Ħ¢
    -0.67
    venge
    -0.66
    ADRA
    -0.66
    yz
    -0.65
    illus
    -0.64
    ithmetic
    -0.64
    POSITIVE LOGITS
     below
    0.93
     excerpt
    0.92
     Transcript
    0.86
     details
    0.85
     HERE
    0.84
     highlights
    0.84
     LINK
    0.80
     Highlights
    0.78
     HuffPost
    0.78
     LAT
    0.78
    Act Density 0.161%

    No Known Activations