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

    Neuronpedia

    INDEX
    Explanations

    words related to news or updates

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "WATCH" and related phrases, indicating a focus on video or media content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gers
    -0.78
    stood
    -0.76
    lee
    -0.75
    este
    -0.74
    arist
    -0.74
    ad
    -0.74
    gy
    -0.71
    athe
    -0.70
    ator
    -0.70
    esse
    -0.70
    POSITIVE LOGITS
    INGTON
    1.26
    BOOK
    1.24
    MORE
    1.22
    HEAD
    1.19
    ISM
    1.16
     PHOTO
    1.15
    DOWN
    1.14
    OGR
    1.12
     REPORT
    1.11
    ATURE
    1.10
    Act Density 0.039%

    No Known Activations