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

    Neuronpedia

    INDEX
    Explanations

    instances of watching or observing behaviors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fres
    -0.15
    à¥Įल
    -0.14
    ãĥ¼ãĥĢ
    -0.14
    coop
    -0.14
    IRR
    -0.14
     circulating
    -0.14
    Ñĥмов
    -0.14
    ì¡´
    -0.14
     writable
    -0.14
    aversal
    -0.14
    POSITIVE LOGITS
     closely
    0.27
     unfold
    0.25
    /watch
    0.19
    unfold
    0.18
     videos
    0.18
     proceedings
    0.15
     Watch
    0.15
     Videos
    0.15
     hab
    0.15
     watch
    0.14
    Act Density 0.095%

    No Known Activations