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

    Neuronpedia

    INDEX
    Explanations

    URLs to watch videos

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Watch" indicating video content or calls to view something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bably
    -0.78
    ctrl
    -0.70
    ãĥł
    -0.66
    emia
    -0.66
     trave
    -0.65
     inval
    -0.65
     rhy
    -0.64
     coma
    -0.64
    cffff
    -0.62
    recy
    -0.61
    POSITIVE LOGITS
    tower
    1.35
    dog
    1.16
    dogs
    1.06
     Dogs
    0.90
    ESPN
    0.90
    ing
    0.87
     clips
    0.83
     Below
    0.81
    imony
    0.79
    ful
    0.79
    Act Density 0.039%

    No Known Activations