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

    Neuronpedia

    INDEX
    Explanations

    video-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "play" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fty
    -0.87
    isse
    -0.64
    urus
    -0.64
    irl
    -0.62
     Beir
    -0.60
    ########
    -0.60
    reach
    -0.59
    kos
    -0.59
    arger
    -0.59
    pora
    -0.59
    POSITIVE LOGITS
    ername
    1.02
    lists
    1.01
    wright
    0.92
     clips
    0.82
     aloud
    0.80
     recordings
    0.80
     havoc
    0.80
     Piano
    0.76
     catch
    0.76
     slideshow
    0.76
    Act Density 0.053%

    No Known Activations