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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "who" indicating references to people or characters in the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concluding
    -0.66
     VIDEOS
    -0.65
     Anything
    -0.64
     beginning
    -0.60
     chronological
    -0.59
     beginnings
    -0.57
     marathon
    -0.56
     stressing
    -0.56
     Ending
    -0.56
     Beginning
    -0.55
    POSITIVE LOGITS
    upon
    1.13
     specializes
    1.08
     resides
    1.02
     resembled
    0.99
     resembles
    0.99
     resided
    0.97
     owns
    0.96
     possesses
    0.94
     knows
    0.92
     incidentally
    0.92
    Act Density 0.179%

    No Known Activations