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

    Neuronpedia

    INDEX
    Explanations

    references to physical activities and training techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overnight
    -0.19
     Overnight
    -0.14
     dates
    -0.14
    overn
    -0.14
    maze
    -0.13
     community
    -0.13
     consumer
    -0.13
     inconvenient
    -0.13
     expans
    -0.12
    æ¶Īæģ¯
    -0.12
    POSITIVE LOGITS
     technique
    0.21
     Technique
    0.20
     movement
    0.19
     movements
    0.17
     Movement
    0.16
     execute
    0.16
     executes
    0.16
     дви
    0.16
     timing
    0.15
     microseconds
    0.15
    Act Density 0.622%

    No Known Activations