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

    Neuronpedia

    INDEX
    Explanations

    words related to movement and flexibility

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to movement and flexibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Thur
    -0.59
     Attempt
    -0.57
     Dating
    -0.56
     Wrong
    -0.55
     Singer
    -0.54
     Destruction
    -0.54
    OSED
    -0.53
     parentheses
    -0.53
    laughter
    -0.53
     VICE
    -0.52
    POSITIVE LOGITS
     efficiently
    1.28
     quicker
    1.25
     safely
    1.20
     freely
    1.17
     easier
    1.09
     confidently
    1.08
     smoother
    1.07
     faster
    1.07
     seamlessly
    1.07
     comfortably
    1.05
    Act Density 0.662%

    No Known Activations