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

    Neuronpedia

    INDEX
    Explanations

    phrases related to action and movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    strument
    -0.15
     crossorigin
    -0.15
    698
    -0.14
    æŃ©
    -0.14
     argc
    -0.14
     коÑĢоб
    -0.13
    juven
    -0.13
     strugg
    -0.13
    èħIJ
    -0.13
    .patch
    -0.13
    POSITIVE LOGITS
     ac
    0.31
     stunt
    0.30
     dare
    0.27
     jumps
    0.25
     flips
    0.25
     tricks
    0.25
     aerial
    0.24
     Evel
    0.24
     extreme
    0.24
     cliff
    0.23
    Act Density 0.069%

    No Known Activations