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

    Neuronpedia

    INDEX
    Explanations

    references to muscles and physical movement

    oai_token-act-pair · gpt-3.5-turbo

    references to muscles and anatomical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Recommend
    -0.71
    Code
    -0.70
    alog
    -0.67
    Operation
    -0.64
    Witness
    -0.64
    OWN
    -0.64
    minist
    -0.64
    Mur
    -0.64
     exception
    -0.63
    event
    -0.62
    POSITIVE LOGITS
    mith
    1.42
    hops
    1.29
    ynthesis
    1.24
    paces
    1.16
    pring
    1.14
    poons
    1.12
    pace
    1.11
    ourcing
    1.10
    hips
    1.06
    hirt
    1.03
    Act Density 0.065%

    No Known Activations