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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical movement, particularly walking and exercise

    oai_token-act-pair · gpt-3.5-turbo

    actions related to movement and physical activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     suspic
    -0.66
     Templ
    -0.66
     Aren
    -0.65
     Aven
    -0.63
    aples
    -0.62
     Monstrous
    -0.61
     concess
    -0.60
     lawy
    -0.60
     Principal
    -0.59
     cinem
    -0.58
    POSITIVE LOGITS
    ings
    1.88
    able
    1.55
    ability
    1.54
    ers
    1.53
    ables
    1.45
    outs
    1.38
    aways
    1.36
    downs
    1.31
    away
    1.29
    out
    1.29
    Act Density 0.343%

    No Known Activations