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

    Neuronpedia

    INDEX
    Explanations

    actions involving physical movement and positioning of characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pole
    -0.17
    #
    -0.16
    otte
    -0.15
     ÙĨسب
    -0.15
    iscard
    -0.15
    zzarella
    -0.14
    âķĹ
    -0.14
    odel
    -0.14
    CONTEXT
    -0.14
     majet
    -0.14
    POSITIVE LOGITS
     knees
    0.44
     bent
    0.41
     knee
    0.38
     bend
    0.37
     bending
    0.34
     genu
    0.34
     kne
    0.32
     kneeling
    0.30
     Bend
    0.30
     bends
    0.30
    Act Density 0.104%

    No Known Activations