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

    Neuronpedia

    INDEX
    Explanations

    references to body parts, specifically legs

    oai_token-act-pair · gpt-3.5-turbo

    references to 'legs' and possibly related body parts or limbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ohn
    -0.69
    sequence
    -0.65
    scape
    -0.63
    1000
    -0.60
     Coun
    -0.60
    OA
    -0.60
    NG
    -0.60
    ount
    -0.59
    Ni
    -0.58
    Ware
    -0.58
    POSITIVE LOGITS
     legs
    3.85
     Legs
    2.48
     limbs
    2.15
     thighs
    2.10
     leg
    1.88
     knees
    1.88
     ankles
    1.84
     feet
    1.76
     hips
    1.65
     arms
    1.57
    Act Density 0.014%

    No Known Activations