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

    Neuronpedia

    INDEX
    Explanations

    references to body parts, particularly the legs

    oai_token-act-pair · gpt-3.5-turbo

    references to legs, both in literal and metaphorical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tics
    -0.64
    ettings
    -0.64
    999
    -0.59
    tical
    -0.59
    berman
    -0.59
     Premium
    -0.56
     groundwater
    -0.56
    anyahu
    -0.55
    rises
    -0.55
     AAP
    -0.55
    POSITIVE LOGITS
     leg
    1.03
    acies
    0.99
    iev
    0.93
    itimate
    0.90
    isl
    0.87
     Leg
    0.85
    ible
    0.83
    ivers
    0.82
    atum
    0.81
    puter
    0.81
    Act Density 0.007%

    No Known Activations