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

    Neuronpedia

    INDEX
    Explanations

    items of clothing, specifically socks and underwear

    oai_token-act-pair · gpt-3.5-turbo

    references to socks and underwear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     miscar
    -0.71
     Alzheimer
    -0.66
     Huntington
    -0.63
     Virgin
    -0.63
    AUT
    -0.62
    ENE
    -0.62
    represented
    -0.62
     CNS
    -0.61
    views
    -0.61
     sob
    -0.60
    POSITIVE LOGITS
     socks
    1.51
     sock
    1.16
     yarn
    0.97
     underwear
    0.96
     Shoes
    0.90
    leeve
    0.88
     Shirt
    0.86
     nodd
    0.86
    ipation
    0.82
    worms
    0.81
    Act Density 0.005%

    No Known Activations