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

    Neuronpedia

    INDEX
    Explanations

    mentions of things considered slender or thin

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being slim or thin

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     citation
    -0.78
    DCS
    -0.74
    rique
    -0.65
     Occupations
    -0.64
    Mobil
    -0.63
     Hosp
    -0.63
    NAT
    -0.62
     Watching
    -0.61
     Ù
    -0.61
     Abuse
    -0.60
    POSITIVE LOGITS
    ming
    1.18
    med
    1.08
    tty
    0.85
    y
    0.81
    ples
    0.79
     waist
    0.79
    ethy
    0.78
    ily
    0.77
    ideshow
    0.76
    suit
    0.75
    Act Density 0.012%

    No Known Activations