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

    Neuronpedia

    INDEX
    Explanations

    mentions of prosthetics or related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prosthetics and artificial limbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INESS
    -0.84
    Dick
    -0.71
    hound
    -0.67
     Finder
    -0.66
    ÃĽ
    -0.66
     Sorcerer
    -0.64
     Grind
    -0.63
     Bard
    -0.62
    hower
    -0.62
     Daly
    -0.61
    POSITIVE LOGITS
    hetics
    1.19
    hetic
    1.09
     prost
    1.08
    orius
    1.06
    heses
    1.05
    hesis
    1.02
    acet
    0.90
    lete
    0.87
    reon
    0.86
    ificial
    0.86
    Act Density 0.016%

    No Known Activations