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

    Neuronpedia

    INDEX
    Explanations

    words related to prosthetics and medical devices designed to replace or support a missing or impaired body part

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prosthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Dick
    -0.78
    INESS
    -0.71
    hound
    -0.71
     Finder
    -0.71
     Bard
    -0.68
     Sorcerer
    -0.64
     Darwin
    -0.64
    hower
    -0.64
    hua
    -0.63
     Bourbon
    -0.63
    POSITIVE LOGITS
     prost
    1.36
    hetics
    1.23
    hesis
    1.07
    hetic
    1.07
    heses
    1.06
    orius
    0.92
    roleum
    0.90
     amput
    0.88
     ende
    0.84
    acet
    0.83
    Act Density 0.008%

    No Known Activations