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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical or mental disabilities

    oai_token-act-pair · gpt-3.5-turbo

    references to disabilities and handicaps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liness
    -0.87
    ership
    -0.87
    achusetts
    -0.69
    lling
    -0.68
     Scully
    -0.67
    IRD
    -0.67
    rence
    -0.67
    ling
    -0.66
    AK
    -0.66
    berman
    -0.65
    POSITIVE LOGITS
    ities
    0.90
    astics
    0.88
    umbered
    0.81
    phant
    0.81
    aments
    0.78
    agi
    0.75
    cycles
    0.71
     traged
    0.69
    ounter
    0.69
    asia
    0.68
    Act Density 0.066%

    No Known Activations