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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agra
    -0.89
    apple
    -0.83
    keye
    -0.77
    nect
    -0.75
    dress
    -0.75
    20439
    -0.74
    upuncture
    -0.74
    river
    -0.73
    lear
    -0.72
    bell
    -0.71
    POSITIVE LOGITS
     Markus
    1.22
     von
    1.13
     Von
    1.04
     Anders
    1.02
     Olivier
    1.00
     Werner
    1.00
     Pascal
    1.00
     Andersen
    0.96
     Stefan
    0.96
     Meier
    0.95
    Act Density 0.061%

    No Known Activations