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

    Neuronpedia

    INDEX
    Explanations

    businesses, organizations, or individuals by name

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ukrain
    -0.70
     discrep
    -0.69
     exha
    -0.68
     Seym
    -0.68
     horm
    -0.67
     Citiz
    -0.66
     Nanto
    -0.66
     challeng
    -0.65
     citiz
    -0.65
     differe
    -0.65
    POSITIVE LOGITS
     Jr
    1.46
     Sr
    1.05
     III
    0.83
     famously
    0.81
     aka
    0.76
     Award
    0.74
    enegger
    0.70
     Foundation
    0.69
    's
    0.69
    erson
    0.69
    Act Density 0.223%

    No Known Activations