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

    Neuronpedia

    INDEX
    Explanations

    proper nouns from various fields like names of people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    names and terms associated with prominent figures, particularly in politics and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Load
    -0.72
     subscript
    -0.69
     Seym
    -0.67
     Vec
    -0.63
     Ukrain
    -0.63
     Wem
    -0.61
     discrep
    -0.61
     pecul
    -0.61
     pestic
    -0.58
     specificity
    -0.58
    POSITIVE LOGITS
     Jr
    1.53
     Sr
    1.13
     famously
    0.95
     III
    0.92
    enegger
    0.86
    Jr
    0.84
    erson
    0.77
    ervatives
    0.74
     aka
    0.73
    's
    0.70
    Act Density 0.228%

    No Known Activations