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

    Neuronpedia

    INDEX
    Explanations

    references to community gatherings and shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barbara
    -0.22
    Jean
    -0.20
     Joan
    -0.20
     Patricia
    -0.20
     Sandra
    -0.18
     Judith
    -0.18
     Ronald
    -0.18
     Nancy
    -0.18
     Susan
    -0.17
     Gerald
    -0.17
    POSITIVE LOGITS
     Ryder
    0.27
     Mason
    0.26
     Logan
    0.25
     Connor
    0.25
     Skyl
    0.25
     Bray
    0.25
     Ember
    0.25
     Chase
    0.25
     Dakota
    0.24
     Riley
    0.24
    Act Density 1.099%

    No Known Activations