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

    Neuronpedia

    INDEX
    Explanations

    personal names, likely politicians or public figures

    oai_token-act-pair · gpt-3.5-turbo

    names or initials of individuals and specific entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sounders
    -0.77
     Hydra
    -0.77
    Cub
    -0.75
    Weiss
    -0.74
     Cuban
    -0.73
     Rebels
    -0.72
     Hearts
    -0.72
     Myr
    -0.71
     Oilers
    -0.68
     Blake
    -0.68
    POSITIVE LOGITS
    umbai
    1.27
    jriwal
    1.25
    ashtra
    1.20
     Shiv
    1.18
    indu
    1.17
     Sharma
    1.14
     Bhar
    1.13
     Kumar
    1.13
    India
    1.13
     Singh
    1.12
    Act Density 0.111%

    No Known Activations