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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical locations, especially cities and regions

    oai_token-act-pair · gpt-3.5-turbo

    prominent political figures and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xon
    -0.76
    Weiss
    -0.67
    Gene
    -0.67
    ARDIS
    -0.66
     Turtles
    -0.65
    Newsletter
    -0.65
     Becky
    -0.65
     Perkins
    -0.64
     Bonnie
    -0.64
    Lex
    -0.62
    POSITIVE LOGITS
    umbai
    1.25
    jriwal
    1.16
     Sharma
    1.10
     Pradesh
    1.07
     Nadu
    1.04
    ibaba
    0.97
     Bh
    0.96
     crore
    0.94
     Kumar
    0.94
     Modi
    0.93
    Act Density 0.489%

    No Known Activations