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

    Neuronpedia

    INDEX
    Explanations

    geographical names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hwy
    -0.20
     Philly
    -0.19
     Indy
    -0.19
     Intl
    -0.18
     Pa
    -0.18
     NYC
    -0.18
     SF
    -0.17
     NZ
    -0.17
     Dems
    -0.17
     ppl
    -0.17
    POSITIVE LOGITS
     Illinois
    0.39
     Pennsylvania
    0.38
     California
    0.38
     Wisconsin
    0.38
     Nebraska
    0.38
     Minnesota
    0.37
     Louisiana
    0.37
     Missouri
    0.37
     Kentucky
    0.36
     Texas
    0.36
    Act Density 0.051%

    No Known Activations