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

    Neuronpedia

    INDEX
    Explanations

    geographic references and specific locations mentioned in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Detroit
    -0.18
     Michigan
    -0.17
     Cincinnati
    -0.17
    Michigan
    -0.16
    èĬĿ
    -0.16
     Clyde
    -0.16
     Ohio
    -0.15
    Ohio
    -0.15
    -mf
    -0.15
     NJ
    -0.15
    POSITIVE LOGITS
     Norwich
    0.38
     Suffolk
    0.36
     Norfolk
    0.32
     Ips
    0.27
     pun
    0.20
     Bulgarian
    0.19
     Bulgaria
    0.19
     Orlando
    0.19
     Cambridge
    0.17
     Lowest
    0.17
    Act Density 0.128%

    No Known Activations