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

    Neuronpedia

    INDEX
    Explanations

    references to legal issues or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Delaware
    -0.21
     ----------------------------------------------------------------------↵
    -0.18
     Deniz
    -0.17
     teg
    -0.15
    NTAX
    -0.15
     Sund
    -0.14
    otts
    -0.14
    adin
    -0.14
    äd
    -0.14
    upo
    -0.14
    POSITIVE LOGITS
     Maharashtra
    0.38
     Pune
    0.33
     Nash
    0.27
     Mumbai
    0.25
     Detroit
    0.22
    Detroit
    0.21
     Kore
    0.21
     Lon
    0.21
     Shir
    0.21
     Paw
    0.20
    Act Density 0.050%

    No Known Activations