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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and specific geographic locations within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bens
    -0.16
     Portland
    -0.16
    Portland
    -0.16
    ijkstra
    -0.15
    åģ
    -0.15
    SG
    -0.15
    anos
    -0.15
    ازÛĮ
    -0.14
    /entities
    -0.14
    ocus
    -0.14
    POSITIVE LOGITS
     Texas
    0.25
     texas
    0.24
     Texans
    0.21
    Texas
    0.21
     TX
    0.19
     TEX
    0.19
     Dallas
    0.17
    Dallas
    0.17
    _tx
    0.17
    .Tx
    0.16
    Act Density 0.456%

    No Known Activations