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

    Neuronpedia

    INDEX
    Explanations

    pronouns and indicators of local context or geography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scarborough
    -0.17
    dlg
    -0.15
    iff
    -0.14
    ког
    -0.14
    untu
    -0.14
     Isl
    -0.14
    سط
    -0.14
     Burl
    -0.14
    .EventQueue
    -0.14
    itez
    -0.14
    POSITIVE LOGITS
     Sic
    0.27
     Interior
    0.21
     Revel
    0.20
    Interior
    0.20
     Princeton
    0.20
     Nicola
    0.20
     Electoral
    0.19
     BX
    0.18
     Nak
    0.18
     interior
    0.18
    Act Density 0.018%

    No Known Activations