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

    Neuronpedia

    INDEX
    Explanations

    names of locations, especially Washington, D.C

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ftu
    -1.05
     reft
    -0.99
     thut
    -0.97
     fto
    -0.96
     fep
    -0.95
     fte
    -0.95
     perfon
    -0.95
     nece
    -0.94
     leaft
    -0.93
     peppa
    -0.92
    POSITIVE LOGITS
     DC
    1.27
    DC
    1.13
     Washington
    1.06
    Washington
    0.99
     dc
    0.97
    dc
    0.96
    WASHINGTON
    0.87
     DCs
    0.84
    DCs
    0.80
     WASHINGTON
    0.78
    Act Density 0.096%

    No Known Activations