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

    Neuronpedia

    INDEX
    Explanations

    references to locations or entities related to Washington, D.C

    oai_token-act-pair · gpt-3.5-turbo

    references to Washington, D.C

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.89
    emi
    -0.78
    eli
    -0.74
    irlf
    -0.73
    ãĥĥ
    -0.71
    INAL
    -0.71
    lass
    -0.71
    rious
    -0.71
    ãĥ³
    -0.67
    milo
    -0.67
    POSITIVE LOGITS
     DC
    1.63
     D
    1.34
    DC
    1.12
     Wizards
    0.98
     Washington
    0.87
     Dull
    0.86
     Jefferson
    0.85
    D
    0.84
     District
    0.83
     dc
    0.80
    Act Density 0.052%

    No Known Activations