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

    Neuronpedia

    INDEX
    Explanations

    mentions of the location "Washington" in a document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Washington"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leness
    -0.74
    oute
    -0.73
    Occ
    -0.72
    Rating
    -0.72
    âĹ¼
    -0.71
    Companies
    -0.70
    vana
    -0.70
    otal
    -0.67
    cffffcc
    -0.67
    ulously
    -0.66
    POSITIVE LOGITS
     DC
    1.09
     Capitals
    1.08
     Bridge
    1.01
     Dull
    0.98
     Monument
    0.96
     Post
    0.95
     Redskins
    0.93
     Heights
    0.92
    sonian
    0.92
     Wizards
    0.89
    Act Density 0.028%

    No Known Activations