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

    Neuronpedia

    INDEX
    Explanations

    mentions of the state code "WA" followed by a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    references to Washington (WA) in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erous
    -0.75
    displayText
    -0.73
    onial
    -0.68
    matter
    -0.67
    sson
    -0.66
    sis
    -0.65
    rious
    -0.62
    ãĤ¨ãĥ«
    -0.62
     accur
    -0.61
    ãģĻ
    -0.61
    POSITIVE LOGITS
    VE
    1.17
    velength
    1.11
    ILA
    1.02
    WA
    0.98
    atche
    0.93
    apon
    0.93
    ITH
    0.91
    UGH
    0.90
    IVERS
    0.87
    HAHA
    0.84
    Act Density 0.010%

    No Known Activations