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

    Neuronpedia

    INDEX
    Explanations

    references to governmental institutions or processes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of government entities and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IU
    -0.72
    FACE
    -0.72
    terday
    -0.70
    uous
    -0.66
    uously
    -0.65
    Ô
    -0.63
    TI
    -0.62
    âĺħâĺħ
    -0.61
    vol
    -0.61
    è¦ļéĨĴ
    -0.61
    POSITIVE LOGITS
     Accountability
    1.37
     Shutdown
    0.94
     Communications
    0.87
     Relations
    0.84
    vernment
    0.80
     Bureau
    0.77
     Reserve
    0.76
     Accounting
    0.75
     Association
    0.75
     Buildings
    0.74
    Act Density 0.019%

    No Known Activations