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

    Neuronpedia

    INDEX
    Explanations

    phrases related to government entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the government

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.83
    IU
    -0.78
    uously
    -0.74
    FACE
    -0.73
    uous
    -0.71
    jad
    -0.68
    Els
    -0.67
    astern
    -0.63
    vol
    -0.63
    Ô
    -0.63
    POSITIVE LOGITS
     Accountability
    1.47
     Communications
    0.90
     Relations
    0.86
     Shutdown
    0.85
     Accounting
    0.78
    vernment
    0.78
     Bureau
    0.78
     Reserve
    0.77
     Association
    0.77
     Publishing
    0.76
    Act Density 0.030%

    No Known Activations