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

    Neuronpedia

    INDEX
    Explanations

    mentions of governmental entities

    oai_token-act-pair · gpt-3.5-turbo

    references to government entities or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IU
    -0.73
    jad
    -0.69
    terday
    -0.69
    vill
    -0.66
    card
    -0.66
    uously
    -0.65
    FACE
    -0.65
    cro
    -0.64
    uous
    -0.62
    aterasu
    -0.61
    POSITIVE LOGITS
     Accountability
    1.36
     Communications
    0.90
     Shutdown
    0.89
    vernment
    0.88
     Relations
    0.86
     Accounting
    0.78
     Employees
    0.74
     Panel
    0.73
     Publishing
    0.71
     Association
    0.70
    Act Density 0.031%

    No Known Activations