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

    Neuronpedia

    INDEX
    Explanations

    words related to government programs and processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    igmatic
    -0.70
    poral
    -0.67
    perfect
    -0.67
     haunting
    -0.66
    mia
    -0.65
    eny
    -0.65
    sie
    -0.64
    iPhone
    -0.64
    inct
    -0.64
    ãĥĺãĥ©
    -0.63
    POSITIVE LOGITS
     academia
    1.21
     policymakers
    1.13
     regulators
    1.11
     bureaucrats
    1.11
     NGOs
    1.07
     judiciary
    1.06
     broadcasters
    1.06
     businessmen
    1.04
     stakeholders
    1.02
     universities
    1.01
    Act Density 1.730%

    No Known Activations