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

    Neuronpedia

    INDEX
    Explanations

    terms related to government protection and safety measures.

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    statements related to legal matters and government actions.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to protecting or safeguarding something, particularly people, rights, or institutions.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Protecting something or someone

    np_acts-logits-general · gemini-2.0-flash

    protecting the valuable or vulnerable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.87
    RegressionTest
    -0.83
    出版年
    -0.82
     cherchés
    -0.74
     kasarigan
    -0.71
     ComVisible
    -0.70
     Савезне
    -0.68
    省市镇
    -0.64
    roek
    -0.63
     manqué
    -0.63
    POSITIVE LOGITS
     against
    1.12
    against
    1.00
     Against
    0.98
     integrity
    0.95
    Against
    0.88
     precious
    0.87
     valuable
    0.83
     delicate
    0.78
     dignity
    0.78
     rights
    0.78
    Act Density 0.223%

    No Known Activations