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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rules, regulations, and their implications in various contexts

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

    answering questions or providing information

    np_acts-logits-general · gemini-2.0-flash

    asking questions to authorities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.58
     BoxFit
    -0.53
     Theſe
    -0.53
     ―――――
    -0.52
    parsedMessage
    -0.50
     myſelf
    -0.49
     ――――
    -0.49
    atorze
    -0.49
    Patient
    -0.48
    참고
    -0.48
    POSITIVE LOGITS
     officials
    1.30
     organizers
    1.23
     organisers
    1.18
     authorities
    1.17
     experts
    1.17
     investigators
    1.17
     researchers
    1.11
     administrators
    1.10
     scientists
    1.08
     Officials
    1.07
    Act Density 1.279%

    No Known Activations