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

    Neuronpedia

    INDEX
    Explanations

    references to political power dynamics and factional relationships

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

    wanted, wished, urged

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.47
     Wiktionnaire
    -0.47
     виправивши
    -0.41
     newOwner
    -0.40
    InSection
    -0.38
    Hentet
    -0.38
    verwijspagina
    -0.38
    }*/
    -0.38
    ⓘ
    -0.36
    MessageWindow
    -0.36
    POSITIVE LOGITS
    PositiveButton
    0.49
    useNewUrlParser
    0.44
    AndEndTag
    0.42
    唱
    0.40
     arguing
    0.39
    disclosure
    0.38
     restraint
    0.38
    iture
    0.38
    ///</
    0.38
    NegativeButton
    0.37
    Act Density 0.094%

    No Known Activations