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

    Neuronpedia

    INDEX
    Explanations

    references to authority and resistance in social and political contexts

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

    references to positions of power and controversial social issues

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

    consequences of which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.70
    GTCX
    -0.67
    protoimpl
    -0.65
    WriteAttribute
    -0.64
    IntentFilter
    -0.60
     الاطلاع
    -0.59
     kasarigan
    -0.58
    UIControlState
    -0.58
    Eloquent
    -0.57
     مرئيه
    -0.57
    POSITIVE LOGITS
     resulting
    1.71
     causing
    1.63
    resulting
    1.58
     resulted
    1.51
    causing
    1.43
     causes
    1.37
     leading
    1.36
     prompting
    1.35
    导致
    1.28
    causes
    1.27
    Act Density 0.432%

    No Known Activations