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

    Neuronpedia

    INDEX
    Explanations

    references to power dynamics and social hierarchy

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

    references to legal provisions or statutes

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

    his seat, shoes, or place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.82
    tagHelperRunner
    -0.78
     nahilalakip
    -0.77
    webElementGuid
    -0.70
     kasarigan
    -0.68
     defaultstate
    -0.66
     Púb
    -0.64
    bootstrapcdn
    -0.63
     مشين
    -0.63
    ArrowToggle
    -0.62
    POSITIVE LOGITS
     place
    1.25
    place
    1.13
     replace
    1.04
     replaces
    1.01
     místo
    1.01
     instead
    1.01
     вместо
    0.98
     stead
    0.98
    代わりに
    0.98
     lugar
    0.95
    Act Density 0.089%

    No Known Activations