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

    Neuronpedia

    INDEX
    Explanations

    words related to identity and cultural background

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

    following a form of "to be"

    np_acts-logits-general · gemini-2.0-flash

    is being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    beforeEach
    -0.64
    BagLayout
    -0.64
    kloped
    -0.63
     którzy
    -0.62
    WRENCE
    -0.61
    argout
    -0.58
    addContainerGap
    -0.57
    standers
    -0.56
     חיצוניים
    -0.56
    TintMode
    -0.56
    POSITIVE LOGITS
     obsessed
    0.69
     wearing
    0.68
     married
    0.67
     trying
    0.67
     suing
    0.63
     doing
    0.63
     aware
    0.62
     famous
    0.60
     interested
    0.59
     part
    0.58
    Act Density 0.474%

    No Known Activations