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

    Neuronpedia

    INDEX
    Explanations

    references to male characters or pronouns in a narrative

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

    masculine singular possessive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?
    -0.53
    новништво
    -0.49
     שוליים
    -0.48
    
    -0.44
    setVerticalGroup
    -0.43
     lateinit
    -0.40
    jsdelivr
    -0.40
    HtmlAttribute
    -0.38
     vrijwilli
    -0.38
     icon
    -0.37
    POSITIVE LOGITS
     himself
    0.96
    himself
    0.91
     Himself
    0.68
    彼は
    0.67
    彼の
    0.66
    彼が
    0.65
     his
    0.64
     그의
    0.61
    his
    0.60
    حياته
    0.59
    Act Density 0.366%

    No Known Activations