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

    Neuronpedia

    INDEX
    Explanations

    references to female-related topics and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     in
    -0.60
     (
    -0.57
     I
    -0.56
    ,
    -0.56
      
    -0.56
     as
    -0.55
     or
    -0.54
     
    -0.54
     and
    -0.52
     is
    -0.51
    POSITIVE LOGITS
    NameInMap
    1.09
     Paglinawan
    1.07
     Houſe
    1.00
     Majefty
    0.97
     Efq
    0.95
     houſe
    0.94
     Jefus
    0.92
    LookAnd
    0.91
     Anſ
    0.90
    Tembelea
    0.90
    Act Density 0.187%

    No Known Activations