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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brotherhood
    -0.85
    łbym
    -0.80
     menswear
    -0.75
     masculinity
    -0.75
     manhood
    -0.75
     Grandpa
    -0.75
     Grandfather
    -0.74
    Mr
    -0.74
     grandpa
    -0.74
     fathers
    -0.74
    POSITIVE LOGITS
     woman
    1.56
     women
    1.54
     girl
    1.44
     female
    1.37
     Women
    1.37
     lady
    1.35
    woman
    1.35
    women
    1.32
     girls
    1.32
     Woman
    1.31
    Act Density 1.217%

    No Known Activations