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

    Neuronpedia

    INDEX
    Explanations

    references to gender and childhood characteristics in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    兒子
    -0.49
    息子
    -0.49
     son
    -0.47
    StoryboardSegue
    -0.44
     Mrs
    -0.44
    MRS
    -0.44
    Mrs
    -0.44
     сын
    -0.43
    儿子
    -0.42
     MRS
    -0.42
    POSITIVE LOGITS
     girls
    2.47
     girl
    2.45
     Girls
    2.09
     Girl
    2.06
    girls
    2.05
    girl
    2.03
    Girls
    1.98
    Girl
    1.93
     GIRLS
    1.91
     GIRL
    1.90
    Act Density 0.385%

    No Known Activations