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

    Neuronpedia

    INDEX
    Explanations

    expressions of stress or mental strain related to relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ผม
    -0.86
    łbym
    -0.82
    ครับ
    -0.75
    łem
    -0.74
    FTFY
    -0.70
     sám
    -0.68
    僕
    -0.68
    僕は
    -0.67
    僕も
    -0.67
     للمعارف
    -0.67
    POSITIVE LOGITS
     loveliness
    0.69
    Obrigada
    0.69
    łam
    0.67
    🏻‍♀️
    0.67
    とっても
    0.61
     hubby
    0.59
    ‍♀️
    0.58
     sparkly
    0.58
    fabulous
    0.57
    けれど
    0.57
    Act Density 0.992%

    No Known Activations