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

    Neuronpedia

    INDEX
    Explanations

    pronouns referring to individuals in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.99
     estekak
    -0.85
     pleaſure
    -0.71
     NSCoder
    -0.69
    Personendaten
    -0.68
    دانشنامهٔ
    -0.67
     fevere
    -0.63
     greateſt
    -0.62
     itſelf
    -0.62
     térm
    -0.62
    POSITIVE LOGITS
     he
    0.98
     she
    0.92
     She
    0.86
     He
    0.82
     THEY
    0.82
     они
    0.80
     they
    0.80
     I
    0.77
     वह
    0.74
     он
    0.74
    Act Density 0.137%

    No Known Activations