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

    Neuronpedia

    INDEX
    Explanations

    elements related to personal relationships and interpersonal dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     själva
    -0.72
     оно
    -0.67
     zostało
    -0.65
     Оно
    -0.60
     juntas
    -0.57
     которое
    -0.56
     powinno
    -0.54
     kteří
    -0.52
     jej
    -0.51
    GEBURTSDATUM
    -0.50
    POSITIVE LOGITS
     himself
    2.86
     his
    2.36
    himself
    2.34
    his
    1.92
     himſelf
    1.91
    彼の
    1.63
    彼は
    1.52
     Himself
    1.51
    他的
    1.48
     그의
    1.48
    Act Density 2.765%

    No Known Activations