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

    Neuronpedia

    INDEX
    Explanations

    references to ownership or possession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yourselves
    -0.68
     conmigo
    -0.67
     comigo
    -0.61
     المعيارى
    -0.58
     Himself
    -0.57
     själva
    -0.56
     himself
    -0.54
    correctly
    -0.54
     irse
    -0.54
     herself
    -0.53
    POSITIVE LOGITS
    sterious
    0.84
    riad
    0.83
     apologies
    0.79
    anmar
    0.78
    thic
    0.73
    rrh
    0.72
    opic
    0.71
     own
    0.71
     favorite
    0.69
    konos
    0.69
    Act Density 0.142%

    No Known Activations