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

    Neuronpedia

    INDEX
    Explanations

    proper names or significant legal entities involved in cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.92
     Himself
    -0.77
     الدولى
    -0.73
     који
    -0.72
     koji
    -0.71
    himself
    -0.71
     Jr
    -0.68
     بيها
    -0.59
    تقاوى
    -0.57
     financières
    -0.56
    POSITIVE LOGITS
     herself
    1.25
    herself
    0.83
     ihrem
    0.72
     bint
    0.69
     koja
    0.68
    protoimpl
    0.66
     ihren
    0.65
     her
    0.63
     која
    0.61
     she
    0.60
    Act Density 0.556%

    No Known Activations