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

    Neuronpedia

    INDEX
    Explanations

    instances of self-reference and personal achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yourselves
    -0.23
     Ñģами
    -0.22
     themselves
    -0.21
     itself
    -0.18
    ÑĪла
    -0.18
     HIS
    -0.17
     collectively
    -0.17
     могла
    -0.17
     collective
    -0.17
     His
    -0.16
    POSITIVE LOGITS
     himself
    0.52
     Himself
    0.32
     должен
    0.22
    aped
    0.20
     deren
    0.19
     persona
    0.19
     бÑĭл
    0.19
     sám
    0.19
     personally
    0.19
     ÙĨÙģسÙĩ
    0.18
    Act Density 0.075%

    No Known Activations