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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-reference and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.69
    __*/
    -0.64
     hunne
    -0.63
     sauvages
    -0.62
    AppCompatTheme
    -0.61
     Crusaders
    -0.60
    contentLoaded
    -0.60
     HttpNotFound
    -0.59
    ButterKnife
    -0.59
    openConnection
    -0.59
    POSITIVE LOGITS
     itself
    1.25
     Itself
    1.11
    itself
    1.09
    本身
    0.87
     himself
    0.85
     самого
    0.79
     sendiri
    0.79
     themselves
    0.78
     herself
    0.78
     Himself
    0.77
    Act Density 0.091%

    No Known Activations