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

    Neuronpedia

    INDEX
    Explanations

    references to self and personal identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hunne
    -0.59
    Scénario
    -0.59
     HttpNotFound
    -0.56
     '/':
    -0.55
    tdc
    -0.55
    ENOS
    -0.54
     Racine
    -0.54
     hyperlink
    -0.54
    AppCompatTheme
    -0.54
    rdoba
    -0.53
    POSITIVE LOGITS
    itself
    1.39
     itself
    1.36
     Itself
    1.30
     himself
    0.94
     Himself
    0.94
     herself
    0.94
    themselves
    0.94
     Roskov
    0.93
     sendiri
    0.92
    herself
    0.89
    Act Density 0.125%

    No Known Activations