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

    Neuronpedia

    INDEX
    Explanations

    phrases related to self-reference and existential concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.95
    NameInMap
    -0.90
     Majefty
    -0.84
     Yud
    -0.84
    richTextPanel
    -0.83
    voorbeeld
    -0.75
    Geplaatst
    -0.74
     actualité
    -0.74
     Prist
    -0.72
     виправивши
    -0.69
    POSITIVE LOGITS
     se
    1.02
     להת
    0.93
     haberse
    0.90
     sich
    0.83
     Se
    0.82
     Mc
    0.75
    '},
    0.74
     се
    0.74
    się
    0.73
    '),
    0.72
    Act Density 0.032%

    No Known Activations