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

    Neuronpedia

    INDEX
    Explanations

    concepts related to freedom and autonomy in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eba
    -0.15
    \Mapping
    -0.14
    à¥Īà¤ł
    -0.14
    inecraft
    -0.14
    umlu
    -0.13
     insider
    -0.13
     Tradable
    -0.13
    ä¸į足
    -0.13
     Insider
    -0.13
    alent
    -0.12
    POSITIVE LOGITS
     freedom
    0.97
     Freedom
    0.77
     liberty
    0.77
     freedoms
    0.77
    Freedom
    0.74
    èĩªçĶ±
    0.66
    fre
    0.65
     Ñģвоб
    0.65
     independence
    0.60
     libert
    0.59
    Act Density 0.306%

    No Known Activations