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

    Neuronpedia

    INDEX
    Explanations

    expressions related to freedom and creative control in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wap
    -0.16
     Germ
    -0.16
     åĽ
    -0.16
    ameda
    -0.14
    riger
    -0.14
    roti
    -0.14
    มà¸Ļ
    -0.13
    ï¸
    -0.13
    _marshall
    -0.13
    _LOGGER
    -0.13
    POSITIVE LOGITS
     freedom
    0.48
    fre
    0.39
    èĩªçĶ±
    0.37
     freedoms
    0.36
     Freedom
    0.36
    Freedom
    0.35
     freely
    0.34
     liberty
    0.34
     Ñģвоб
    0.34
     free
    0.32
    Act Density 0.271%

    No Known Activations