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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of being "free" or "unrestricted" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.63
    ↩
    -0.61
    __);
    -0.58
    amentlich
    -0.57
    GZIP
    -0.56
     donkeys
    -0.56
     Cæsar
    -0.56
     محفوظة
    -0.55
     tecnici
    -0.55
    NullCheck
    -0.55
    POSITIVE LOGITS
     free
    1.07
     libre
    1.07
     bebas
    0.99
     freely
    0.96
     libres
    0.93
     freedom
    0.93
     Free
    0.92
     freien
    0.91
    Free
    0.89
    free
    0.88
    Act Density 0.542%

    No Known Activations