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

    Neuronpedia

    INDEX
    Explanations

    the word "Free" followed by a variety of different terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Free."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acea
    -0.68
    IOR
    -0.63
     bore
    -0.62
    stroke
    -0.62
    essa
    -0.61
     aggrav
    -0.60
    isks
    -0.60
    TIT
    -0.59
     leth
    -0.58
    ihu
    -0.57
    POSITIVE LOGITS
     Free
    3.89
    Free
    2.84
     free
    2.29
    free
    2.25
     FREE
    2.15
    FREE
    1.91
     Freedom
    1.26
     Freed
    1.12
    Freedom
    1.11
     Freeze
    1.11
    Act Density 0.015%

    No Known Activations