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

    Neuronpedia

    INDEX
    Explanations

    qualities related to smoothness

    oai_token-act-pair · gpt-3.5-turbo

    references to smoothness or smooth-related attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arium
    -0.77
    EMP
    -0.68
    REL
    -0.68
    ilogy
    -0.66
    CVE
    -0.66
    Experts
    -0.65
    Quotes
    -0.65
    ³³³³³³³³³³³³³³³³
    -0.64
     Ancients
    -0.63
    acons
    -0.63
    POSITIVE LOGITS
     sailing
    1.09
     smooth
    0.98
    ies
    0.95
     transitions
    0.94
    ness
    0.94
    ie
    0.84
     transition
    0.82
    edo
    0.78
     clears
    0.78
    sheet
    0.78
    Act Density 0.021%

    No Known Activations