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

    Neuronpedia

    INDEX
    Explanations

    scientific terminology and concepts related to physics or technology

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.63
    ✨:
    -0.62
     виправивши
    -0.61
    --)
    -0.60
    setVerticalGroup
    -0.59
     memoized
    -0.58
    />";
    -0.58
    ”),
    -0.57
    ']):
    -0.57
    .",
    -0.57
    POSITIVE LOGITS
    发表于
    0.70
     IIRC
    0.66
     BTW
    0.61
    Amicalement
    0.57
     IMHO
    0.56
    >@
    0.55
     btw
    0.54
     Sorry
    0.54
    DTD
    0.53
     Posted
    0.52
    Act Density 1.513%

    No Known Activations