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

    Neuronpedia

    INDEX
    Explanations

    underscore-prefixed variables commonly used in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TagMode
    -0.59
    bitField
    -0.55
    XmlAccessorType
    -0.55
    jsxFileName
    -0.54
     réf
    -0.52
     AssemblyProduct
    -0.51
    homonymie
    -0.50
    ποτε
    -0.49
    weza
    -0.48
     dési
    -0.48
    POSITIVE LOGITS
     greateſt
    0.68
     Chriftian
    0.66
    gerald
    0.66
     iſt
    0.65
     fevere
    0.64
     ſmall
    0.63
     виправивши
    0.62
    ſelves
    0.62
     ſtre
    0.61
    ſelf
    0.61
    Act Density 0.221%

    No Known Activations