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

    Neuronpedia

    INDEX
    Explanations

    references to built-in components or features in technology or software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.71
    ValueStyle
    -0.66
    twimg
    -0.65
    permitAll
    -0.56
    WriteTagHelper
    -0.56
     שוליים
    -0.55
     متعلقه
    -0.54
    elemField
    -0.52
    بوابة
    -0.51
    AndEndTag
    -0.49
    POSITIVE LOGITS
     builtin
    0.95
     intrinsic
    0.92
    intrinsic
    0.89
     endogenous
    0.88
     Intrinsic
    0.81
    内置
    0.80
    builtin
    0.78
     inherent
    0.77
     native
    0.77
    Intrinsic
    0.76
    Act Density 0.400%

    No Known Activations