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

    Neuronpedia

    INDEX
    Explanations

    references to quality control and verification processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.88
    writeFieldEnd
    -0.64
     downvotes
    -0.60
    ictured
    -0.57
    HomeAsUp
    -0.56
     defaultValue
    -0.56
    RegressionTest
    -0.56
     downvoted
    -0.55
    akujem
    -0.55
     defStyle
    -0.55
    POSITIVE LOGITS
    HasAnnotation
    0.66
     whether
    0.65
     apakah
    0.65
     是否
    0.57
    是否有
    0.57
    是否是
    0.56
    是否
    0.56
     آیا
    0.56
    check
    0.54
    有無
    0.54
    Act Density 0.403%

    No Known Activations