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

    Neuronpedia

    INDEX
    Explanations

    phrases that reference commonality and frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.68
     EconPapers
    -0.63
    interopRequire
    -0.63
    <!--[
    -0.62
    SequentialGroup
    -0.62
    发表于
    -0.61
    offsetof
    -0.61
    הערות
    -0.59
    tagHelperRunner
    -0.58
    ()]);
    -0.56
    POSITIVE LOGITS
     common
    1.36
    common
    1.22
    Common
    1.20
     Common
    1.13
     Commonly
    1.12
     commonly
    1.12
     común
    1.10
     COMMON
    1.10
    COMMON
    1.07
     popular
    1.03
    Act Density 0.564%

    No Known Activations