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

    Neuronpedia

    INDEX
    Explanations

    contextually significant punctuation and formatting marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fallu
    -0.82
    &=&
    -0.66
     &=&
    -0.65
    &=&\
    -0.62
    Ї
    -0.61
    IUrlHelper
    -0.59
     AssemblyCulture
    -0.59
    featureID
    -0.58
     करती
    -0.58
    XmlAttribute
    -0.57
    POSITIVE LOGITS
     He
    3.79
    He
    3.46
     His
    2.80
    His
    2.78
     he
    2.69
     his
    2.43
    彼は
    2.37
     him
    2.37
     Он
    2.24
     그는
    2.22
    Act Density 0.700%

    No Known Activations