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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms related to analysis and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.74
    клопе
    -0.66
    NgModule
    -0.57
    évaluateur
    -0.51
    StructEnd
    -0.51
     Wicidata
    -0.50
     Мексичка
    -0.49
    Jîn
    -0.47
    TabStop
    -0.45
    emlrt
    -0.42
    POSITIVE LOGITS
    UnsafeEnabled
    0.65
    SpringBootTest
    0.63
     aufzu
    0.62
    _{[
    0.61
    Tembelea
    0.60
    XmlAccessType
    0.59
    complished
    0.59
    IBarButtonItem
    0.59
    reportWebVitals
    0.59
    oneofs
    0.59
    Act Density 0.980%

    No Known Activations