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

    Neuronpedia

    INDEX
    Explanations

    phrases that express uncertainty or conditionality in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    attamento
    -0.60
    <bos>
    -0.58
     Meksiku
    -0.56
    msgTypes
    -0.56
     viata
    -0.52
    BURGH
    -0.51
     Svg
    -0.51
    PII
    -0.50
    :✨
    -0.49
    onaire
    -0.49
    POSITIVE LOGITS
    izarse
    0.63
    NewUrlParser
    0.61
     chắc
    0.60
     Genu
    0.59
    writeFieldEnd
    0.59
    trun
    0.57
    Externé
    0.55
     дописавши
    0.55
    ंदीखरीदारी
    0.54
     CURIAM
    0.54
    Act Density 0.197%

    No Known Activations