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

    Neuronpedia

    INDEX
    Explanations

    instances of misinformation or misleading statements in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     BytesLike
    -0.40
    ISupport
    -0.38
     useAppContext
    -0.37
     JScrollPane
    -0.37
    XmlSchema
    -0.37
    isContained
    -0.37
    Cyfarwyddwr
    -0.36
     theoretical
    -0.36
     tearDown
    -0.35
    Географија
    -0.35
    POSITIVE LOGITS
     fooled
    0.63
     betweenstory
    0.60
     confuse
    0.59
     mimicking
    0.57
     confund
    0.57
    principalColumn
    0.57
     deceived
    0.57
     disambiguazione
    0.57
     confusing
    0.56
     misled
    0.55
    Act Density 0.494%

    No Known Activations