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

    Neuronpedia

    INDEX
    Explanations

    clauses that express causation or reasoning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adaptiveStyles
    -0.61
     unread
    -0.61
     deactivate
    -0.61
     regrettable
    -0.59
    ifflin
    -0.59
    RegressionTest
    -0.58
     autoradio
    -0.58
    Baylor
    -0.58
     Tajikistan
    -0.56
    ValueGenerated
    -0.55
    POSITIVE LOGITS
    newBuilder
    0.58
    closePath
    0.57
    /}.
    0.57
     estimés
    0.56
    ografija
    0.55
    @[+][
    0.53
     StatelessWidget
    0.52
    IVOS
    0.50
    setLayoutManager
    0.48
    出版年
    0.48
    Act Density 0.477%

    No Known Activations