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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating likelihood or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.71
    XmlAccessorType
    -0.70
     inol
    -0.68
     referenties
    -0.67
     مُعرِّف
    -0.67
     насељу
    -0.64
    ISODE
    -0.61
     wikipagina
    -0.60
     IBOutlet
    -0.60
     commences
    -0.59
    POSITIVE LOGITS
    .
    0.58
    </blockquote>
    0.55
     want
    0.55
     it
    0.55
    </h1>
    0.54
     you
    0.54
     sense
    0.53
     isNameExpr
    0.52
     risk
    0.51
     people
    0.50
    Act Density 1.804%

    No Known Activations