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

    Neuronpedia

    INDEX
    Explanations

    specific phrasing and references to titles or names within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.82
    parsedMessage
    -0.71
    InjectAttribute
    -0.67
    __*/
    -0.66
    basicConfig
    -0.58
    ViewImports
    -0.58
     estimés
    -0.58
     guère
    -0.58
     Superhosts
    -0.58
    دانشنامهٔ
    -0.58
    POSITIVE LOGITS
    ⓘ
    0.63
     lautet
    0.61
    「
    0.59
     باسم
    0.58
    Datuak
    0.57
     titled
    0.56
     bernama
    0.56
     entitled
    0.55
    ering
    0.54
    prm
    0.53
    Act Density 1.044%

    No Known Activations