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

    Neuronpedia

    INDEX
    Explanations

    references to possessive pronouns in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OGND
    -0.82
    XmlAccessorType
    -0.71
     kaarangay
    -0.68
    verwijspagina
    -0.66
    TagMode
    -0.66
    сылкі
    -0.65
    featureID
    -0.65
    Välislingid
    -0.65
    MessageOf
    -0.64
    Билгалдахарш
    -0.63
    POSITIVE LOGITS
     therein
    0.42
     trong
    0.41
     inside
    0.40
     nella
    0.40
    在他
    0.39
    Dalam
    0.39
     darin
    0.38
     dalam
    0.38
     didalam
    0.38
     in
    0.38
    Act Density 0.186%

    No Known Activations