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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns and references to ownership or personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.78
    :✨
    -0.64
    ⟬
    -0.59
    ✨:
    -0.59
     للمعارف
    -0.59
     ***!
    -0.57
    cellation
    -0.56
     Rutland
    -0.55
     disambiguazione
    -0.54
     pageContext
    -0.54
    POSITIVE LOGITS
    whose
    0.49
     whose
    0.47
     cuja
    0.40
     cuyo
    0.38
    Whose
    0.36
    HideFlags
    0.35
    туга
    0.34
     His
    0.34
     jonka
    0.34
     hjælp
    0.33
    Act Density 0.261%

    No Known Activations