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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    possessive pronoun followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     your
    -0.32
     my
    -0.31
     his
    -0.29
     Your
    -0.28
     the
    -0.26
     Prensa
    -0.26
     our
    -0.26
     their
    -0.25
    Your
    -0.25
     человеком
    -0.25
    POSITIVE LOGITS
    providedIn
    0.84
     HasFactory
    0.83
    Rüyada
    0.81
     oprot
    0.81
     فريبيس
    0.75
    ⮜
    0.75
    <unused8>
    0.74
    <unused3>
    0.74
    windowFixed
    0.74
    <unused14>
    0.74
    Act Density 0.105%

    No Known Activations