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

    Neuronpedia

    INDEX
    Explanations

    references to the reader or audience, particularly focusing on possessive terms related to "you" and "your."

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

    your followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     invokingState
    -0.49
     AssemblyProduct
    -0.47
     resourceCulture
    -0.44
    jiny
    -0.43
    }{*}{
    -0.42
    lark
    -0.41
    InitVars
    -0.40
    -0.40
     noten
    -0.40
    出版年
    -0.39
    POSITIVE LOGITS
     your
    0.62
     you
    0.56
    あなたの
    0.52
    votre
    0.51
    your
    0.51
     yourself
    0.50
    ándote
    0.50
    讓你
    0.49
    あなた
    0.48
     você
    0.48
    Act Density 0.170%

    No Known Activations