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

    Neuronpedia

    INDEX
    Explanations

    pronouns expressing personal sentiment or connection

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

    but followed by personal pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدی
    -0.56
    存于互联网档案馆
    -0.56
     planche
    -0.39
    posedge
    -0.38
    (__('
    -0.37
     Fron
    -0.37
    >{{
    -0.36
     redor
    -0.35
    )="
    -0.35
    typeOf
    -0.35
    POSITIVE LOGITS
    But
    0.96
     but
    0.88
     But
    0.87
    but
    0.85
    但她
    0.76
    但他
    0.73
    BUT
    0.73
     dennoch
    0.71
    但我
    0.71
     BUT
    0.69
    Act Density 0.043%

    No Known Activations