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

    Neuronpedia

    INDEX
    Explanations

    references to a specific personal pronoun indicating the second person

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
    posedge
    -0.71
     BorderRadius
    -0.70
     GenerationType
    -0.65
    πάρχ
    -0.63
    jfree
    -0.62
    StructEnd
    -0.62
     urbanos
    -0.59
    LookAnd
    -0.57
    openConnection
    -0.56
    Ligações
    -0.56
    POSITIVE LOGITS
    you
    1.34
    YOU
    1.16
    você
    0.77
    protoimpl
    0.63
     سكانية
    0.57
    bleau
    0.56
    Ours
    0.56
     Ours
    0.53
    yoo
    0.52
     itr
    0.52
    Act Density 0.004%

    No Known Activations