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

    Neuronpedia

    INDEX
    Explanations

    self-referential statements within a mathematical proof.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thats
    -0.07
    olds
    -0.07
    That
    -0.07
    CustomAttributes
    -0.06
    è¿Ļæĺ¯
    -0.06
    že
    -0.06
     THAT
    -0.06
    ÑĮого
    -0.06
     That
    -0.06
    /query
    -0.06
    POSITIVE LOGITS
    Unless
    0.10
     unless
    0.10
     nothing
    0.09
     Unless
    0.09
     initially
    0.09
     no
    0.08
     nowhere
    0.08
    unless
    0.08
    nothing
    0.08
     maybe
    0.07
    Act Density 0.064%

    No Known Activations