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

    Neuronpedia

    INDEX
    Explanations

    operations related to bit-shifting in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Groen
    -0.58
    RAHAM
    -0.58
    Corn
    -0.57
    Toponymie
    -0.57
    复制代码
    -0.55
     Horv
    -0.54
     corn
    -0.53
    Anhalt
    -0.50
    SequentialGroup
    -0.49
    ёх
    -0.49
    POSITIVE LOGITS
     <<
    2.94
    <<
    2.51
    )<<
    2.00
    ]<<
    1.94
    <<<
    1.75
    ()<<
    1.70
     <<=
    1.68
    <<"
    1.65
    <<(
    1.64
    <<<<
    1.58
    Act Density 0.032%

    No Known Activations