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

    Neuronpedia

    INDEX
    Explanations

    references to different types and characteristics of pipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.98
     Coliseum
    -0.84
     Quis
    -0.84
     honore
    -0.84
    gtest
    -0.84
    PhysRev
    -0.83
     estimés
    -0.82
     desorption
    -0.82
    SceneManagement
    -0.81
    PhysRevD
    -0.79
    POSITIVE LOGITS
     pipes
    1.37
     pipe
    1.31
    pipe
    1.30
     Pipe
    1.29
     Pipes
    1.20
    Pipes
    1.19
    Pipe
    1.17
    PIPE
    1.16
    Piper
    1.15
     Piper
    1.14
    Act Density 0.187%

    No Known Activations