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

    Neuronpedia

    INDEX
    Explanations

    references to pipes and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -1.02
     Efq
    -0.92
    ☆☆☆☆
    -0.92
     myſelf
    -0.91
    makeConstraints
    -0.90
     Jefus
    -0.87
     chofe
    -0.86
    PhysRev
    -0.84
     pleaſure
    -0.84
    exemplar
    -0.81
    POSITIVE LOGITS
     pipes
    2.24
     pipe
    2.20
     Pipe
    2.10
    pipe
    2.02
    Pipe
    1.94
    Pipes
    1.91
     Pipes
    1.89
    pipes
    1.83
     PIPE
    1.82
    PIPE
    1.71
    Act Density 0.053%

    No Known Activations