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

    Neuronpedia

    INDEX
    Explanations

    references to piping and plumbing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     obstante
    -0.86
    <%=
    -0.84
    permitAll
    -0.82
     Goddard
    -0.81
     Elbe
    -0.81
     entanto
    -0.80
     Denison
    -0.79
     estimés
    -0.79
    theless
    -0.78
    makeConstraints
    -0.75
    POSITIVE LOGITS
    pipe
    1.11
     pipe
    1.10
     Pipe
    1.09
    Pipe
    1.04
     pipes
    0.93
    pipes
    0.90
     Hilde
    0.89
    piper
    0.86
    Pipes
    0.86
     piper
    0.85
    Act Density 0.592%

    No Known Activations