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

    Neuronpedia

    INDEX
    Explanations

    patterns related to URL formatting and programming code

    oai_token-act-pair · gpt-3.5-turbo

    elements related to code and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ometimes
    -0.88
    surprisingly
    -0.81
    etheless
    -0.80
    conservancy
    -0.71
    theless
    -0.69
    ecause
    -0.60
     VIDEOS
    -0.60
     Invention
    -0.60
     exhibits
    -0.60
     spons
    -0.59
    POSITIVE LOGITS
    ")
    1.53
    ").
    1.46
    ");
    1.42
    "))
    1.42
    "]
    1.41
    )"
    1.40
    )",
    1.39
    "/>
    1.23
    "}
    1.23
    "),
    1.21
    Act Density 0.155%

    No Known Activations