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

    Neuronpedia

    INDEX
    Explanations

    terms related to edges and boundaries in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnsafeEnabled
    -0.42
    RenderAtEndOf
    -0.42
    //
    -0.38
    っくり
    -0.38
     aDecoder
    -0.38
    zkod
    -0.37
    UVWXYZ
    -0.36
     bombar
    -0.35
    jsii
    -0.34
    bomb
    -0.34
    POSITIVE LOGITS
     edge
    3.08
     edges
    2.83
     Edge
    2.63
    edge
    2.53
    Edge
    2.52
     Edges
    2.44
     EDGE
    2.33
    edges
    2.23
    Edges
    2.14
    EDGE
    2.14
    Act Density 0.733%

    No Known Activations