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

    Neuronpedia

    INDEX
    Explanations

    patterns related to skipping actions or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    action to skip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dataclass
    -0.47
    er
    -0.44
     PeEnEo
    -0.43
     BrowserRouter
    -0.43
    Bibliograf
    -0.42
     HomeController
    -0.42
    bootstrapcdn
    -0.42
     bauer
    -0.41
     Mason
    -0.39
     Const
    -0.39
    POSITIVE LOGITS
    skip
    2.61
    Skip
    2.47
     skip
    2.34
     Skip
    2.33
     SKIP
    1.91
    SKIP
    1.80
     skips
    1.77
     skipped
    1.58
     skipping
    1.56
    skipped
    1.28
    Act Density 0.005%

    No Known Activations