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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditions, restrictions, or negative implications

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

    either ... or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.46
    kháu
    -0.45
     artikkelen
    -0.44
    AnchorTagHelper
    -0.42
    hands
    -0.42
     defaultstate
    -0.40
    DeleteBehavior
    -0.39
     Penrose
    -0.39
    ButterKnife
    -0.39
     jär
    -0.39
    POSITIVE LOGITS
     too
    0.57
     again
    0.56
    これも
    0.53
     Again
    0.50
    Again
    0.47
    again
    0.46
     <=",
    0.45
    too
    0.45
     ebenfalls
    0.44
    こちらも
    0.43
    Act Density 0.671%

    No Known Activations