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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate concerns, observations, and relationships between entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     كومونز
    -0.65
    Биография
    -0.64
     tantôt
    -0.61
     näin
    -0.59
     onely
    -0.59
    لمانيا
    -0.58
    alnız
    -0.58
     zwar
    -0.56
    setLayoutManager
    -0.55
     Simplemente
    -0.55
    POSITIVE LOGITS
     utafitiHapana
    0.78
    ValueStyle
    0.57
    MLLoader
    0.57
    Kjelder
    0.57
    日閲覧
    0.56
     וגם
    0.56
     aussi
    0.56
    ALSO
    0.55
    Diweddarwch
    0.54
    :✨
    0.54
    Act Density 0.686%

    No Known Activations