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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships and properties of objects in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    substack
    -0.54
    はじめに
    -0.49
    Begriffsklä
    -0.49
     الدولى
    -0.47
    HomeAsUpEnabled
    -0.47
    IBAction
    -0.46
     noten
    -0.45
    ribusi
    -0.44
    FontAwesomeIcon
    -0.44
    >--}}
    -0.43
    POSITIVE LOGITS
    gadas
    0.59
    ebvre
    0.55
     سكانية
    0.54
    IndentedString
    0.53
     list
    0.52
    多い
    0.52
     peine
    0.52
     Offisielt
    0.52
     pack
    0.52
    єра
    0.51
    Act Density 0.807%

    No Known Activations