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

    Neuronpedia

    INDEX
    Explanations

    terms related to tools and means for achieving tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    twimg
    -0.91
     actionTypes
    -0.86
    TagMode
    -0.83
    itinéraire
    -0.82
     disambiguazione
    -0.81
     Hift
    -0.79
     Majefty
    -0.77
    ViewFeatures
    -0.77
     Efq
    -0.76
     EnglishChoose
    -0.76
    POSITIVE LOGITS
     tools
    1.47
     tool
    1.23
    tools
    1.13
     Tools
    1.11
     outils
    1.11
     herramientas
    1.04
    工具
    1.01
     TOOLS
    0.99
    Tools
    0.97
     means
    0.97
    Act Density 0.435%

    No Known Activations