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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate intent or purpose, particularly in the context of actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oon
    -0.19
    arat
    -0.17
    481
    -0.16
    ãģ¡ãģ¯
    -0.16
    à¤Ĥà¤ĺ
    -0.15
     cha
    -0.15
    illow
    -0.14
     dit
    -0.14
     Hubbard
    -0.14
    igest
    -0.14
    POSITIVE LOGITS
    oka
    0.16
     dÆ°
    0.15
     omap
    0.15
    ĴĮ
    0.14
    gage
    0.14
    akis
    0.14
    ãĥĻãĥ«
    0.14
    /XMLSchema
    0.13
    /inc
    0.13
    ForKey
    0.13
    Act Density 0.013%

    No Known Activations