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

    Neuronpedia

    INDEX
    Explanations

    the word "that" in various contexts and frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essen
    -0.16
     Äijáng
    -0.15
    ushman
    -0.15
    odate
    -0.15
     wounded
    -0.14
     brethren
    -0.14
    zew
    -0.14
    sic
    -0.14
    etu
    -0.14
    ieu
    -0.13
    POSITIVE LOGITS
    /th
    0.16
    caffold
    0.15
     mesma
    0.14
    anders
    0.14
    wend
    0.14
     putas
    0.14
    Extras
    0.14
     ÐĵÐŀ
    0.14
    oping
    0.14
    æ´
    0.13
    Act Density 0.113%

    No Known Activations