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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence-ending markers in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allo
    -0.14
    ĨĴ
    -0.14
    plus
    -0.13
    ied
    -0.13
     ÐĿапÑĢимеÑĢ
    -0.13
    æľīä¸Ģ
    -0.13
     Nearby
    -0.13
    anos
    -0.13
    asted
    -0.13
     plus
    -0.12
    POSITIVE LOGITS
     Dub
    0.26
     Span
    0.23
     Comb
    0.22
    Dub
    0.20
     Spear
    0.20
     Mode
    0.20
     Bo
    0.20
     Cons
    0.19
     Apt
    0.19
     known
    0.19
    Act Density 0.399%

    No Known Activations