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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their associations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    list separators and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     istrinya
    -0.33
    imágenes
    -0.31
     have
    -0.26
     liggen
    -0.26
     latas
    -0.25
    esercito
    -0.25
    อ้าง
    -0.25
     leggen
    -0.24
     če
    -0.24
    相关文章
    -0.24
    POSITIVE LOGITS
    [@BOS@]
    0.79
    <unused41>
    0.79
    <unused43>
    0.78
    <unused23>
    0.78
    <unused79>
    0.78
    <unused74>
    0.78
    <unused16>
    0.78
    <unused14>
    0.78
    <unused8>
    0.78
    <unused3>
    0.78
    Act Density 0.039%

    No Known Activations