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

    Neuronpedia

    INDEX
    Explanations

    questions and punctuation marks, indicating a focus on interrogative statements and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.87
     <>",
    -0.73
    Билгалдахарш
    -0.72
     surla
    -0.68
    BASEPATH
    -0.66
     nakalista
    -0.64
     '\\;'
    -0.62
    stdc
    -0.61
    testens
    -0.61
     intptr
    -0.61
    POSITIVE LOGITS
    那就是
    0.80
     nämlich
    0.74
     namely
    0.67
     nemlig
    0.66
     Namely
    0.64
    :✨
    0.64
    대로
    0.62
    näm
    0.59
    namely
    0.59
    就是
    0.58
    Act Density 0.249%

    No Known Activations