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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their variations in style

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

    dashes and em dashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.42
     Rud
    -0.40
     it
    -0.39
     H
    -0.38
     P
    -0.38
     pape
    -0.37
     Oil
    -0.36
     It
    -0.35
     Is
    -0.35
     $\
    -0.35
    POSITIVE LOGITS
    AndEndTag
    0.72
    Rüyada
    0.70
    aarrggbb
    0.69
    [@BOS@]
    0.67
    <unused17>
    0.66
    <unused14>
    0.66
    <unused23>
    0.66
    <unused28>
    0.66
    <unused3>
    0.66
    <unused8>
    0.66
    Act Density 0.026%

    No Known Activations