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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically quotation marks and apostrophes

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

    code string literals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.40
    xase
    -0.40
     wyś
    -0.37
    _{(
    -0.37
     vindt
    -0.37
    _{[
    -0.36
    lorette
    -0.35
    setViewportView
    -0.35
    在于
    -0.34
    <tbody>
    -0.34
    POSITIVE LOGITS
    ]+"
    0.63
    )+"
    0.59
    ()+"
    0.57
    ]<<"
    0.55
    +"
    0.54
     Speer
    0.49
    anskje
    0.49
     +"
    0.49
    +="
    0.47
    luß
    0.47
    Act Density 0.009%

    No Known Activations