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

    Neuronpedia

    INDEX
    Explanations

    list items in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.81
     パンチラ
    -0.71
    󠁣
    -0.71
     fashiola
    -0.69
    <unused14>
    -0.69
    <unused8>
    -0.69
    <unused41>
    -0.69
    <unused51>
    -0.69
    <pad>
    -0.69
    <unused1>
    -0.69
    POSITIVE LOGITS
    :✨
    0.55
    <eos>
    0.45
    ________________
    0.40
    ↵↵
    0.35
     ویکی‌آمباردا
    0.32
    ↵
    0.32
    <tr>
    0.32
     intptr
    0.32
    ↵↵↵
    0.32
    LITERAL
    0.30
    Act Density 0.000%

    No Known Activations