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

    Neuronpedia

    INDEX
    Explanations

    terms related to sorting and database management

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

    upcoming events and sorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -1.09
    <unused52>
    -0.97
    [@BOS@]
    -0.97
    <unused43>
    -0.97
    <unused41>
    -0.97
    <unused16>
    -0.96
    <unused51>
    -0.96
    <unused14>
    -0.96
    <unused79>
    -0.96
    <unused3>
    -0.96
    POSITIVE LOGITS
    :
    0.52
    ↵
    0.40
     
    0.40
    \
    0.37
    .
    0.37
    ↵↵
    0.37
    2
    0.35
     is
    0.35
    (
    0.35
    _
    0.34
    Act Density 0.004%

    No Known Activations