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

    Neuronpedia

    INDEX
    Explanations

    sequences related to structural or functional programming elements

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

    start of user turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.29
    1
    -0.29
    ↵
    -0.27
    2
    -0.27
    0
    -0.25
     пле
    -0.24
    3
    -0.24
      
    -0.24
    ↵↵
    -0.22
    Expiry
    -0.21
    POSITIVE LOGITS
    parsedMessage
    1.02
    <unused41>
    0.98
    <unused28>
    0.97
    <unused17>
    0.97
    <unused79>
    0.97
     kasarigan
    0.97
    <unused14>
    0.97
    <unused3>
    0.97
    [@BOS@]
    0.97
    <pad>
    0.97
    Act Density 0.000%

    No Known Activations