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

    Neuronpedia

    INDEX
    Explanations

    terms and structures related to programming and data processing in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.96
     
    -0.95
    ↵
    -0.95
    ↵↵
    -0.93
    2
    -0.91
     (
    -0.90
    1
    -0.90
    -
    -0.87
    (
    -0.86
    3
    -0.83
    POSITIVE LOGITS
    parsedMessage
    1.75
     queſta
    1.63
     imagui
    1.52
    [@BOS@]
    1.50
    <unused43>
    1.50
    <unused16>
    1.49
    <unused23>
    1.49
    <unused14>
    1.49
    <unused3>
    1.49
    <unused8>
    1.49
    Act Density 0.792%

    No Known Activations