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

    Neuronpedia

    INDEX
    Explanations

    references to system-generated code or warnings related to programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.42
    ↵
    -0.38
      
    -0.32
     civilización
    -0.32
    ,
    -0.31
    -
    -0.31
    1
    -0.31
    ↵↵
    -0.30
    2
    -0.30
    _
    -0.29
    POSITIVE LOGITS
    <unused3>
    1.42
    <unused28>
    1.41
    <unused8>
    1.41
    <unused43>
    1.41
    <unused14>
    1.41
    <unused41>
    1.41
    <unused42>
    1.41
    <unused17>
    1.41
    [@BOS@]
    1.41
    <unused16>
    1.41
    Act Density 0.677%

    No Known Activations