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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and code-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     civilización
    -0.46
    ↵
    -0.42
      
    -0.42
    ↵↵
    -0.41
     
    -0.40
     humanidad
    -0.38
     península
    -0.38
     religión
    -0.34
     amizade
    -0.33
    </em>
    -0.32
    POSITIVE LOGITS
    <unused3>
    1.60
    <unused43>
    1.60
    <unused28>
    1.60
    <unused41>
    1.60
    <unused8>
    1.60
    [@BOS@]
    1.60
    <unused14>
    1.60
    <unused23>
    1.59
    <unused17>
    1.59
    <unused16>
    1.59
    Act Density 0.665%

    No Known Activations