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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical functions and probabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.74
    <b>
    -0.60
      
    -0.59
    <eos>
    -0.57
    ↵↵
    -0.54
    ​
    -0.49
     .
    -0.49
     trade
    -0.49
    <strong>
    -0.48
     
    -0.47
    POSITIVE LOGITS
    tagext
    0.96
    RegressionTest
    0.96
     betweenstory
    0.95
     houſe
    0.92
     becauſe
    0.92
     Efq
    0.91
    SharedCtor
    0.91
     ſta
    0.91
     Monfieur
    0.90
     perfons
    0.90
    Act Density 2.542%

    No Known Activations