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

    Neuronpedia

    INDEX
    Explanations

    numerical values and percentages in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
      
    -0.69
    ↵↵
    -0.64
    <eos>
    -0.61
     Cor
    -0.61
     currency
    -0.60
    ↵
    -0.60
    ...
    -0.60
     за
    -0.57
    <em>
    -0.57
     Krueger
    -0.56
    POSITIVE LOGITS
    Datuak
    1.35
     myſelf
    1.12
     invokingState
    1.07
     kaynağından
    1.05
     doInBackground
    1.04
     Monfieur
    1.01
     Majefty
    1.00
     doubtnut
    1.00
     raiſ
    0.99
     quæ
    0.99
    Act Density 0.790%

    No Known Activations