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

    Neuronpedia

    INDEX
    Explanations

    occurrences of completion and progress indicators in instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    expandindo
    -0.93
     cherchés
    -0.89
     insuffisamment
    -0.88
     doInBackground
    -0.87
     StatefulWidget
    -0.86
    ContentAsync
    -0.84
    tvguidetime
    -0.84
     AssemblyTitle
    -0.83
     виправивши
    -0.83
    SequentialGroup
    -0.79
    POSITIVE LOGITS
    Then
    0.64
     Then
    0.62
     then
    0.61
    then
    0.60
    <eos>
    0.59
     Alternatively
    0.58
    Alternatively
    0.57
    "".
    0.49
     Start
    0.48
     Note
    0.47
    Act Density 0.058%

    No Known Activations