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

    Neuronpedia

    INDEX
    Explanations

    terms related to medical conditions and treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused3>
    -1.79
    <unused52>
    -1.79
    <unused14>
    -1.79
    <unused51>
    -1.78
    <unused16>
    -1.78
    [@BOS@]
    -1.78
    <unused17>
    -1.77
    <unused23>
    -1.77
    <unused8>
    -1.77
    <pad>
    -1.77
    POSITIVE LOGITS
    ↵↵
    0.49
    <strong>
    0.43
     
    0.40
    2
    0.37
    <em>
    0.36
    -
    0.36
    /
    0.35
    <eos>
    0.35
    +
    0.34
    1
    0.34
    Act Density 2.739%

    No Known Activations