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

    Neuronpedia

    INDEX
    Explanations

    statuses and legal terms related to judicial matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused14>
    -1.07
    <unused8>
    -1.07
    <unused41>
    -1.07
    <unused52>
    -1.07
    <unused17>
    -1.06
    <unused16>
    -1.06
    <unused28>
    -1.06
    <unused42>
    -1.06
    [@BOS@]
    -1.06
    <unused3>
    -1.06
    POSITIVE LOGITS
     known
    0.62
     
    0.56
    ↵
    0.54
    ↵↵
    0.49
     nice
    0.49
    न
    0.46
     (
    0.43
    ,
    0.43
     key
    0.42
     water
    0.41
    Act Density 0.276%

    No Known Activations