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

    Neuronpedia

    INDEX
    Explanations

    references to food and dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     queſta
    -1.30
    <unused41>
    -1.10
    <unused28>
    -1.09
    [@BOS@]
    -1.09
    <unused8>
    -1.09
    <unused17>
    -1.09
    <unused23>
    -1.09
    <unused16>
    -1.09
    <pad>
    -1.09
    <unused14>
    -1.09
    POSITIVE LOGITS
    ↵
    0.73
    .
    0.70
    <em>
    0.69
    ,
    0.67
    <strong>
    0.66
      
    0.66
    1
    0.66
    *
    0.65
    2
    0.63
    <i>
    0.63
    Act Density 0.133%

    No Known Activations