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

    Neuronpedia

    INDEX
    Explanations

    XML parameters and statistics related to memory and processing performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -1.23
    <unused8>
    -1.07
    <unused23>
    -1.07
    <unused43>
    -1.07
    <unused51>
    -1.07
    [@BOS@]
    -1.07
    <unused16>
    -1.07
    <unused42>
    -1.07
    <unused74>
    -1.07
    <unused41>
    -1.07
    POSITIVE LOGITS
     city
    0.37
    ↵↵
    0.33
     book
    0.32
    ↵
    0.31
     
    0.31
      
    0.30
     food
    0.30
     girl
    0.28
    ,
    0.28
    <eos>
    0.28
    Act Density 0.536%

    No Known Activations