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

    Neuronpedia

    INDEX
    Explanations

    references to non-fiction or specific data types in structured formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     الحره
    -1.14
    parsedMessage
    -1.11
    <unused41>
    -0.98
    <unused74>
    -0.98
    <unused42>
    -0.98
    <unused43>
    -0.98
    <unused79>
    -0.98
    [@BOS@]
    -0.98
    <pad>
    -0.97
    <unused8>
    -0.97
    POSITIVE LOGITS
     city
    0.45
     state
    0.40
     place
    0.39
     level
    0.38
     body
    0.37
     value
    0.36
     type
    0.36
     model
    0.35
     company
    0.35
     price
    0.35
    Act Density 0.589%

    No Known Activations