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

    Neuronpedia

    INDEX
    Explanations

    references to news articles, particularly ones discussing specific events or topics

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or actions discussed in a news context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.67
     acquisitions
    -0.56
    advant
    -0.54
     hosp
    -0.53
    iever
    -0.50
     acquisition
    -0.50
    merce
    -0.50
     battled
    -0.50
     Advantage
    -0.48
    undai
    -0.48
    POSITIVE LOGITS
     reader
    0.68
     pages
    0.68
     narration
    0.68
     circulated
    0.68
     reprinted
    0.67
     readers
    0.66
     summar
    0.66
     redacted
    0.66
     quoted
    0.64
     caption
    0.63
    Act Density 1.304%

    No Known Activations