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

    Neuronpedia

    INDEX
    Explanations

    reports of events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reports."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wedge
    -0.76
    aughs
    -0.67
    arden
    -0.67
    stad
    -0.63
     manslaughter
    -0.62
    asper
    -0.60
    inant
    -0.60
     bung
    -0.59
    anthrop
    -0.59
     palate
    -0.59
    POSITIVE LOGITS
     emanating
    0.77
     reports
    0.76
    uggest
    0.73
    è¦ļéĨĴ
    0.71
     compiled
    0.71
    ynthesis
    0.70
    books
    0.70
    hran
    0.70
     briefings
    0.69
    flows
    0.69
    Act Density 0.039%

    No Known Activations