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

    Neuronpedia

    INDEX
    Explanations

    instances of events or situations being officially documented or made known to the public

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "reported."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vous
    -0.77
    ierre
    -0.74
    enta
    -0.71
    oldemort
    -0.70
    alos
    -0.70
    creen
    -0.69
    ophers
    -0.69
    aho
    -0.68
    ificial
    -0.68
    ateral
    -0.67
    POSITIVE LOGITS
    è¦ļéĨĴ
    1.01
     sightings
    0.96
     sighting
    0.78
     favorably
    0.73
     reports
    0.72
     Stories
    0.72
    ounces
    0.71
     Patterns
    0.71
     extensively
    0.69
     incidents
    0.67
    Act Density 0.041%

    No Known Activations