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

    Neuronpedia

    INDEX
    Explanations

    instances of people reporting observations or experiences

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "have" and its associations with reports or actions related to groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.68
    inventoryQuantity
    -0.64
    lein
    -0.63
     predecessor
    -0.62
    Vers
    -0.62
    âĶ
    -0.61
     resides
    -0.60
    Aw
    -0.58
    Evil
    -0.58
     Viz
    -0.57
    POSITIVE LOGITS
     routinely
    1.00
     increasingly
    0.97
     everywhere
    0.95
     beware
    0.90
     clam
    0.89
     outnumbered
    0.88
     encouraged
    0.88
     alike
    0.88
     plentiful
    0.86
    ateurs
    0.84
    Act Density 0.394%

    No Known Activations