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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names with variations in spelling

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "us" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ottest
    -0.71
    regor
    -0.67
    taboola
    -0.62
    GM
    -0.61
     td
    -0.61
    quartered
    -0.60
    attery
    -0.60
    RAG
    -0.59
    ANK
    -0.59
    issance
    -0.59
    POSITIVE LOGITS
    pect
    1.07
    sein
    1.05
    pecting
    1.02
    pects
    0.98
    peed
    0.96
    hers
    0.95
    pex
    0.94
    cus
    0.91
    cules
    0.91
    pec
    0.87
    Act Density 0.027%

    No Known Activations