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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leadership and authority

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ially
    -0.81
    rics
    -0.78
    affiliated
    -0.78
    untarily
    -0.74
    EH
    -0.71
    iculty
    -0.71
    accompanied
    -0.71
    members
    -0.70
    Contact
    -0.70
    atively
    -0.70
    POSITIVE LOGITS
     apocalypse
    1.17
     abyss
    1.10
     heavens
    1.07
     afterlife
    1.03
     cosmos
    1.02
     iceberg
    1.00
     universe
    0.99
     proverbial
    0.97
     devil
    0.96
     imagination
    0.95
    Act Density 0.423%

    No Known Activations