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

    Neuronpedia

    INDEX
    Explanations

    names, likely of authors or characters in literary and media contexts

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.74
     WHERE
    -0.69
    etheless
    -0.65
    orthern
    -0.63
    LEASE
    -0.61
    behind
    -0.61
     TBD
    -0.60
    orate
    -0.59
    include
    -0.58
     CPC
    -0.58
    POSITIVE LOGITS
     prefers
    1.07
     recommends
    1.05
     invented
    1.04
     remembers
    1.03
     coined
    1.01
     pioneered
    0.99
     knows
    0.99
     thinks
    0.97
     mentions
    0.96
     describes
    0.96
    Act Density 0.398%

    No Known Activations