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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to physical qualities or abilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaming mechanics and strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    angered
    -0.64
    ndum
    -0.59
    ̶
    -0.52
    Merit
    -0.52
     BuzzFeed
    -0.50
    realDonaldTrump
    -0.50
    Brexit
    -0.49
     embattled
    -0.49
     Trayvon
    -0.49
    SPONSORED
    -0.49
    POSITIVE LOGITS
     is
    1.23
     consists
    1.22
     includes
    1.22
     retains
    1.18
     tends
    1.17
     comprises
    1.16
     ensures
    1.15
     refers
    1.14
     utilizes
    1.14
     incorporates
    1.14
    Act Density 0.891%

    No Known Activations