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

    Neuronpedia

    INDEX
    Explanations

    references to specific athletes or sports figures

    oai_token-act-pair · gpt-3.5-turbo

    names of sports players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.88
    FINE
    -0.75
    scribe
    -0.64
     newsp
    -0.62
    clusive
    -0.62
    cerpt
    -0.62
     Afterwards
    -0.61
     Enlightenment
    -0.60
     explicit
    -0.60
    ranging
    -0.60
    POSITIVE LOGITS
     deserves
    1.42
     possesses
    1.38
     lacks
    1.36
     shines
    1.30
     tends
    1.30
     dominates
    1.27
     averages
    1.27
     excel
    1.26
     performs
    1.23
     ranks
    1.22
    Act Density 0.296%

    No Known Activations