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

    Neuronpedia

    INDEX
    Explanations

    mentions of prestigious or top-ranking entities or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "premier" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alle
    -0.84
    gers
    -0.83
    akia
    -0.82
    arettes
    -0.81
    IGHTS
    -0.75
    amus
    -0.75
    urat
    -0.72
    ravings
    -0.72
    urers
    -0.71
    avery
    -0.71
    POSITIVE LOGITS
     premier
    0.96
     antioxid
    0.78
    wcs
    0.77
     Premiere
    0.76
    ois
    0.76
    sonian
    0.75
    iary
    0.72
     certs
    0.72
    aire
    0.71
    CTV
    0.70
    Act Density 0.004%

    No Known Activations