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

    Neuronpedia

    INDEX
    Explanations

    proper names, specifically focusing on the name "Alexis."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Alexis" and "Tul," as well as their associations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hered
    -0.89
    lla
    -0.88
    wagon
    -0.86
    shaw
    -0.83
    loads
    -0.82
    oreal
    -0.78
    ork
    -0.76
    orters
    -0.75
    ãĤ¦ãĤ¹
    -0.74
    ombat
    -0.73
    POSITIVE LOGITS
     mosqu
    0.90
    anke
    0.72
     topple
    0.69
    mol
    0.67
     coron
    0.66
    phas
    0.65
     Alexis
    0.64
     distingu
    0.63
    ARP
    0.63
     suspic
    0.63
    Act Density 0.035%

    No Known Activations