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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onies
    -0.76
    techn
    -0.75
    count
    -0.74
    vag
    -0.74
    ************
    -0.73
    vir
    -0.72
    safety
    -0.72
    ystem
    -0.70
    system
    -0.70
    tracking
    -0.70
    POSITIVE LOGITS
     Holt
    0.88
     Ack
    0.87
     Fernandez
    0.87
     Gos
    0.86
     Gors
    0.84
     Seb
    0.84
     Silva
    0.83
     Dillon
    0.83
     Doe
    0.80
     Grayson
    0.79
    Act Density 0.202%

    No Known Activations