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

    Neuronpedia

    INDEX
    Explanations

    titles or roles within organizations

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles of executives or leaders in organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nikov
    -0.78
    orsi
    -0.70
     needle
    -0.70
    oven
    -0.68
     helicop
    -0.66
    perate
    -0.64
    umatic
    -0.63
    abet
    -0.62
    اÙĦ
    -0.62
    schild
    -0.62
    POSITIVE LOGITS
     Shaun
    0.80
     Becky
    0.75
    ounces
    0.73
    ially
    0.70
     Tony
    0.70
     Patty
    0.68
     laureate
    0.68
     Lucy
    0.67
     Hide
    0.66
     Cecil
    0.66
    Act Density 0.158%

    No Known Activations