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

    Neuronpedia

    INDEX
    Explanations

    profession or role titles

    oai_token-act-pair · gpt-3.5-turbo

    titles or roles related to leadership and professional positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اÙĦ
    -0.70
    STDOUT
    -0.69
    doors
    -0.67
     Invalid
    -0.67
     Liberties
    -0.63
    earchers
    -0.63
     Dragons
    -0.60
     Dolphin
    -0.60
     Maiden
    -0.60
     Kitchen
    -0.60
    POSITIVE LOGITS
    hood
    1.16
    dom
    1.08
    ship
    1.02
    doms
    1.00
    alties
    0.99
    ially
    0.99
    esses
    0.98
    ial
    0.96
    rics
    0.89
     corps
    0.88
    Act Density 0.496%

    No Known Activations