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

    Neuronpedia

    INDEX
    Explanations

    the surname "Wallace" and potentially the word followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    the name "Wallace."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    country
    -0.82
    oint
    -0.76
     motorcycle
    -0.70
     pist
    -0.70
    controller
    -0.67
    Hot
    -0.67
    AS
    -0.66
    Active
    -0.66
     Nep
    -0.65
     heavenly
    -0.65
    POSITIVE LOGITS
     Wallace
    3.94
    Wall
    1.65
     Hayes
    1.35
     Wolfe
    1.30
     Stevenson
    1.19
     Walters
    1.17
     Sanford
    1.17
     Irwin
    1.16
     Wilde
    1.16
    Wilson
    1.13
    Act Density 0.018%

    No Known Activations