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

    Neuronpedia

    INDEX
    Explanations

    references to the word "brown" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -0.78
     Ellison
    -0.69
    Ciri
    -0.65
     }?>
    -0.63
    Kiri
    -0.63
     CreateTagHelper
    -0.61
     Champlain
    -0.61
    ropractic
    -0.61
    Erreferentziak
    -0.61
    НИК
    -0.60
    POSITIVE LOGITS
     Browns
    1.06
     Brown
    1.06
    BROWN
    1.02
     BROWN
    0.99
    Brown
    0.96
     browns
    0.92
     brown
    0.84
    brown
    0.82
    Brow
    0.80
     BROW
    0.73
    Act Density 0.073%

    No Known Activations