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

    Neuronpedia

    INDEX
    Explanations

    references to equality and equal treatment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "):
    -0.81
     Kaye
    -0.79
    ProgressHUD
    -0.78
    Hawks
    -0.69
    kirakan
    -0.69
     pinulongan
    -0.69
    /***/
    -0.68
    Pyx
    -0.68
     Montrose
    -0.67
    es
    -0.67
    POSITIVE LOGITS
     equal
    1.79
     Equal
    1.71
    Equal
    1.60
    equal
    1.60
     EQUAL
    1.58
    EQUAL
    1.45
     égal
    1.39
     equals
    1.39
     égale
    1.15
    ('=
    1.12
    Act Density 0.066%

    No Known Activations