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

    Neuronpedia

    INDEX
    Explanations

    mentions of equality, specifically related to rights, worth, and love

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     liberality
    -0.59
     thereupon
    -0.58
     Voilà
    -0.56
     Shakspeare
    -0.56
     tolerably
    -0.55
     Aras
    -0.54
     endeavouring
    -0.54
     Autre
    -0.53
     Inhabitants
    -0.52
     Sugges
    -0.51
    POSITIVE LOGITS
     Equal
    1.08
     equal
    1.07
    equal
    0.99
     EQUAL
    0.99
    Equal
    0.97
     equality
    0.85
     equ
    0.83
    EQUAL
    0.82
     EQU
    0.81
     equals
    0.80
    Act Density 0.103%

    No Known Activations