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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uniqueness and differentiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    'acc
    -0.14
    ladu
    -0.13
    stery
    -0.13
    ugin
    -0.13
    ArrayOf
    -0.13
    èĮĤ
    -0.13
     cpt
    -0.13
    ä¸
    -0.13
    ’acc
    -0.13
    loquent
    -0.12
    POSITIVE LOGITS
     unique
    0.50
    unique
    0.45
     uniqueness
    0.45
     Unique
    0.44
    Unique
    0.44
     differ
    0.43
     UNIQUE
    0.42
     difference
    0.42
     differs
    0.41
     unlike
    0.39
    Act Density 0.293%

    No Known Activations