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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of popularity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اظ
    -0.16
    empre
    -0.16
    edi
    -0.15
    uality
    -0.15
     Rossi
    -0.15
    Ìĥ
    -0.15
    manship
    -0.14
    ors
    -0.14
    ä¸į足
    -0.14
    ored
    -0.14
    POSITIVE LOGITS
    ly
    0.28
     culture
    0.24
    izers
    0.23
    izing
    0.23
    izer
    0.21
    ized
    0.21
    ization
    0.20
     Culture
    0.20
     sovereignty
    0.19
    culture
    0.19
    Act Density 0.010%

    No Known Activations