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

    Neuronpedia

    INDEX
    Explanations

    phrases and metaphors related to superficial improvements or rebranding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TypeInfo
    -0.17
    icare
    -0.16
    ekk
    -0.15
    ÑĨез
    -0.15
    unci
    -0.15
    uder
    -0.15
    jour
    -0.15
    ilar
    -0.15
    efon
    -0.14
    ermo
    -0.14
    POSITIVE LOGITS
     fac
    0.15
    owski
    0.15
    zi
    0.15
    СÐŀ
    0.15
     Kou
    0.14
    olves
    0.14
    iani
    0.14
    osl
    0.14
    ango
    0.14
    ÐĵÐŀ
    0.14
    Act Density 0.256%

    No Known Activations