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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotions or personal opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.75
    PDF
    -0.75
     outset
    -0.73
    Attempts
    -0.73
    onding
    -0.72
    earchers
    -0.71
    igent
    -0.70
    utterstock
    -0.68
    istrates
    -0.68
     permitting
    -0.67
    POSITIVE LOGITS
    âĢ
    0.99
     Kanye
    0.98
     Elsa
    0.98
     âĢ
    0.96
    âĿ
    0.96
     he
    0.94
     Beyon
    0.90
     Blizz
    0.90
     Rih
    0.90
     Kyl
    0.89
    Act Density 0.591%

    No Known Activations