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

    Neuronpedia

    INDEX
    Explanations

    words related to the term "lingua," especially when coupled with specific qualities

    oai_token-act-pair · gpt-3.5-turbo

    references to language and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DonaldTrump
    -0.88
    Õ
    -0.78
    κ
    -0.77
    awaru
    -0.76
    night
    -0.74
    ¶ħ
    -0.73
    ï¸
    -0.71
    hyde
    -0.71
    âķIJâķIJ
    -0.69
    urnal
    -0.69
    POSITIVE LOGITS
     Ling
    0.88
     Tigers
    0.82
    zzo
    0.81
    ering
    0.76
     ling
    0.69
    xit
    0.69
     Xin
    0.68
     Lauder
    0.67
    enf
    0.67
    anguage
    0.67
    Act Density 0.041%

    No Known Activations