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

    Neuronpedia

    INDEX
    Explanations

    mentions of words related to computer programming languages

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apego
    -0.86
    rodu
    -0.85
    roxy
    -0.82
    agher
    -0.81
    kus
    -0.80
    ilts
    -0.79
    arranted
    -0.77
    TAIN
    -0.77
    arios
    -0.76
    enary
    -0.76
    POSITIVE LOGITS
     spoken
    1.02
    ĨĴ
    0.94
    language
    0.88
     learners
    0.87
     interpreter
    0.86
     flu
    0.85
     proficiency
    0.81
     translation
    0.78
     languages
    0.76
     Languages
    0.76
    Act Density 0.023%

    No Known Activations