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

    Neuronpedia

    INDEX
    Explanations

    language that is emotionally charged or carries significant meaning or impact

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "language" in various contexts, particularly those related to legal, social, or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilon
    -0.92
    kus
    -0.83
    roxy
    -0.82
    rodu
    -0.81
    oppable
    -0.81
    rolet
    -0.80
    rium
    -0.79
    iary
    -0.78
    ilts
    -0.78
    romeda
    -0.76
    POSITIVE LOGITS
     learners
    1.05
    language
    1.01
     spoken
    0.98
     language
    0.91
    anguage
    0.90
     interpreter
    0.87
     barrier
    0.84
     barriers
    0.83
     flu
    0.81
     lear
    0.81
    Act Density 0.015%

    No Known Activations