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

    Neuronpedia

    INDEX
    Explanations

    phrases related to introductions and introductory language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ma
    -0.72
    na
    -0.67
    m
    -0.65
    mathsf
    -0.64
     Gü
    -0.64
    mo
    -0.63
    5
    -0.62
     Vegas
    -0.61
    iritual
    -0.61
     m
    -0.60
    POSITIVE LOGITS
     Introduce
    2.11
     introduction
    2.11
     introductions
    2.05
     introduce
    2.02
     introduces
    2.01
     introducing
    1.93
     Introdu
    1.92
    introduce
    1.92
    Introduce
    1.89
     introdu
    1.88
    Act Density 0.050%

    No Known Activations