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

    Neuronpedia

    INDEX
    Explanations

    the accented letter "è"

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific accented characters or symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ording
    -0.76
    aimon
    -0.75
    utterstock
    -0.73
    assic
    -0.73
    assian
    -0.72
    ragon
    -0.70
    itation
    -0.70
    itations
    -0.70
    icult
    -0.69
    vasive
    -0.68
    POSITIVE LOGITS
    vre
    1.10
    ¬
    1.01
    ·
    0.87
    lette
    0.86
    sin
    0.81
    tis
    0.78
    sts
    0.77
     é
    0.77
    µ
    0.75
    ij
    0.75
    Act Density 0.012%

    No Known Activations