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

    Neuronpedia

    INDEX
    Explanations

    the letter "è" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific accented letters or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.77
    vasive
    -0.76
    assic
    -0.73
    aimon
    -0.72
    enegger
    -0.71
    oted
    -0.67
    assian
    -0.67
    frame
    -0.65
    caps
    -0.65
    oppable
    -0.64
    POSITIVE LOGITS
    vre
    1.18
    ¬
    1.07
    lette
    0.92
    ÃįÃį
    0.84
    ¤
    0.84
    ·
    0.84
    tis
    0.81
    ternity
    0.81
    ħ
    0.80
     é
    0.80
    Act Density 0.007%

    No Known Activations