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

    Neuronpedia

    INDEX
    Explanations

    French words and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character "é" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.73
    frames
    -0.72
    assic
    -0.72
    ragon
    -0.71
    EStreamFrame
    -0.70
    frame
    -0.69
    idious
    -0.68
    vasive
    -0.68
    aimon
    -0.67
    assian
    -0.67
    POSITIVE LOGITS
    ¬
    1.14
    vre
    1.04
    ·
    1.00
    lette
    0.96
    ħ
    0.95
    ¯¯¯¯
    0.91
    è
    0.89
    µ
    0.87
    ¤
    0.85
     é
    0.84
    Act Density 0.005%

    No Known Activations