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

    Neuronpedia

    INDEX
    Explanations

    names with accents or special characters

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols in the text, likely related to encoding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.76
    Downloadha
    -0.70
     guiActiveUnfocused
    -0.67
    urst
    -0.65
     buckle
    -0.65
    ible
    -0.64
     Elm
    -0.63
    nut
    -0.63
     seeded
    -0.62
    owed
    -0.62
    POSITIVE LOGITS
    ÃŃ
    1.05
    ¢
    0.98
    ð
    0.92
    Ãī
    0.87
    ternity
    0.85
    lean
    0.85
    Å
    0.81
    Ãį
    0.81
    án
    0.80
    á
    0.80
    Act Density 0.007%

    No Known Activations