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

    Neuronpedia

    INDEX
    Explanations

    instances of specific characters or symbols in the text, particularly accents and typographical marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abelle
    -0.17
     at
    -0.17
    enton
    -0.16
    cts
    -0.15
    ering
    -0.15
    ito
    -0.15
    ingham
    -0.15
    ager
    -0.15
    oup
    -0.15
     Kauf
    -0.15
    POSITIVE LOGITS
     partir
    0.22
     travers
    0.20
     la
    0.18
     propos
    0.18
     titre
    0.17
    ylan
    0.17
     tort
    0.16
    rox
    0.16
     cause
    0.15
    ussy
    0.15
    Act Density 0.008%

    No Known Activations