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

    Neuronpedia

    INDEX
    Explanations

    characters in non-English alphabets

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or names with diacritics or unusual orthography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etts
    -0.91
    enna
    -0.88
    yrus
    -0.85
    artisan
    -0.84
    rils
    -0.82
    patrick
    -0.78
    hens
    -0.77
    ements
    -0.75
    acity
    -0.74
    andestine
    -0.73
    POSITIVE LOGITS
    士
    0.97
    ufact
    0.87
    ãĤ¨ãĥ«
    0.87
    Ü
    0.82
    ``
    0.80
    vous
    0.77
    âĶĢâĶĢ
    0.76
    WithNo
    0.75
    ccording
    0.74
    姫
    0.71
    Act Density 0.035%

    No Known Activations