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

    Neuronpedia

    INDEX
    Explanations

    words that contain non-standard characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    specific characters or symbols in text, particularly unusual or non-standard ones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.67
     eclips
    -0.62
     bund
    -0.62
     enriched
    -0.61
     hurd
    -0.61
    otrop
    -0.60
     hasht
    -0.60
     android
    -0.60
    oids
    -0.59
    acity
    -0.58
    POSITIVE LOGITS
    ï¸ı
    0.99
    ¯
    0.99
    ï¸
    0.97
    ternity
    0.95
    Vers
    0.89
    ¢
    0.89
    te
    0.85
    dust
    0.83
    sand
    0.83
    should
    0.83
    Act Density 0.024%

    No Known Activations