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

    Neuronpedia

    INDEX
    Explanations

    text written in languages using Cyrillic script

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that represent specific encodings or formatting that are likely non-standard in textual content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sapphire
    -0.68
    ebted
    -0.68
    alities
    -0.65
     Riley
    -0.65
    makers
    -0.63
     Daly
    -0.62
    istically
    -0.59
     Lisp
    -0.59
     fitness
    -0.59
    landish
    -0.58
    POSITIVE LOGITS
    ¿
    1.90
    ³
    1.84
    ±
    1.84
    ·
    1.84
    ¹
    1.74
    1.67
    ļ
    1.59
    ¡
    1.57
    ĺ
    1.50
    ł
    1.50
    Act Density 0.015%

    No Known Activations