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

    Neuronpedia

    INDEX
    Explanations

    non-standard characters or symbols, often found in languages with diacritics or special typographic characters

    oai_token-act-pair · gpt-4-turbo

    characters from foreign languages

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols or non-standard characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.80
    thumbnails
    -0.70
    htaking
    -0.67
    rals
    -0.66
     tremend
    -0.66
    awaru
    -0.65
     glitches
    -0.64
    iosyn
    -0.64
    generated
    -0.63
    geries
    -0.63
    POSITIVE LOGITS
    ·
    0.78
    Å
    0.75
    °
    0.75
    çİĭ
    0.75
    ó
    0.73
    ±
    0.72
    bis
    0.72
    Ļ
    0.72
    ³
    0.72
    Ĺ
    0.71
    Act Density 0.211%

    No Known Activations