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

    Neuronpedia

    INDEX
    Explanations

    bullet points and section separators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -1.16
     autorytatywna
    -1.00
    Personendaten
    -1.00
    tvguidetime
    -0.98
    Билгалдахарш
    -0.97
    sizeCache
    -0.96
    NUMX
    -0.94
     Paglinawan
    -0.93
    withIdentifier
    -0.92
    出版年
    -0.92
    POSITIVE LOGITS
    ↵↵
    0.88
     Furthermore
    0.70
     Also
    0.70
    Furthermore
    0.68
     Moreover
    0.62
    Also
    0.62
    Moreover
    0.61
    ↵
    0.59
     Additionally
    0.53
    .
    0.53
    Act Density 0.088%

    No Known Activations