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

    Neuronpedia

    INDEX
    Explanations

    specific Unicode or special characters, possibly related to non-English text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Choi
    -0.17
    KI
    -0.17
    .deb
    -0.15
    YO
    -0.15
    etter
    -0.15
    OOM
    -0.14
    blick
    -0.14
    umas
    -0.14
    oric
    -0.14
    struction
    -0.14
    POSITIVE LOGITS
    icao
    0.20
     Bian
    0.20
    Çİ
    0.19
    'er
    0.18
    Ç
    0.17
    angling
    0.17
    xi
    0.17
    angu
    0.17
     Fen
    0.17
    lish
    0.17
    Act Density 0.038%

    No Known Activations