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

    Neuronpedia

    INDEX
    Explanations

    expressions related to questioning and uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Erstellt
    -0.59
    EDEFAULT
    -0.59
    lemented
    -0.57
    ARTER
    -0.55
    izzati
    -0.54
    reness
    -0.53
    STERS
    -0.53
     оригинала
    -0.53
    inghouse
    -0.53
    PyExc
    -0.52
    POSITIVE LOGITS
    aarrggbb
    0.72
     Winaray
    0.70
     kasarigan
    0.69
     utafitiHapana
    0.68
     rhestr
    0.65
     ostavi
    0.60
     Roskov
    0.58
     Comprometido
    0.57
    rungsseite
    0.57
     betweenstory
    0.56
    Act Density 1.552%

    No Known Activations