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

    Neuronpedia

    INDEX
    Explanations

    references to measurements, counts, or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     оригіналу
    -0.66
    ("]");
    -0.65
     uhr
    -0.61
    irtschaft
    -0.60
    ]").
    -0.60
    )\}$
    -0.59
    ④
    -0.58
    írus
    -0.57
     ]}
    -0.55
     autorytatywna
    -0.55
    POSITIVE LOGITS
    zzleHttp
    0.69
    GenerationType
    0.68
     فريبيس
    0.66
    tencent
    0.65
    ArrowToggle
    0.63
     száz
    0.62
    afficheront
    0.60
     Ten
    0.59
    fortawesome
    0.59
    titleMargin
    0.58
    Act Density 0.551%

    No Known Activations