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

    Neuronpedia

    INDEX
    Explanations

    references to scientific terminology and technical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quæ
    -0.69
     فريبيس
    -0.62
    MLLoader
    -0.62
     سكانية
    -0.61
     >=",
    -0.61
    anyahu
    -0.60
     Oso
    -0.59
     Krakowie
    -0.59
     Provenance
    -0.58
    Sneaky
    -0.58
    POSITIVE LOGITS
    AddHtmlAttribute
    0.68
     bang
    0.54
     cure
    0.53
    throughput
    0.51
     Encyclopedia
    0.51
     akrab
    0.50
    /~
    0.49
     pr
    0.45
     fantasy
    0.45
     wizard
    0.44
    Act Density 2.319%

    No Known Activations