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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of software or programming concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    inghouse
    -0.70
     myſelf
    -0.69
     diſt
    -0.69
     ſtate
    -0.68
     itſelf
    -0.68
     greateſt
    -0.67
     deſt
    -0.66
    ustimmung
    -0.65
     Reſ
    -0.65
     cauſe
    -0.65
    POSITIVE LOGITS
    OGND
    0.60
    MENAFN
    0.57
    complexContent
    0.55
     aload
    0.53
    Tembelea
    0.52
     Cok
    0.50
    énario
    0.49
     hombros
    0.49
    tagext
    0.48
     depan
    0.46
    Act Density 0.003%

    No Known Activations