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

    Neuronpedia

    INDEX
    Explanations

    occurrences of specific numeric values and their relationships within a context involving quantities and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.01
     للمعارف
    -1.00
     חיצוניים
    -0.99
     تانيه
    -0.90
     विश्वसनीयता
    -0.85
     للاسماء
    -0.84
     ***!
    -0.84
     kasarigan
    -0.81
    Diweddarwch
    -0.74
     ་་
    -0.71
    POSITIVE LOGITS
     
    0.58
    BindView
    0.57
     cielos
    0.55
     sauvage
    0.51
     $
    0.47
     sauvages
    0.46
    arXiv
    0.46
    minecraftforge
    0.45
    Portail
    0.45
     high
    0.43
    Act Density 0.613%

    No Known Activations