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

    Neuronpedia

    INDEX
    Explanations

    specific health-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -
    -0.46
     “
    -0.40
     Feind
    -0.38
     Handwerk
    -0.36
     Segen
    -0.36
     Dlatego
    -0.36
     Acerca
    -0.35
     Darum
    -0.34
    ～
    -0.34
     Licht
    -0.33
    POSITIVE LOGITS
     <>",
    0.89
    tagHelperRunner
    0.88
    +#+
    0.84
     betweenstory
    0.77
    ⤹
    0.76
    évaluateur
    0.72
    AddTagHelper
    0.72
     kaarangay
    0.71
    iſen
    0.71
     Савезне
    0.70
    Act Density 0.913%

    No Known Activations