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

    Neuronpedia

    INDEX
    Explanations

    dimensions of chart areas and boxes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    érience
    -0.61
     parson
    -0.58
     Kristine
    -0.58
    ค์
    -0.57
    الحياه
    -0.57
    namentales
    -0.56
     Fara
    -0.56
     capitaine
    -0.55
    setVerticalGroup
    -0.55
     wireType
    -0.54
    POSITIVE LOGITS
    Width
    0.79
    rein
    0.57
    Referencie
    0.57
     reinforce
    0.57
     rein
    0.56
     racing
    0.55
     traders
    0.54
     kasarigan
    0.54
    AddTagHelper
    0.54
     Económica
    0.53
    Act Density 0.068%

    No Known Activations