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

    Neuronpedia

    INDEX
    Explanations

    comparisons indicating an increased quantity or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pants
    -0.34
     lightweight
    -0.34
     Olsson
    -0.34
     wid
    -0.34
     rides
    -0.34
    身后
    -0.33
     nud
    -0.33
    szcz
    -0.33
    blad
    -0.32
     سد
    -0.32
    POSITIVE LOGITS
     than
    0.74
     pinulongan
    0.64
     CreateTagHelper
    0.62
    better
    0.59
     betere
    0.58
     better
    0.57
    UnifiedTopology
    0.56
     lepiej
    0.56
     niż
    0.56
     belangrij
    0.56
    Act Density 0.785%

    No Known Activations