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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate inclusivity or references to groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     réguli
    -0.67
     greateſt
    -0.63
     noires
    -0.55
     Flü
    -0.54
     litté
    -0.53
     automatiques
    -0.53
     Gine
    -0.53
     Cedric
    -0.52
     équilibr
    -0.52
     neceffary
    -0.52
    POSITIVE LOGITS
     đều
    0.90
    FormTagHelper
    0.79
    MLLoader
    0.78
     gynhyrchwyd
    0.71
    ItemLayout
    0.69
    LayoutStyle
    0.67
    govina
    0.66
    IANGLES
    0.65
     Picchu
    0.64
    욱
    0.63
    Act Density 0.223%

    No Known Activations