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

    Neuronpedia

    INDEX
    Explanations

    references to coding or programming elements, especially those involving underscores and wildcard characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vikipedi
    -0.72
     endforeach
    -0.67
     faſt
    -0.65
     foon
    -0.64
    ViewChild
    -0.62
    tagHelperRunner
    -0.61
    aarrggbb
    -0.61
    NewRow
    -0.60
    LayoutConstraint
    -0.60
    Autoritní
    -0.59
    POSITIVE LOGITS
     damn
    0.62
     entier
    0.60
    (!)
    0.57
     (!)
    0.56
     absolutely
    0.54
     itself
    0.53
     absolument
    0.53
     nữa
    0.52
     (!
    0.52
     really
    0.51
    Act Density 0.142%

    No Known Activations