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

    Neuronpedia

    INDEX
    Explanations

    references to specific programming concepts or code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.69
    BeginContext
    -0.58
     MainAxisSize
    -0.57
    posedge
    -0.56
     gjø
    -0.50
    inaison
    -0.48
     Descubre
    -0.47
     كومونز
    -0.47
    Kuva
    -0.47
     podjet
    -0.47
    POSITIVE LOGITS
     zui
    0.59
     cj
    0.58
    хьтан
    0.57
     zalo
    0.56
    ApplicationTests
    0.54
     mik
    0.53
     lun
    0.53
     nx
    0.53
    finals
    0.52
    corpions
    0.52
    Act Density 0.024%

    No Known Activations