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

    Neuronpedia

    INDEX
    Explanations

    patterns consisting of a combination of numbers and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoField
    -0.53
    żeli
    -0.49
     Hero
    -0.48
    <eos>
    -0.47
     we
    -0.47
     hero
    -0.46
    FormTagHelper
    -0.46
     call
    -0.46
     so
    -0.45
    ゴリー
    -0.43
    POSITIVE LOGITS
     nahilalakip
    0.84
    MemoryWarning
    0.79
     autorytatywna
    0.74
     bezeichneter
    0.72
    abestanden
    0.71
     \%)
    0.70
    '][$
    0.70
    Personensuche
    0.70
     EconPapers
    0.69
    '])->
    0.68
    Act Density 1.382%

    No Known Activations