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

    Neuronpedia

    INDEX
    Explanations

    French phrases or references to programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     budou
    -0.62
     буду
    -0.56
     werde
    -0.55
     budú
    -0.54
     werden
    -0.50
     būtų
    -0.50
     budu
    -0.50
     possam
    -0.48
     będę
    -0.47
     werdet
    -0.47
    POSITIVE LOGITS
    saraba
    0.50
    хьтан
    0.50
    olars
    0.49
    matchCondition
    0.48
     Dryer
    0.47
    tera
    0.46
     Cooker
    0.45
    TERA
    0.42
    chera
    0.41
     Aura
    0.41
    Act Density 0.124%

    No Known Activations