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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating relationships or combinations between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mourir
    -0.62
     neuve
    -0.61
     vectorielles
    -0.61
     étoient
    -0.58
    independent
    -0.58
    multer
    -0.57
     auroit
    -0.57
     prisonniers
    -0.56
     indépendante
    -0.55
     feroit
    -0.55
    POSITIVE LOGITS
    matchCondition
    0.70
    انجليز
    0.54
    一方で
    0.50
     arşivlendi
    0.49
    .(*
    0.48
    ✭
    0.48
    emus
    0.47
    却又
    0.47
    Accessors
    0.47
    StackSize
    0.47
    Act Density 0.460%

    No Known Activations