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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating past habits or repeated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kılıf
    -0.64
     habet
    -0.61
     ſtate
    -0.60
     exceptionnelle
    -0.59
     énergé
    -0.59
    {@
    -0.58
     addObject
    -0.58
     työn
    -0.58
     énergétique
    -0.58
     contributo
    -0.57
    POSITIVE LOGITS
    adays
    0.91
     früher
    0.86
    AsUp
    0.86
    昔
    0.81
     раньше
    0.79
     ehem
    0.78
     vroeger
    0.78
     olden
    0.75
     محفوظة
    0.74
     formerly
    0.74
    Act Density 0.070%

    No Known Activations