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

    Neuronpedia

    INDEX
    Explanations

    references to online platforms and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     îna
    -1.23
     câte
    -1.19
     gând
    -1.18
     picioare
    -1.17
     maș
    -1.15
     stället
    -1.13
     ་་
    -1.13
     quæ
    -1.12
    seamnă
    -1.12
     виправивши
    -1.11
    POSITIVE LOGITS
     t
    0.90
     o
    0.86
     th
    0.80
     c
    0.79
     s
    0.79
     h
    0.77
     w
    0.76
     d
    0.74
     f
    0.74
     ma
    0.71
    Act Density 2.830%

    No Known Activations