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

    Neuronpedia

    INDEX
    Explanations

    the preposition "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     for
    -0.18
     dafür
    -0.16
    jee
    -0.15
     için
    -0.15
     untuk
    -0.15
    erta
    -0.14
    ties
    -0.14
     für
    -0.14
    λει
    -0.14
     για
    -0.14
    POSITIVE LOGITS
     sake
    0.45
     purposes
    0.38
    bidden
    0.33
    aging
    0.32
    geries
    0.31
     instance
    0.31
    -profit
    0.31
    ays
    0.26
    ges
    0.26
    king
    0.26
    Act Density 0.733%

    No Known Activations