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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ohjel
    -0.52
     Polsek
    -0.50
    ungkinkan
    -0.49
    botten
    -0.49
    ?」
    -0.49
     nonUne
    -0.49
     Erfurt
    -0.49
     kasarigan
    -0.49
     Haush
    -0.47
     Forsch
    -0.47
    POSITIVE LOGITS
     forState
    0.55
     на
    0.49
     surla
    0.48
     at
    0.46
    hematical
    0.45
    แก่
    0.44
    Скачать
    0.44
    mappedBy
    0.43
     Chwiliwch
    0.43
     в
    0.42
    Act Density 0.028%

    No Known Activations