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

    Neuronpedia

    INDEX
    Explanations

    phrases related to excessive quantities or repetitive themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    λικά
    -0.33
    moveToFirst
    -0.31
    Hochspringen
    -0.29
     resultar
    -0.29
     slik
    -0.29
    しかない
    -0.28
    関連リンク
    -0.28
    niosek
    -0.28
     purposes
    -0.28
    Див
    -0.28
    POSITIVE LOGITS
    crow
    0.69
    worked
    0.68
    weight
    0.68
    whelmed
    0.67
    whelming
    0.66
    sized
    0.66
    powering
    0.66
    sight
    0.64
    rated
    0.63
    priced
    0.63
    Act Density 0.197%

    No Known Activations