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

    Neuronpedia

    INDEX
    Explanations

    adverbs that describe manner or degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adapt
    -0.58
    ècie
    -0.57
    met
    -0.57
    わかった
    -0.56
     поня
    -0.56
    卉
    -0.56
    れた
    -0.55
    れる
    -0.55
    わからない
    -0.54
    出る
    -0.53
    POSITIVE LOGITS
    sively
    2.05
    ously
    1.95
    ently
    1.91
    ically
    1.86
    istically
    1.83
    ificantly
    1.83
    tically
    1.83
    ctively
    1.82
    antly
    1.82
    mically
    1.81
    Act Density 2.794%

    No Known Activations