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

    Neuronpedia

    INDEX
    Explanations

    adverbs that describe the manner or intensity of actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    al
    -0.88
    p
    -0.81
    b
    -0.79
    k
    -0.77
    ma
    -0.76
    z
    -0.76
    l
    -0.75
    ck
    -0.74
    us
    -0.73
    an
    -0.72
    POSITIVE LOGITS
    sively
    1.45
    ently
    1.43
    ']")
    1.42
    cerely
    1.41
    denly
    1.39
    ificantly
    1.37
    ALLY
    1.37
    Autoritní
    1.34
    atically
    1.33
    tically
    1.31
    Act Density 0.589%

    No Known Activations