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

    Neuronpedia

    INDEX
    Explanations

    adverbs describing manner or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    al
    -0.88
    b
    -0.72
    z
    -0.71
    p
    -0.71
    l
    -0.71
    tic
    -0.71
    an
    -0.71
    ma
    -0.70
    h
    -0.69
    k
    -0.68
    POSITIVE LOGITS
    ently
    1.49
    sively
    1.47
    denly
    1.39
    cerely
    1.37
    ']")
    1.36
    ously
    1.35
    handedly
    1.35
    ificantly
    1.33
    xically
    1.31
    ALLY
    1.31
    Act Density 0.777%

    No Known Activations