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

    Neuronpedia

    INDEX
    Explanations

    adverbs modifying actions, often emphasizing manner, frequency, or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    al
    -0.77
     Adapt
    -0.69
    z
    -0.66
    an
    -0.65
     Amad
    -0.65
    ck
    -0.63
    us
    -0.60
    r
    -0.60
     Wulf
    -0.60
     hals
    -0.59
    POSITIVE LOGITS
    ']")
    1.31
    ently
    1.30
    sively
    1.29
    denly
    1.28
    handedly
    1.22
    )";
    1.22
    "]),
    1.21
    '):
    1.20
    quely
    1.18
    "])
    1.17
    Act Density 0.642%

    No Known Activations