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

    Neuronpedia

    INDEX
    Explanations

    keywords denoting uncertainty or open possibilities

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite pronoun "any."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rex
    -0.76
    rez
    -0.69
     Alps
    -0.66
     Trib
    -0.64
    pees
    -0.61
    lymp
    -0.60
    romy
    -0.58
    bows
    -0.58
    staking
    -0.57
    DA
    -0.57
    POSITIVE LOGITS
    THING
    1.29
    body
    1.23
    where
    1.22
    WHERE
    0.98
    how
    0.84
    etheless
    0.78
    ways
    0.77
    thin
    0.76
    ONE
    0.76
     conceivable
    0.74
    Act Density 0.049%

    No Known Activations