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

    Neuronpedia

    INDEX
    Explanations

    uncertainty or generality in texts, as it is triggered by phrases indicating a lack of commitment to a specific idea

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schild
    -0.72
    locks
    -0.68
    ãĥĸ
    -0.67
    nas
    -0.63
    CLOSE
    -0.63
     Gong
    -0.62
    aceae
    -0.61
    iov
    -0.61
    bid
    -0.61
     Rumble
    -0.61
    POSITIVE LOGITS
     happens
    0.77
    etheless
    0.67
     consistency
    0.65
    uthor
    0.64
     cohesion
    0.64
    istrate
    0.63
     regress
    0.62
    assador
    0.62
    /(
    0.61
     else
    0.60
    Act Density 0.043%

    No Known Activations