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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating uncertainty or lack of specification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tenance
    -0.74
    saf
    -0.72
    ãĤ£
    -0.68
    how
    -0.67
    ould
    -0.66
    leen
    -0.65
    Ô
    -0.65
     manag
    -0.65
    ERG
    -0.65
    WAY
    -0.63
    POSITIVE LOGITS
     necessarily
    1.20
     formally
    1.12
     overtly
    1.12
     explicitly
    1.09
     outright
    1.07
     directly
    1.06
     definitive
    1.02
     definitively
    1.01
     exact
    1.00
     conclusive
    0.98
    Act Density 0.476%

    No Known Activations