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

    Neuronpedia

    INDEX
    Explanations

    sentences involving uncertainty or lack of knowledge

    oai_token-act-pair · gpt-3.5-turbo

    statements reflecting uncertainty or indecision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oppers
    -0.72
     exemplary
    -0.68
     denomin
    -0.67
    ielding
    -0.67
     absor
    -0.67
    ievers
    -0.67
     ensured
    -0.66
     mobil
    -0.65
     benefiting
    -0.65
     integral
    -0.64
    POSITIVE LOGITS
     Maybe
    1.09
    maybe
    1.04
     Probably
    1.02
     Honestly
    0.99
     Anyway
    0.95
     maybe
    0.93
     :(
    0.91
     dunno
    0.89
    Maybe
    0.87
    Honestly
    0.87
    Act Density 0.412%

    No Known Activations