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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty or lack of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or the need for further information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Resist
    -0.69
    die
    -0.68
    bestos
    -0.67
     Dil
    -0.66
    tick
    -0.60
    ilege
    -0.59
    matter
    -0.59
    itton
    -0.59
    ructose
    -0.57
    bia
    -0.56
    POSITIVE LOGITS
     definitively
    0.90
     specifics
    0.88
     nor
    0.79
     conclusive
    0.77
     conflicting
    0.77
     definitive
    0.75
     confir
    0.74
     forthcoming
    0.73
    details
    0.72
     details
    0.72
    Act Density 0.272%

    No Known Activations