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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty or confusion about current events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to uncertainty or the future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Horus
    -0.73
    rique
    -0.68
    ullah
    -0.67
    cluding
    -0.66
    hold
    -0.65
    picking
    -0.63
    friends
    -0.62
     Sut
    -0.61
    ifle
    -0.60
    ises
    -0.60
    POSITIVE LOGITS
    Ń·
    0.88
    0.77
    ļéĨĴ
    0.75
    lems
    0.75
    ¸
    0.74
     bankrupt
    0.74
    -+
    0.74
    °
    0.73
     overboard
    0.71
    verning
    0.70
    Act Density 0.053%

    No Known Activations