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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a change or continuation from a past time point

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.75
    immer
    -0.67
    ÙĴ
    -0.66
    natureconservancy
    -0.62
    atron
    -0.61
    amina
    -0.61
    adiator
    -0.60
     lookout
    -0.59
    ymph
    -0.59
    buster
    -0.58
    POSITIVE LOGITS
    rely
    1.61
    ĸļ
    0.75
    rest
    0.75
    pite
    0.71
     inception
    0.70
     October
    0.69
     January
    0.67
     1945
    0.67
     1999
    0.67
     1979
    0.67
    Act Density 0.034%

    No Known Activations