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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pta
    -0.72
    amina
    -0.67
    ÙĴ
    -0.66
    natureconservancy
    -0.65
    ©¶æ¥µ
    -0.63
    ABLE
    -0.63
    ereo
    -0.63
    atron
    -0.60
    adiator
    -0.59
    ashes
    -0.59
    POSITIVE LOGITS
    rely
    1.48
    pite
    0.83
    ĸļ
    0.80
     1979
    0.69
     declass
    0.68
     1981
    0.67
     2006
    0.66
     January
    0.65
     1945
    0.65
     1999
    0.64
    Act Density 0.031%

    No Known Activations