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

    Neuronpedia

    INDEX
    Explanations

    key phrases indicating a change or event occurring at a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    the word "Since" followed by a value indicating time, suggesting a focus on historical context or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.74
    immer
    -0.63
    igans
    -0.62
    Si
    -0.61
    adiator
    -0.60
    alian
    -0.58
    amina
    -0.58
    pta
    -0.58
    ©¶æ¥µ
    -0.57
     lookout
    -0.57
    POSITIVE LOGITS
    rely
    1.80
     inception
    0.93
     1999
    0.85
     2006
    0.83
     1979
    0.83
     1995
    0.83
     1981
    0.81
     2009
    0.81
     2005
    0.81
     2007
    0.81
    Act Density 0.041%

    No Known Activations