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

    Neuronpedia

    INDEX
    Explanations

    find phrases containing dates or numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" related to context and timing within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oldown
    -0.71
    inion
    -0.70
    Unknown
    -0.69
    catentry
    -0.68
     <+
    -0.68
    oven
    -0.67
     %%
    -0.67
    illary
    -0.67
    izens
    -0.66
    oeuv
    -0.66
    POSITIVE LOGITS
    juries
    1.34
    jury
    1.09
     Week
    1.09
     2014
    1.08
     preseason
    1.07
     2013
    1.05
     2015
    1.04
     2016
    1.00
     2012
    0.99
     lieu
    0.99
    Act Density 0.104%

    No Known Activations