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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of dates in years

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢij
    -0.72
    arry
    -0.71
    craft
    -0.68
    acy
    -0.63
    /
    -0.61
    hd
    -0.61
     varies
    -0.59
     persists
    -0.58
     exceeds
    -0.57
    pers
    -0.57
    POSITIVE LOGITS
     same
    1.23
     latter
    1.21
     latest
    1.12
     entire
    1.10
     aforementioned
    1.04
     largest
    1.02
     entirety
    1.00
     remainder
    0.98
     fastest
    0.97
     hottest
    0.94
    Act Density 0.639%

    No Known Activations