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

    Neuronpedia

    INDEX
    Explanations

    references to various industries

    oai_token-act-pair · gpt-3.5-turbo

    references to various industries and their characteristics or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     omission
    -0.78
     cuff
    -0.67
     apologise
    -0.67
    tein
    -0.65
     swear
    -0.64
     scrolls
    -0.64
     deletion
    -0.64
     deeds
    -0.63
    terday
    -0.63
     delet
    -0.63
    POSITIVE LOGITS
     booming
    1.21
     thriving
    1.08
     flourishing
    1.07
     flourished
    1.03
     dominated
    1.00
     stagn
    0.94
     prosper
    0.92
     fragmented
    0.89
    growing
    0.87
     thri
    0.86
    Act Density 0.391%

    No Known Activations