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

    Neuronpedia

    INDEX
    Explanations

    references to the use of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "use" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barg
    -0.69
     aber
    -0.62
     Vie
    -0.59
     Zur
    -0.58
     Aber
    -0.58
     Beir
    -0.57
     Sandwich
    -0.57
     Bert
    -0.57
     Empires
    -0.57
     Emir
    -0.57
    POSITIVE LOGITS
    fulness
    1.22
    fully
    1.20
    FUL
    1.12
    ful
    1.02
    full
    1.00
    nels
    0.86
    ability
    0.83
    onomy
    0.82
    ables
    0.81
    ivation
    0.79
    Act Density 0.042%

    No Known Activations