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

    Neuronpedia

    INDEX
    Explanations

    phrases related to company activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or commas in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.59
    miah
    -0.57
    jured
    -0.56
    ls
    -0.56
    ivity
    -0.56
    gow
    -0.55
    roup
    -0.53
    ulent
    -0.53
    isode
    -0.53
    -,
    -0.52
    POSITIVE LOGITS
     respectively
    1.27
     whichever
    1.01
    depending
    0.95
     albeit
    0.93
     depending
    0.92
     thereby
    0.91
     lest
    0.83
     culminating
    0.81
     resulting
    0.81
     despite
    0.80
    Act Density 0.352%

    No Known Activations