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

    Neuronpedia

    INDEX
    Explanations

    numbers related to statistics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify or specify numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ername
    -0.80
    feeding
    -0.79
    rade
    -0.77
    inking
    -0.77
    nature
    -0.76
    acus
    -0.76
    fort
    -0.75
    forward
    -0.74
    doing
    -0.72
     srfAttach
    -0.72
    POSITIVE LOGITS
     times
    1.14
     entrants
    1.04
     deaths
    1.04
     occasions
    1.03
     days
    1.00
     fatalities
    0.99
     occurrences
    0.99
     people
    0.99
     households
    0.98
     vacancies
    0.97
    Act Density 0.074%

    No Known Activations