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

    Neuronpedia

    INDEX
    Explanations

    phrases related to similarity or repetition

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" used in various contexts, indicating a strong emphasis on specific subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apache
    -0.77
    js
    -0.74
    mares
    -0.74
    berries
    -0.71
     existed
    -0.70
    apons
    -0.69
    adeon
    -0.69
     exists
    -0.69
    advertising
    -0.68
    isco
    -0.67
    POSITIVE LOGITS
     same
    1.10
     easiest
    1.05
     extent
    1.02
     culmination
    1.00
     biggest
    0.98
     safest
    0.97
     gist
    0.95
     longest
    0.95
     largest
    0.95
     toughest
    0.95
    Act Density 0.146%

    No Known Activations