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

    Neuronpedia

    INDEX
    Explanations

    numeric values related to monetary amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific numerical values, particularly those associated with monetary amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scra
    -0.68
    phia
    -0.67
    llo
    -0.61
     flock
    -0.59
     traveller
    -0.58
     blessing
    -0.57
     curly
    -0.57
     cohesive
    -0.57
     toe
    -0.57
     dispar
    -0.56
    POSITIVE LOGITS
    40
    3.23
    50
    2.22
    60
    2.19
    80
    2.14
    30
    2.12
    70
    2.10
    20
    2.08
    41
    2.06
    45
    2.03
    39
    2.00
    Act Density 0.019%

    No Known Activations