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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and letter combinations

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.83
     cumbers
    -0.77
    quartered
    -0.75
    undreds
    -0.75
    eatures
    -0.74
     carbohyd
    -0.73
     entreprene
    -0.72
    conservancy
    -0.70
     endors
    -0.69
    catentry
    -0.68
    POSITIVE LOGITS
     0
    1.23
     2
    1.02
     1
    1.02
     3
    1.01
     4
    0.96
     5
    0.83
    66666666
    0.81
     6
    0.78
     TOTAL
    0.76
     7
    0.76
    Act Density 0.028%

    No Known Activations