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

    Neuronpedia

    INDEX
    Explanations

    number patterns represented as sequences of three connected numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data in specific contexts, likely related to scores or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jarring
    -0.68
     mete
    -0.67
     genuine
    -0.66
     waning
    -0.65
     obvious
    -0.65
     consum
    -0.65
     mature
    -0.64
     treat
    -0.64
     glaring
    -0.64
     audience
    -0.64
    POSITIVE LOGITS
    0
    1.16
    1
    1.15
    2
    1.05
    3
    1.03
    5
    1.00
    Switch
    0.95
    4
    0.95
    8
    0.93
    7
    0.92
    quart
    0.90
    Act Density 0.065%

    No Known Activations