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

    Neuronpedia

    INDEX
    Explanations

    large numerical values, such as monetary amounts

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to financial figures and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \":
    -0.62
    icter
    -0.58
    hod
    -0.55
    Catalog
    -0.55
    "]=>
    -0.54
     Liver
    -0.53
    "))
    -0.53
    lessly
    -0.52
    comes
    -0.52
     resemb
    -0.52
    POSITIVE LOGITS
     midway
    0.88
     amid
    0.85
     by
    0.83
     shortly
    0.81
     after
    0.78
     today
    0.78
     apiece
    0.77
     before
    0.76
     amidst
    0.75
     again
    0.75
    Act Density 0.175%

    No Known Activations