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

    Neuronpedia

    INDEX
    Explanations

    large numerical values, specifically related to money, taxes, and statistics

    oai_token-act-pair · gpt-3.5-turbo

    financial figures and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >:
    -0.56
    gewater
    -0.53
     Encyclopedia
    -0.53
    .):
    -0.53
    look
    -0.53
     Hancock
    -0.53
     -----
    -0.52
     Druid
    -0.50
    Overview
    -0.50
    Labor
    -0.50
    POSITIVE LOGITS
     thereafter
    1.17
     respectively
    0.83
     afterward
    0.82
     when
    0.76
     apiece
    0.75
     if
    0.74
     versa
    0.74
     for
    0.72
     afterwards
    0.71
     during
    0.70
    Act Density 0.227%

    No Known Activations