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

    Neuronpedia

    INDEX
    Explanations

    percentages or numerical figures with a higher degree of change or growth

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to percentages and statistical changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tools
    -0.62
     fame
    -0.61
     secrets
    -0.60
     instruments
    -0.60
     Rica
    -0.60
     adultery
    -0.59
     guts
    -0.59
     antagonists
    -0.59
     frameworks
    -0.58
     grounds
    -0.58
    POSITIVE LOGITS
    %-
    1.19
    -
    0.97
    fold
    0.88
    th
    0.88
    minute
    0.86
    %
    0.85
     percent
    0.82
    taboola
    0.81
    -,
    0.79
    percent
    0.79
    Act Density 0.128%

    No Known Activations