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

    Neuronpedia

    INDEX
    Explanations

    comparisons of quantities

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases that indicate greater or lesser quantities, frequencies, or efficiencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mand
    -0.83
    dra
    -0.67
    RAW
    -0.64
     Recogn
    -0.61
    rich
    -0.60
    LAN
    -0.59
     Guid
    -0.59
    Wiki
    -0.59
    group
    -0.58
    Af
    -0.58
    POSITIVE LOGITS
     than
    0.83
    acters
    0.75
     Than
    0.73
    enegger
    0.72
     per
    0.71
    illard
    0.70
     heels
    0.67
    itsu
    0.67
    than
    0.66
    poons
    0.66
    Act Density 0.114%

    No Known Activations