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

    Neuronpedia

    INDEX
    Explanations

    quantitative comparisons

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases related to quantities and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DL
    -0.64
    ocy
    -0.63
     seriousness
    -0.60
    Introdu
    -0.59
    beh
    -0.59
     derog
    -0.58
     Penal
    -0.58
    iber
    -0.58
    iatrics
    -0.57
    Attempts
    -0.56
    POSITIVE LOGITS
     tripled
    1.19
     doubled
    1.16
     quadru
    1.08
     doubling
    1.05
     double
    1.03
     twice
    0.99
     triple
    0.98
    thirds
    0.87
     half
    0.84
     600
    0.80
    Act Density 0.130%

    No Known Activations