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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to weights and dimensions

    oai_token-act-pair · gpt-3.5-turbo

    measurements and specifications related to weight and capacity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kus
    -0.64
    issance
    -0.62
    plet
    -0.62
    rique
    -0.61
    thia
    -0.61
    iership
    -0.61
    alus
    -0.61
    ĪĴ
    -0.59
    vell
    -0.59
    rete
    -0.58
    POSITIVE LOGITS
     varies
    1.14
    :
    1.09
    *:
    0.95
     =
    0.94
    %:
    0.90
     :
    0.89
     TBD
    0.88
    :'
    0.87
     Range
    0.86
    =$
    0.86
    Act Density 0.174%

    No Known Activations