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

    Neuronpedia

    INDEX
    Explanations

    concepts related to indexes or comparisons of values

    oai_token-act-pair · gpt-3.5-turbo

    references to indexes and their numerical values or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.86
    creen
    -0.73
    soever
    -0.72
    STON
    -0.71
    isSpecialOrderable
    -0.70
     Honour
    -0.70
     behav
    -0.69
    uggage
    -0.68
    overs
    -0.66
    loo
    -0.65
    POSITIVE LOGITS
     mund
    0.91
     index
    0.84
    uated
    0.76
    illary
    0.72
     finger
    0.72
    eus
    0.71
     indexed
    0.71
    ilation
    0.70
    ilated
    0.70
    irection
    0.69
    Act Density 0.023%

    No Known Activations