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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to statistics or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beaut
    -0.65
     parach
    -0.62
     liberation
    -0.57
     Rhodes
    -0.55
     perfection
    -0.52
     adventurer
    -0.51
     embattled
    -0.51
     suppressed
    -0.51
     advis
    -0.51
     pandemonium
    -0.51
    POSITIVE LOGITS
    0
    1.48
    5
    1.47
    8
    1.43
    9
    1.42
    6
    1.41
    3
    1.40
    4
    1.40
    7
    1.37
    2
    1.36
    1
    1.29
    Act Density 0.066%

    No Known Activations