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

    Neuronpedia

    INDEX
    Explanations

    numbers, dates, and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and time-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newsp
    -0.64
     ninety
    -0.60
     metic
    -0.58
     suff
    -0.56
     perspect
    -0.54
    attering
    -0.54
     distingu
    -0.54
     mutually
    -0.52
     ric
    -0.52
    pering
    -0.51
    POSITIVE LOGITS
     6
    1.82
     7
    1.80
     8
    1.57
    7
    1.55
    6
    1.55
     5
    1.43
    8
    1.35
     9
    1.34
    5
    1.15
     4
    1.13
    Act Density 0.238%

    No Known Activations