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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks or web addresses

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    —"
    -0.51
    ,—
    -0.51
     cautiously
    -0.50
     âĵĺ
    -0.49
    iyah
    -0.48
     outset
    -0.47
     abruptly
    -0.45
    —
    -0.45
     finally
    -0.44
     Petersen
    -0.43
    POSITIVE LOGITS
    sic
    0.56
     similarities
    0.55
     similarity
    0.52
    other
    0.50
     resemblance
    0.49
    åĮ
    0.49
    Others
    0.48
     english
    0.47
    similar
    0.47
    Interstitial
    0.47
    Act Density 1.468%

    No Known Activations