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

    Neuronpedia

    INDEX
    Explanations

    IP addresses and numerical sequences

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and specific formats related to data or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onse
    -0.64
    anchester
    -0.62
    ieth
    -0.61
     downs
    -0.60
    arer
    -0.60
    Dat
    -0.59
     approving
    -0.58
    Writ
    -0.58
     scrut
    -0.58
     garn
    -0.57
    POSITIVE LOGITS
     istg
    0.80
     partName
    0.70
    Ļ½
    0.68
     Fiat
    0.67
     Trave
    0.64
     Barrier
    0.63
     Lua
    0.62
     Territory
    0.62
     Collider
    0.61
     Cellular
    0.61
    Act Density 0.118%

    No Known Activations