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

    Neuronpedia

    INDEX
    Explanations

    stings of multiple letters ending in 'es'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´
    -0.66
    éĹĺ
    -0.64
     shortened
    -0.63
     commissions
    -0.62
    nels
    -0.58
     evenings
    -0.58
    ãĤ´ãĥ³
    -0.56
     apprehension
    -0.56
     referrals
    -0.56
     Akira
    -0.56
    POSITIVE LOGITS
    arsity
    1.40
    oodoo
    1.34
    ulture
    1.30
    anguard
    1.25
    iking
    1.13
    andals
    1.13
    ult
    1.11
    iii
    1.10
    alkyrie
    1.10
    itals
    1.09
    Act Density 0.035%

    No Known Activations