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

    Neuronpedia

    INDEX
    Explanations

    a variety of different characters and symbols in the text, possibly related to a specific type of encoding or language

    oai_token-act-pair · gpt-3.5-turbo

    unique or rare symbols and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sidx
    -0.54
     GOODMAN
    -0.54
    anwhile
    -0.52
    staking
    -0.51
     scraping
    -0.50
     convol
    -0.50
     suspic
    -0.49
    ccording
    -0.49
     warranties
    -0.48
     turnout
    -0.48
    POSITIVE LOGITS
    âĢİ
    0.70
    ilet
    0.61
    ensis
    0.61
    ihara
    0.59
    Herm
    0.58
    renheit
    0.58
    pic
    0.55
    çļĦ
    0.54
    ii
    0.52
    LI
    0.51
    Act Density 0.400%

    No Known Activations