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

    Neuronpedia

    INDEX
    Explanations

    the prefix "am-" which is present in words

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     concession
    -0.66
     aver
    -0.65
     takeaway
    -0.64
    DragonMagazine
    -0.64
     Clause
    -0.61
    mining
    -0.60
     kinderg
    -0.60
     discretionary
    -0.58
     gorilla
    -0.58
     targ
    -0.58
    POSITIVE LOGITS
    ethyst
    1.34
    ateurs
    1.30
    azon
    1.28
    sterdam
    1.22
    assing
    1.12
    ajor
    1.11
    icable
    1.11
    nesia
    1.08
    essage
    1.06
    azes
    1.02
    Act Density 0.028%

    No Known Activations