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

    Neuronpedia

    INDEX
    Explanations

    prefixes and terms starting with "pre-"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    loo
    -0.74
     Shack
    -0.64
    Ø©
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.63
    IBLE
    -0.62
    ãĤ¼ãĤ¦ãĤ¹
    -0.62
     Heights
    -0.62
    oice
    -0.61
     GOODMAN
    -0.61
     Cup
    -0.60
    POSITIVE LOGITS
    requisites
    1.36
    occup
    1.23
    ceed
    1.21
    fecture
    1.20
    empt
    1.17
    req
    1.17
    hens
    1.15
    requisite
    1.10
    achers
    1.09
    occupied
    1.08
    Act Density 0.256%

    No Known Activations