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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with the prefix "Pre"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Pre" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥīãĥ©ãĤ´ãĥ³
    -0.94
    è¦ļéĨĴ
    -0.75
    å°Ĩ
    -0.73
    IBLE
    -0.72
    loo
    -0.71
     GOODMAN
    -0.70
    ãĤ¼ãĤ¦ãĤ¹
    -0.69
    oice
    -0.69
    owship
    -0.68
    ibility
    -0.66
    POSITIVE LOGITS
    cision
    1.09
    hend
    1.07
    requisite
    1.06
    requisites
    1.01
    fecture
    0.99
    achy
    0.96
    fect
    0.95
    empt
    0.94
    hens
    0.93
    acher
    0.91
    Act Density 0.014%

    No Known Activations