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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the word "keep"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "ke" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.88
    displayText
    -0.77
    ãĥ´ãĤ¡
    -0.77
    naire
    -0.71
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    Ùħ
    -0.70
    IONS
    -0.67
    PsyNetMessage
    -0.67
    姫
    -0.66
    MpServer
    -0.66
    POSITIVE LOGITS
    erk
    1.04
    eling
    1.00
    jriwal
    0.96
    eter
    0.92
    ez
    0.92
    ller
    0.87
    pler
    0.87
    vel
    0.85
    pper
    0.85
    eding
    0.84
    Act Density 0.006%

    No Known Activations