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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "deconstruction" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dec" and its variations or derivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inki
    -0.72
    minecraft
    -0.72
    vana
    -0.65
     Galile
    -0.64
    anamo
    -0.61
    utra
    -0.60
    ghan
    -0.59
    adesh
    -0.58
    virt
    -0.58
     Shank
    -0.57
    POSITIVE LOGITS
    ãĤ¼ãĤ¦ãĤ¹
    0.67
    ¬¼
    0.67
    rules
    0.66
    ributed
    0.66
    uration
    0.66
    erence
    0.65
    cision
    0.65
    struction
    0.65
    uve
    0.64
    Ĥİ
    0.62
    Act Density 0.093%

    No Known Activations