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

    Neuronpedia

    INDEX
    Explanations

    locations or names containing the word "at."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥ŀ
    -0.82
     Tsukuyomi
    -0.68
    ©¶æ
    -0.66
    SPONSORED
    -0.65
    ppelin
    -0.65
    ADE
    -0.63
     precedent
    -0.63
    士
    -0.59
    vous
    -0.59
    HAM
    -0.58
    POSITIVE LOGITS
    rix
    1.39
    hemat
    1.18
    rices
    1.16
    chers
    1.16
    chell
    1.15
    rice
    1.15
    imes
    1.15
    ting
    1.14
    hetically
    1.13
    ches
    1.12
    Act Density 0.855%

    No Known Activations