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

    Neuronpedia

    INDEX
    Explanations

    names or references to individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Br."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AMERICA
    -0.79
    eers
    -0.78
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.77
    æĸ¹
    -0.76
    姫
    -0.72
    ãģŁ
    -0.67
    PLIED
    -0.67
    BOX
    -0.66
    heid
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.63
    POSITIVE LOGITS
    acket
    1.11
    anca
    1.04
    unn
    1.03
    atton
    1.02
    idget
    1.02
    anches
    1.01
    ackets
    1.00
    itt
    0.99
    ings
    0.94
    uns
    0.92
    Act Density 0.007%

    No Known Activations