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

    Neuronpedia

    INDEX
    Explanations

    the string "Hu" followed by a single numerical digit

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Hu

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.91
    */(
    -0.85
    Ú
    -0.77
    creen
    -0.77
    ãĥĩãĤ£
    -0.76
    cape
    -0.75
    Interstitial
    -0.74
    ãĥ¼ãĥĨ
    -0.71
     partName
    -0.71
    ãĥĹ
    -0.70
    POSITIVE LOGITS
    awei
    1.32
    lda
    1.18
    anca
    1.06
    bert
    0.96
     Hu
    0.96
    undai
    0.96
    asca
    0.92
    acan
    0.91
    ahah
    0.91
    anan
    0.89
    Act Density 0.014%

    No Known Activations