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

    Neuronpedia

    INDEX
    Explanations

    names or words containing "Hu" with various numbers after them

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named "Hu" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.90
    20439
    -0.89
    Interstitial
    -0.80
    Ú
    -0.77
    pmwiki
    -0.75
    creen
    -0.74
    ãĥ¼ãĥĨ
    -0.74
    ãģķ
    -0.73
    ãĥĩãĤ£
    -0.72
    cape
    -0.69
    POSITIVE LOGITS
    awei
    1.30
     Hu
    1.08
    lda
    1.07
    anca
    1.00
    bert
    0.99
    undai
    0.97
    Hu
    0.97
    ahah
    0.90
    acan
    0.88
    illard
    0.87
    Act Density 0.007%

    No Known Activations