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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals and government officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Victorian
    -0.19
    ï¼Īå¹³æĪIJ
    -0.19
    201
    -0.17
    Û±Û¹Û¹
    -0.16
    187
    -0.15
    199
    -0.15
    Û²Û°Û±
    -0.15
    utherford
    -0.15
    elems
    -0.15
     Nano
    -0.14
    POSITIVE LOGITS
    196
    0.54
    195
    0.45
    197
    0.39
    ï¼ĪæĺŃåĴĮ
    0.32
    Û±Û¹Û¶
    0.30
     USSR
    0.29
    194
    0.27
     Soviet
    0.26
    Û±Û¹Ûµ
    0.23
     Ð¡Ð¡Ð¡Ðł
    0.23
    Act Density 1.390%

    No Known Activations