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

    Neuronpedia

    INDEX
    Explanations

    male first names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and significant references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Sharp
    -0.70
    ©¶æ¥µ
    -0.68
    ................................
    -0.68
    ãĤ¤ãĥĪ
    -0.65
    MpServer
    -0.65
    marked
    -0.63
    angering
    -0.63
    probably
    -0.63
    lime
    -0.62
    acceptable
    -0.62
    POSITIVE LOGITS
     debuted
    1.03
     arrived
    1.00
     first
    0.99
     arrives
    0.99
     asked
    0.96
     enters
    0.94
     approached
    0.94
     finally
    0.92
     inquired
    0.90
     premiered
    0.88
    Act Density 0.239%

    No Known Activations