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

    Neuronpedia

    INDEX
    Explanations

    occurrences of quotes or references to quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erness
    -0.18
    deer
    -0.16
    weg
    -0.16
    raci
    -0.15
    å½¹
    -0.15
    ement
    -0.15
    eview
    -0.15
     ruk
    -0.14
    785
    -0.14
    amiento
    -0.14
    POSITIVE LOGITS
    -worthy
    0.18
     Generator
    0.17
     generation
    0.17
     generators
    0.16
    hoot
    0.16
    ãĥ¥
    0.16
     generator
    0.16
    Generator
    0.16
    eded
    0.16
    URE
    0.15
    Act Density 0.152%

    No Known Activations