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

    Neuronpedia

    INDEX
    Explanations

    names of specific locations, individuals, and organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.84
    CLASS
    -0.80
    nah
    -0.74
    wt
    -0.73
    ITNESS
    -0.73
    ochond
    -0.71
    ipeg
    -0.71
    krit
    -0.70
    inburgh
    -0.68
     glim
    -0.68
    POSITIVE LOGITS
    zzi
    1.22
     Gomez
    1.07
     Gonzalez
    1.07
    ño
    1.05
    elli
    1.03
    zza
    1.00
     Grande
    0.96
     Gutierrez
    0.96
     Aires
    0.95
    osa
    0.95
    Act Density 0.236%

    No Known Activations