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

    Neuronpedia

    INDEX
    Explanations

    mentions of the name "Lamb" with a stronger preference for mentions where the word is followed by 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    references to an individual named Lamb

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PLIED
    -0.81
     Subtle
    -0.76
    ãģ¦
    -0.66
    Downloadha
    -0.66
     Kindle
    -0.66
    ×Ļ×
    -0.65
     ignorance
    -0.64
    BOOK
    -0.63
     pac
    -0.62
     beware
    -0.62
    POSITIVE LOGITS
    da
    1.02
    rop
    0.95
    din
    0.91
    alle
    0.91
    ont
    0.91
    onde
    0.88
    alo
    0.88
    inate
    0.87
     Lamb
    0.87
    loo
    0.87
    Act Density 0.007%

    No Known Activations