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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    plurals of the letter 's'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.67
    icz
    -0.64
     infringement
    -0.62
    EEE
    -0.62
     precon
    -0.61
    ships
    -0.60
     reservation
    -0.60
     congress
    -0.60
     chalk
    -0.59
    âĢ¢âĢ¢
    -0.58
    POSITIVE LOGITS
    ources
    1.14
    nyder
    1.12
    arnaev
    1.10
    ullivan
    1.09
    kaya
    1.00
    inki
    0.98
    atisf
    0.97
    outhern
    0.96
    por
    0.95
    outheast
    0.92
    Act Density 0.054%

    No Known Activations