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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governmental and political entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "data"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.66
    paren
    -0.66
    Ö¼
    -0.65
    tails
    -0.65
    ãĤ©
    -0.63
     Ghosts
    -0.61
    stery
    -0.61
    ONSORED
    -0.61
     convict
    -0.59
     CBO
    -0.57
    POSITIVE LOGITS
    ña
    1.10
    ñ
    1.02
    illon
    1.02
    hedral
    0.99
    ño
    0.95
    hea
    0.94
    eus
    0.90
    eva
    0.89
    onga
    0.87
    ppa
    0.87
    Act Density 0.046%

    No Known Activations