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

    Neuronpedia

    INDEX
    Explanations

    words related to legal and political matters

    oai_token-act-pair · gpt-3.5-turbo

    prefixes and suffixes associated with various terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kush
    -1.03
     Lizard
    -0.80
    Reloaded
    -0.79
     Mara
    -0.78
     Shutterstock
    -0.76
     Moose
    -0.76
     Nek
    -0.74
    kson
    -0.73
     Minotaur
    -0.73
     Norn
    -0.73
    POSITIVE LOGITS
    enary
    1.01
    ial
    0.98
    icial
    0.97
    ials
    0.96
    ciplinary
    0.96
    iple
    0.96
    ciation
    0.94
    ciples
    0.94
    ference
    0.90
    unal
    0.88
    Act Density 0.120%

    No Known Activations