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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal proceedings or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     monop
    -0.79
     chained
    -0.73
     shack
    -0.70
     mixed
    -0.68
     multiplying
    -0.66
     machine
    -0.65
     floating
    -0.65
     sor
    -0.65
     gum
    -0.64
     backdoor
    -0.64
    POSITIVE LOGITS
    ĸļ
    0.98
    º
    0.93
    į
    0.88
    £
    0.86
    terness
    0.83
    cipline
    0.81
    ®
    0.81
    ¹
    0.81
    »
    0.80
    agree
    0.80
    Act Density 0.210%

    No Known Activations