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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evidence or examples of specific situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of societal issues and injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MpServer
    -0.74
    atos
    -0.73
    ertation
    -0.73
    ([
    -0.67
     CLSID
    -0.66
    iston
    -0.65
    çļ
    -0.63
     Referred
    -0.63
     <-
    -0.63
    ((
    -0.62
    POSITIVE LOGITS
     imperialism
    0.79
     militar
    0.77
     politic
    0.76
     embattled
    0.76
     sorely
    0.75
     evolving
    0.74
     collaborative
    0.74
    ettel
    0.73
     secretive
    0.72
     enduring
    0.72
    Act Density 0.863%

    No Known Activations