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

    Neuronpedia

    INDEX
    Explanations

    countries and organizations related to international politics

    oai_token-act-pair · gpt-3.5-turbo

    statements related to the existence or status of entities and actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDENT
    -0.64
    ãĥ´
    -0.60
    ieves
    -0.59
     Salary
    -0.58
    iversary
    -0.58
    ãĥĹ
    -0.55
     Pers
    -0.55
     IMAGES
    -0.55
    ipers
    -0.55
    Rew
    -0.55
    POSITIVE LOGITS
     likewise
    1.51
     meanwhile
    1.36
     similarly
    1.34
     also
    1.14
     unaffected
    1.07
    another
    1.06
     another
    1.04
    Another
    0.93
     additionally
    0.93
    also
    0.90
    Act Density 0.530%

    No Known Activations