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

    Neuronpedia

    INDEX
    Explanations

    references to social behavior, including conflicts and interactions within various groups

    oai_token-act-pair · gpt-3.5-turbo

    instances of social conflict and public behavior topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     newcomer
    -0.65
    ĪĴ
    -0.65
    orney
    -0.64
     transpired
    -0.63
    anse
    -0.63
    éŃĶ
    -0.63
    ipient
    -0.62
     continued
    -0.62
     resumed
    -0.62
    å¼
    -0.61
    POSITIVE LOGITS
     everywhere
    1.29
     alot
    1.20
     nowadays
    1.20
     everyday
    1.16
     EVERY
    1.09
     constantly
    1.06
     sometimes
    1.01
     whenever
    1.00
     every
    0.98
     indiscrim
    0.97
    Act Density 0.673%

    No Known Activations