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

    Neuronpedia

    INDEX
    Explanations

    complex phrases containing a mix of words related to ownership, government, investigation techniques, cultural institutions, legal concepts, economics, and historical backgrounds

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various social, political, and economic issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     oneself
    -0.80
    estern
    -0.72
     Ack
    -0.66
     Cary
    -0.65
     Almighty
    -0.65
     Hond
    -0.64
     extrad
    -0.63
     Cran
    -0.61
     Cox
    -0.61
     Hess
    -0.60
    POSITIVE LOGITS
     counterparts
    0.90
     counterpart
    0.84
     woes
    0.80
     cousins
    0.74
     moniker
    0.71
     selves
    0.70
     predicament
    0.67
     antics
    0.65
    </
    0.64
    milo
    0.64
    Act Density 0.658%

    No Known Activations