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

    Neuronpedia

    INDEX
    Explanations

    references to protests and activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bracket
    -0.14
    eral
    -0.14
    532
    -0.14
    forcements
    -0.14
     Stam
    -0.13
    Segue
    -0.13
     Drawer
    -0.13
    andom
    -0.13
    idget
    -0.12
    ÐĤ
    -0.12
    POSITIVE LOGITS
     plac
    0.27
     signs
    0.27
     posters
    0.24
     banners
    0.23
     slogans
    0.22
     eff
    0.21
     homemade
    0.20
     banner
    0.20
     Stars
    0.19
     sign
    0.19
    Act Density 0.122%

    No Known Activations