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

    Neuronpedia

    INDEX
    Explanations

    phrases related to critique and analysis of societal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ennen
    -0.16
    олеÑĤ
    -0.15
     labeled
    -0.15
    ilden
    -0.14
     Jacqu
    -0.14
    hind
    -0.14
    arov
    -0.14
     hypoth
    -0.14
    леÑĤ
    -0.14
     REL
    -0.14
    POSITIVE LOGITS
    оÑĤов
    0.18
    UNET
    0.16
     BUF
    0.15
     jour
    0.14
    alÄ±ÅŁ
    0.14
    ISC
    0.14
    uras
    0.14
     zase
    0.14
     tá»
    0.13
    uzzi
    0.13
    Act Density 0.001%

    No Known Activations