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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wo
    -0.17
    ायत
    -0.17
    ÑĢаÑĤи
    -0.16
    еÑĢÑĤи
    -0.16
    eger
    -0.15
    Ñĥбли
    -0.15
    utan
    -0.15
    oust
    -0.15
     pip
    -0.14
    ISBN
    -0.14
    POSITIVE LOGITS
     STATS
    0.16
    crement
    0.15
     pars
    0.15
     dirs
    0.15
    idi
    0.14
    omap
    0.14
    otes
    0.14
    pedia
    0.14
    .apps
    0.14
    orama
    0.13
    Act Density 0.131%

    No Known Activations