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

    Neuronpedia

    INDEX
    Explanations

    references to images or visual representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ra
    -0.17
    Ùij
    -0.16
    osh
    -0.16
    ëĭ¤ê°Ģ
    -0.15
    ities
    -0.15
    ri
    -0.15
    shire
    -0.15
    ilet
    -0.15
    lei
    -0.14
    yla
    -0.14
    POSITIVE LOGITS
    -per
    0.23
    orial
    0.22
     perfect
    0.20
    perfect
    0.19
    ocks
    0.18
    Perfect
    0.18
    ofday
    0.18
    /video
    0.17
     Perfect
    0.17
    colo
    0.17
    Act Density 0.027%

    No Known Activations