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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neau
    -0.18
    kar
    -0.14
    isten
    -0.13
     prest
    -0.13
    hl
    -0.13
     lcm
    -0.13
    è´¹
    -0.13
    ona
    -0.13
    HEET
    -0.13
    adow
    -0.13
    POSITIVE LOGITS
    .Restr
    0.18
    xa
    0.17
    ities
    0.17
    ìĤ¬íķŃ
    0.16
    odore
    0.16
     Isles
    0.16
    spb
    0.15
    pollo
    0.15
     ìĤ¬íķŃ
    0.15
    LIMIT
    0.15
    Act Density 0.074%

    No Known Activations