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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ïħμ
    -0.17
    OLT
    -0.16
    idor
    -0.15
    Ã
    -0.15
    rott
    -0.15
    asan
    -0.14
    ÛĮدÙĨ
    -0.14
    isd
    -0.13
    uyla
    -0.13
    ãģ¬
    -0.13
    POSITIVE LOGITS
    hei
    0.14
    213
    0.14
    oret
    0.14
    orial
    0.13
     foss
    0.13
    225
    0.13
    ighton
    0.13
    ÃŃrk
    0.13
     Meal
    0.13
     handful
    0.13
    Act Density 0.173%

    No Known Activations