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

    Neuronpedia

    INDEX
    Explanations

    numerical values, particularly those that might indicate dates or financial amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еÑĢин
    -0.16
    žil
    -0.15
    avan
    -0.15
    linger
    -0.15
     cen
    -0.14
    ristol
    -0.14
    ean
    -0.14
    mtree
    -0.14
    urat
    -0.14
     Race
    -0.13
    POSITIVE LOGITS
    ÑĩаÑĤ
    0.15
    âĶĥ
    0.13
     Colbert
    0.13
    enda
    0.13
    ventus
    0.13
     ÎŃκ
    0.13
    bish
    0.13
    Mocks
    0.13
    ıt
    0.13
    setPosition
    0.13
    Act Density 0.000%

    No Known Activations