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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and punctuation in written text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cott
    -0.18
    tach
    -0.16
     ÑĢаÑģк
    -0.16
    ÃĸL
    -0.15
    culate
    -0.14
    664
    -0.14
    862
    -0.14
     corpor
    -0.14
    Convertible
    -0.14
     -------------------------------------------------------------------------
    -0.14
    POSITIVE LOGITS
     then
    0.21
    then
    0.20
    opa
    0.18
    çĦ¶åIJİ
    0.16
    AREST
    0.15
    pus
    0.15
    	then
    0.15
    aras
    0.15
    Seller
    0.14
    íģ¼
    0.14
    Act Density 0.126%

    No Known Activations