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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çļĦæĺ¯
    -0.16
    asher
    -0.16
    aul
    -0.15
    iction
    -0.15
    еÑĩ
    -0.14
     kia
    -0.14
    ictions
    -0.13
    ãģ®ãģĮ
    -0.13
    ERCHANT
    -0.13
    abbo
    -0.13
    POSITIVE LOGITS
    oping
    0.18
    upon
    0.18
    soever
    0.17
    indi
    0.16
     is
    0.16
     has
    0.15
     we
    0.15
    odos
    0.14
    ληÏĤ
    0.14
     incident
    0.14
    Act Density 0.126%

    No Known Activations