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

    Neuronpedia

    INDEX
    Explanations

    the word "which" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ære
    -0.15
    ouv
    -0.15
    lix
    -0.15
    ount
    -0.14
     اÛĮÙĨÚ©Ùĩ
    -0.14
     Roose
    -0.14
     Fox
    -0.14
    ãĢħ
    -0.14
    runner
    -0.14
    ista
    -0.14
    POSITIVE LOGITS
    soever
    0.28
    oping
    0.16
     we
    0.15
    .compiler
    0.15
    esser
    0.15
     cabinet
    0.15
    errat
    0.15
    itzer
    0.15
    andler
    0.15
    ãĥĦ
    0.14
    Act Density 0.047%

    No Known Activations