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
    luiting
    -0.55
     חיצוניים
    -0.54
    gisi
    -0.50
    rzez
    -0.50
    TabLayout
    -0.49
    مرد
    -0.49
     Vall
    -0.48
    PONENT
    -0.48
    oley
    -0.48
     Poco
    -0.48
    POSITIVE LOGITS
     whereof
    1.21
     auquel
    1.13
     which
    1.10
     whom
    1.07
     auxquelles
    1.04
     duquel
    1.03
     waarop
    1.03
     waarmee
    1.00
     auxquels
    0.99
    Which
    0.99
    Act Density 0.100%

    No Known Activations