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

    Neuronpedia

    INDEX
    Explanations

    URLs, particularly those related to Wikipedia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    äter
    -0.17
    utsch
    -0.14
    rum
    -0.14
    edu
    -0.14
     mek
    -0.14
     weakness
    -0.13
     Bale
    -0.13
    vl
    -0.13
    oggle
    -0.13
    ont
    -0.13
    POSITIVE LOGITS
    ondon
    0.15
    Ŀ
    0.14
    ETS
    0.14
    bette
    0.14
     Third
    0.14
    chia
    0.14
    izard
    0.13
     Mi
    0.13
     BoxFit
    0.13
    /manual
    0.13
    Act Density 0.009%

    No Known Activations