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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "über."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adena
    -0.16
    itere
    -0.15
    akis
    -0.15
    edic
    -0.15
    alers
    -0.15
    aria
    -0.14
    çĵ¶
    -0.14
     Pant
    -0.14
    ially
    -0.13
     Thin
    -0.13
    POSITIVE LOGITS
    ecycle
    0.17
    Spo
    0.17
     Spo
    0.15
     tslib
    0.15
    loh
    0.15
    forman
    0.15
    اÙĨÙĩ
    0.15
    erli
    0.15
    erif
    0.14
    umann
    0.14
    Act Density 0.010%

    No Known Activations