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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to architecture and notable buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ehler
    -0.19
     regul
    -0.17
    ä
    -0.17
    otts
    -0.16
    uzzer
    -0.16
    ayment
    -0.15
    heritance
    -0.15
     Wah
    -0.15
    iÄĻ
    -0.15
    endet
    -0.15
    POSITIVE LOGITS
    ij
    0.23
    rij
    0.20
    ijd
    0.18
    ieren
    0.18
    reek
    0.18
    IJ
    0.18
     overt
    0.17
    ijkl
    0.17
    uw
    0.17
     Hij
    0.16
    Act Density 0.040%

    No Known Activations