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

    Neuronpedia

    INDEX
    Explanations

    references to Notre Dame, particularly in a context that triggers emotional or evaluative reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oon
    -0.17
    SED
    -0.16
    pag
    -0.16
    wer
    -0.16
    warf
    -0.15
    ster
    -0.15
    kop
    -0.15
    еÑĢг
    -0.15
    STER
    -0.14
    ìĸ¸
    -0.14
    POSITIVE LOGITS
     Dame
    0.27
    amment
    0.17
     Higgins
    0.15
     Aires
    0.15
    alk
    0.15
    .sdk
    0.14
    574
    0.14
     prise
    0.14
    amus
    0.14
    epad
    0.14
    Act Density 0.005%

    No Known Activations