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

    Neuronpedia

    INDEX
    Explanations

    references to deception or things that are not genuine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    रण
    -0.15
    TINGS
    -0.15
    енÑı
    -0.15
    elah
    -0.14
    ,No
    -0.14
    alom
    -0.14
    ttl
    -0.14
    gni
    -0.14
    ognition
    -0.14
     backpage
    -0.13
    POSITIVE LOGITS
    inen
    0.17
    ocy
    0.15
    orus
    0.15
    por
    0.15
    -caret
    0.15
    iten
    0.14
    æīĺ
    0.14
     Wak
    0.14
    ê¸
    0.14
    oje
    0.14
    Act Density 0.158%

    No Known Activations