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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or prepositions that indicate affiliation or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CHANT
    -0.17
    ewan
    -0.16
     Тим
    -0.15
    TestMethod
    -0.15
     równ
    -0.15
    tim
    -0.14
    اÙĬÙĨ
    -0.14
    phinx
    -0.14
    bst
    -0.14
    CHAIN
    -0.13
    POSITIVE LOGITS
    cott
    0.16
     nhau
    0.14
     Garrett
    0.14
    andas
    0.14
     homo
    0.14
    _SCOPE
    0.14
    út
    0.13
     monoc
    0.13
     jav
    0.13
    stime
    0.13
    Act Density 0.050%

    No Known Activations