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

    Neuronpedia

    INDEX
    Explanations

    various forms of conjunctions and markers indicating continuity in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avax
    -0.17
    oling
    -0.16
    Ñıд
    -0.15
    zin
    -0.15
     Heb
    -0.14
    ibia
    -0.14
    Äįek
    -0.14
    ieg
    -0.14
    liament
    -0.14
    kova
    -0.14
    POSITIVE LOGITS
    ural
    0.14
    unch
    0.14
    quo
    0.14
     Enrique
    0.14
    _fifo
    0.14
    upp
    0.13
    ÅŁt
    0.13
     hal
    0.13
    ulas
    0.13
    ures
    0.13
    Act Density 0.002%

    No Known Activations