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

    Neuronpedia

    INDEX
    Explanations

    conjunctions indicating contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opsida
    -0.73
     /\.
    -0.56
    SPATH
    -0.54
     Parco
    -0.53
    ícil
    -0.51
     Coro
    -0.50
     CAG
    -0.50
     pewno
    -0.50
    Переваги
    -0.49
     intStringLen
    -0.49
    POSITIVE LOGITS
     also
    0.79
    findpost
    0.70
    also
    0.66
    而且
    0.66
     también
    0.63
    OGND
    0.61
     juga
    0.61
    surate
    0.60
     아니라
    0.60
     també
    0.59
    Act Density 0.099%

    No Known Activations