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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collective evaluation or generalization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.43
     conmigo
    -0.43
    -0.40
     quidem
    -0.39
     permanently
    -0.38
    AsUp
    -0.37
    IVEREF
    -0.37
    emale
    -0.37
    angliski
    -0.37
     sarung
    -0.37
    POSITIVE LOGITS
     tudo
    0.76
    everything
    0.69
     wszystko
    0.68
     everything
    0.68
    这一切
    0.65
    Everything
    0.64
    Всё
    0.63
    Tudo
    0.63
     Tudo
    0.62
    的一切
    0.61
    Act Density 0.342%

    No Known Activations