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

    Neuronpedia

    INDEX
    Explanations

    references to pairs or groups of two entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     a
    -0.63
    tera
    -0.43
     an
    -0.41
    то
    -0.41
     unui
    -0.40
    Cone
    -0.39
     leyendas
    -0.39
     another
    -0.38
    scaleY
    -0.37
     lecteurs
    -0.37
    POSITIVE LOGITS
    Ambos
    1.33
     Beide
    1.17
     Ambos
    1.17
    +#+#
    1.14
     beiden
    1.13
     beider
    1.13
     betweenstory
    1.10
    BOTH
    1.08
    IntoConstraints
    1.03
     beide
    1.03
    Act Density 0.122%

    No Known Activations