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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing exclusivity or limitations within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     both
    -0.97
     zarówno
    -0.90
    both
    -0.84
     både
    -0.84
     sowohl
    -0.78
     zowel
    -0.78
    BOTH
    -0.75
     nejen
    -0.73
     BOTH
    -0.69
     also
    -0.68
    POSITIVE LOGITS
     limited
    0.74
    少数
    0.69
     handful
    0.68
    ごく
    0.67
    Limited
    0.66
     finitely
    0.65
     limitado
    0.64
    limited
    0.64
     wenige
    0.62
     limitada
    0.60
    Act Density 0.713%

    No Known Activations