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

    Neuronpedia

    INDEX
    Explanations

    phrases related to weight and measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cuerdas
    -0.49
     ustedes
    -0.47
     Vorbild
    -0.45
     вот
    -0.45
     ElementRef
    -0.45
     Könige
    -0.44
     novios
    -0.44
     empleos
    -0.44
     meille
    -0.43
    manera
    -0.43
    POSITIVE LOGITS
     Deputy
    0.69
     Late
    0.69
     accept
    0.68
     late
    0.66
     Accept
    0.66
     accepts
    0.65
     accepting
    0.65
     accep
    0.63
     acceptance
    0.62
     ACCEPT
    0.62
    Act Density 0.208%

    No Known Activations