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

    Neuronpedia

    INDEX
    Explanations

    the word "both."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AppBar
    -0.52
     surla
    -0.48
     Mula
    -0.48
     nakalista
    -0.48
     Bré
    -0.48
    ampung
    -0.46
    Referencer
    -0.46
     hole
    -0.45
     marta
    -0.45
     Hoje
    -0.44
    POSITIVE LOGITS
     both
    2.01
    both
    1.89
    Both
    1.76
     Both
    1.72
    BOTH
    1.52
    Ambos
    1.51
     BOTH
    1.47
     entrambi
    1.30
     ambos
    1.29
     beide
    1.21
    Act Density 0.079%

    No Known Activations