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

    Neuronpedia

    INDEX
    Explanations

    references to the word "whom"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.67
    ↵
    -0.64
    ,
    -0.59
     (
    -0.57
      
    -0.57
     Je
    -0.57
     Chi
    -0.56
    is
    -0.55
    ess
    -0.55
    los
    -0.55
    POSITIVE LOGITS
     ainfi
    0.93
     avoient
    0.92
     plufieurs
    0.87
     Monfieur
    0.86
     miniaturka
    0.85
     wikipagina
    0.84
     <=",
    0.82
     indígen
    0.81
     feroit
    0.81
     desmotivaciones
    0.79
    Act Density 0.402%

    No Known Activations