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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical propositions or theorems

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     témoin
    -0.80
     témoins
    -0.78
    phazard
    -0.77
    adaptiveStyles
    -0.74
     urmă
    -0.73
     testigos
    -0.71
    Begriff
    -0.70
    öglichkeiten
    -0.70
    LError
    -0.70
    checklist
    -0.69
    POSITIVE LOGITS
     Proposition
    1.06
    Proposition
    0.95
     proposition
    0.82
     propositions
    0.82
    proposition
    0.68
    $)$
    0.65
     lenker
    0.64
    Allister
    0.63
     Cors
    0.62
    Duc
    0.61
    Act Density 0.003%

    No Known Activations