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

    Neuronpedia

    INDEX
    Explanations

    occurrences of regulatory and procedural terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     and
    -0.58
    енча
    -0.48
    tron
    -0.45
     împ
    -0.45
     linkovi
    -0.44
    лона
    -0.44
     these
    -0.43
     fede
    -0.42
     والت
    -0.42
     plus
    -0.42
    POSITIVE LOGITS
     poffe
    0.94
     perſon
    0.87
     Monfieur
    0.86
     whoſe
    0.85
     preſent
    0.83
     pleaſure
    0.82
     purpoſe
    0.81
     ſtate
    0.80
     ſeveral
    0.80
     reaſon
    0.79
    Act Density 1.634%

    No Known Activations