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

    Neuronpedia

    INDEX
    Explanations

    terms related to financial transactions and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     man
    -0.51
     sim
    -0.51
     variety
    -0.49
     @
    -0.49
     young
    -0.49
    tés
    -0.49
     talking
    -0.48
     x
    -0.48
     men
    -0.48
    果
    -0.48
    POSITIVE LOGITS
     purpoſe
    1.11
     fubject
    1.05
     reaſon
    1.02
     ſtate
    0.99
     myſelf
    0.96
     pleaſure
    0.95
     himſelf
    0.93
     ſhall
    0.91
     cauſe
    0.90
     itſelf
    0.90
    Act Density 0.350%

    No Known Activations