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

    Neuronpedia

    INDEX
    Explanations

    references to legal actions and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.11
     itſelf
    -1.07
     Theſe
    -1.06
     Jefus
    -1.03
     purpoſe
    -1.02
     Monfieur
    -1.02
     ſche
    -1.01
     ſtate
    -1.00
     houſe
    -0.99
     pleaſure
    -0.97
    POSITIVE LOGITS
     an
    0.78
     after
    0.76
     a
    0.69
    因
    0.66
    此前
    0.65
     I
    0.64
     zuvor
    0.63
     recent
    0.61
     previously
    0.60
     
    0.60
    Act Density 0.230%

    No Known Activations