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

    Neuronpedia

    INDEX
    Explanations

    instances of character names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.90
     ſtand
    -0.84
     houſe
    -0.81
     ſtate
    -0.81
     purpoſe
    -0.80
     Majefty
    -0.80
     Jefus
    -0.79
     deſt
    -0.77
     itſelf
    -0.77
     uſed
    -0.76
    POSITIVE LOGITS
     @
    0.75
     Mr
    0.74
    Mr
    0.62
     Z
    0.57
     j
    0.56
     J
    0.55
     z
    0.52
     G
    0.52
     Ar
    0.51
     Dr
    0.50
    Act Density 0.174%

    No Known Activations