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

    Neuronpedia

    INDEX
    Explanations

    references to programming systems and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.56
     *>(
    -0.52
    PhysRev
    -0.50
     –
    -0.50
     --
    -0.48
     unknownFields
    -0.47
    NullException
    -0.47
    ,
    -0.46
     '
    -0.46
     start
    -0.46
    POSITIVE LOGITS
     houſe
    0.97
     pleaſure
    0.97
     purpoſe
    0.97
     ſche
    0.96
     reaſon
    0.92
     Diſ
    0.90
     Chriſt
    0.90
     Majefty
    0.90
     ſch
    0.89
     himſelf
    0.89
    Act Density 0.005%

    No Known Activations