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

    Neuronpedia

    INDEX
    Explanations

    instances of significant numerical data or dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.11
     ſtate
    -1.00
     Majefty
    -0.97
     perſon
    -0.96
     fubject
    -0.95
     cauſe
    -0.94
     ſeveral
    -0.93
     reaſon
    -0.93
     purpoſe
    -0.90
     myſelf
    -0.89
    POSITIVE LOGITS
     vuotta
    0.61
    1
    0.60
     ۱۹
    0.58
    Cyfeiriadau
    0.56
     past
    0.56
     २०
    0.54
     years
    0.54
    CELLANEOUS
    0.53
    xmlns
    0.53
    byter
    0.52
    Act Density 0.189%

    No Known Activations