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

    Neuronpedia

    INDEX
    Explanations

    key terms related to processes and events in experimental and statistical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     S
    -0.78
     Gr
    -0.76
     N
    -0.75
     P
    -0.70
     F
    -0.70
    präsident
    -0.70
     b
    -0.69
     mo
    -0.69
     
    -0.69
     W
    -0.68
    POSITIVE LOGITS
     pleaſure
    1.35
     himſelf
    1.23
     themſelves
    1.22
     Monfieur
    1.22
     ſeveral
    1.22
     theſe
    1.20
     reaſon
    1.20
     Jefus
    1.18
     viſ
    1.17
     myſelf
    1.17
    Act Density 0.161%

    No Known Activations