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

    Neuronpedia

    INDEX
    Explanations

    sections of text that contain formatting elements or symbols, indicating structural components of a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     T
    -0.72
     L
    -0.70
     S
    -0.68
    RuleContext
    -0.68
     N
    -0.65
     V
    -0.64
     M
    -0.64
     D
    -0.63
     
    -0.63
     R
    -0.62
    POSITIVE LOGITS
     ſtate
    1.36
     themſelves
    1.35
     Majefty
    1.34
     itſelf
    1.30
     Shakspeare
    1.28
     houſe
    1.28
     Reſ
    1.26
     himſelf
    1.26
     Houſe
    1.26
     pleaſure
    1.25
    Act Density 0.387%

    No Known Activations