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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software development and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.90
      
    -0.74
    ,
    -0.60
     so
    -0.59
     The
    -0.54
     i
    -0.53
     "
    -0.52
       
    -0.51
    The
    -0.51
     (
    -0.51
    POSITIVE LOGITS
     ſtate
    1.29
     Majefty
    1.28
    ſelves
    1.28
    ſelf
    1.25
     Efq
    1.22
     ſind
    1.21
     Anſ
    1.19
     Diſ
    1.17
     ſche
    1.16
     itſelf
    1.16
    Act Density 1.247%

    No Known Activations