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

    Neuronpedia

    INDEX
    Explanations

    references to programming constructs and code-related functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.82
      
    -0.71
     &
    -0.64
     and
    -0.63
     of
    -0.59
    .
    -0.57
     C
    -0.56
     ,
    -0.56
    &
    -0.55
     On
    -0.54
    POSITIVE LOGITS
     iſt
    1.16
     purpoſe
    1.12
     autorytatywna
    1.09
     ſind
    1.09
     $_"
    1.06
     Majefty
    1.06
     ſtate
    1.05
     חיצוניים
    1.05
     المعيارى
    1.03
    ValueStyle
    1.03
    Act Density 1.055%

    No Known Activations