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

    Neuronpedia

    INDEX
    Explanations

    the concept of breaking or interruptions within texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.47
    Portály
    -0.45
    Literals
    -0.45
    Geplaatst
    -0.43
     Normdatei
    -0.42
    
    -0.42
    ThemeOverlay
    -0.41
    literals
    -0.41
     ControllerBase
    -0.41
     OkHttpClient
    -0.40
    POSITIVE LOGITS
     break
    2.86
     Break
    2.59
     breaking
    2.50
    Break
    2.45
    break
    2.45
     breaks
    2.28
     broke
    2.27
     Breaking
    2.23
     BREAK
    2.23
    Breaking
    2.19
    Act Density 0.258%

    No Known Activations