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

    Neuronpedia

    INDEX
    Explanations

    references to breaks and pauses in work or activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    habit
    -0.14
    едаг
    -0.14
    IFY
    -0.14
    era
    -0.13
    sworth
    -0.13
    weep
    -0.13
    éra
    -0.13
    ваем
    -0.13
    avad
    -0.12
    ULAR
    -0.12
    POSITIVE LOGITS
     break
    0.52
     pause
    0.41
     hiatus
    0.41
    ä¼ij
    0.41
     rest
    0.40
     breaks
    0.40
     rests
    0.36
     Break
    0.35
    -break
    0.35
    break
    0.34
    Act Density 0.235%

    No Known Activations