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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual significance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    calls-to-action and exclamatory statements that encourage reader engagement or response.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     therefore
    -1.16
     Therefore
    -1.07
    Therefore
    -1.06
     Поэтому
    -1.02
    所以
    -1.01
    Поэтому
    -1.01
    therefore
    -0.98
     поэтому
    -0.98
     Derfor
    -0.98
     więc
    -0.95
    POSITIVE LOGITS
     chances
    0.64
    Chances
    0.56
     Chances
    0.56
     remember
    0.54
    畢竟
    0.49
    きっと
    0.49
     youll
    0.49
     Remember
    0.49
     then
    0.47
    Remember
    0.46
    Act Density 0.316%

    No Known Activations