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

    Neuronpedia

    INDEX
    Explanations

    discourse markers and conversational turn-taking cues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     while
    -0.21
     since
    -0.19
     though
    -0.19
     after
    -0.17
     moreover
    -0.17
     plus
    -0.17
     however
    -0.16
    æѤ
    -0.16
     heck
    -0.16
     WHILE
    -0.16
    POSITIVE LOGITS
     And
    0.28
    And
    0.25
     Cause
    0.21
    Cause
    0.21
    	So
    0.20
     Number
    0.19
    So
    0.19
     So
    0.19
    Number
    0.18
     Again
    0.17
    Act Density 0.141%

    No Known Activations