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

    Neuronpedia

    INDEX
    Explanations

    contextual cues like sentence endings or structural elements such as quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and patterns related to dialogue or quoted speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =]
    -0.62
    idth
    -0.61
     watered
    -0.59
    userc
    -0.59
    iliated
    -0.58
    ãĤ¼ãĤ¦ãĤ¹
    -0.57
     designated
    -0.57
     disapprove
    -0.57
     antit
    -0.56
    aditional
    -0.56
    POSITIVE LOGITS
    Researchers
    0.80
    SPONSORED
    0.80
    Dur
    0.78
    Labour
    0.77
    RESULTS
    0.75
    Press
    0.75
    Students
    0.74
    Finally
    0.74
    Shape
    0.74
    ¶
    0.72
    Act Density 0.886%

    No Known Activations