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

    Neuronpedia

    INDEX
    Explanations

    quotations ending with a comma followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    punctuation related to dialogue or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.76
    ardless
    -0.76
    taboola
    -0.72
    etheless
    -0.71
    ĻĤ
    -0.69
    wp
    -0.68
    ahime
    -0.67
    displayText
    -0.65
    ãĥij
    -0.65
    renheit
    -0.64
    POSITIVE LOGITS
     said
    1.29
     says
    1.21
    said
    1.12
     remarked
    1.02
     joked
    1.02
     explained
    1.00
     commented
    0.97
     explains
    0.96
     exclaimed
    0.93
     recalled
    0.92
    Act Density 0.102%

    No Known Activations