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

    Neuronpedia

    INDEX
    Explanations

    quotations ending with a comma

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate dialogue or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.83
     tremend
    -0.63
     stret
    -0.59
    ãĥij
    -0.58
    Widget
    -0.57
     misunder
    -0.55
    amorph
    -0.54
     Directions
    -0.54
    soDeliveryDate
    -0.54
    ãĥĻ
    -0.53
    POSITIVE LOGITS
     said
    1.23
    said
    1.17
     he
    1.04
     says
    1.03
     wrote
    1.01
     she
    0.92
     reads
    0.91
     replied
    0.90
     writes
    0.90
     joked
    0.86
    Act Density 0.109%

    No Known Activations