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

    Neuronpedia

    INDEX
    Explanations

    dialogue between characters

    oai_token-act-pair · gpt-3.5-turbo

    expressions of dialogue and character interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uably
    -0.70
     "#
    -0.64
     batters
    -0.63
     WATCHED
    -0.62
     NYT
    -0.61
    ardi
    -0.61
    NBA
    -0.59
    NFL
    -0.59
    CNN
    -0.59
    endi
    -0.59
    POSITIVE LOGITS
    -"
    1.61
    âĢ¦"
    1.49
    ..."
    1.41
    —"
    1.35
     âĢ¦"
    1.24
    âĢ¦."
    1.22
    !?"
    1.16
    ãĢį
    1.12
    ?"
    1.12
    !"
    1.09
    Act Density 0.559%

    No Known Activations