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

    Neuronpedia

    INDEX
    Explanations

    character names in a narrative scene

    oai_token-act-pair · gpt-3.5-turbo

    character interactions and emotional expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilater
    -0.83
    taboola
    -0.82
    mercial
    -0.77
    oÄŁ
    -0.76
    osponsors
    -0.75
    kefeller
    -0.74
    adelphia
    -0.74
    ecast
    -0.71
    Bey
    -0.69
    letes
    -0.69
    POSITIVE LOGITS
     Snape
    1.03
     Pyrrha
    1.01
     Hermione
    1.01
     Jaune
    1.00
     Weasley
    0.98
     Dumbledore
    0.96
     sigh
    0.90
     grin
    0.89
     Malfoy
    0.89
     Draco
    0.89
    Act Density 1.121%

    No Known Activations