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

    Neuronpedia

    INDEX
    Explanations

    grammar patterns indicating past actions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    instances of emotional complexity in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.72
    TRUMP
    -0.72
     promotes
    -0.71
    agogue
    -0.71
    espie
    -0.71
     Replay
    -0.69
    eware
    -0.69
     demos
    -0.66
    FM
    -0.65
    olphins
    -0.65
    POSITIVE LOGITS
     Jaune
    1.33
     Pyrrha
    1.25
     Malfoy
    1.14
     Severus
    1.13
     Elsa
    1.12
     Weasley
    1.09
     sighed
    1.08
     Snape
    1.07
     Hermione
    1.06
     Dumbledore
    1.01
    Act Density 0.953%

    No Known Activations