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

    Neuronpedia

    INDEX
    Explanations

    questions regarding character restrictions and events in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     PILOT
    -0.53
    PIL
    -0.53
     Pilot
    -0.50
    Pilot
    -0.50
    anthin
    -0.49
     pilot
    -0.47
    Pil
    -0.46
     pilotes
    -0.45
    pilot
    -0.42
    NSF
    -0.41
    POSITIVE LOGITS
     Harry
    1.02
     Hermione
    0.96
     Dumbledore
    0.95
     Hogwarts
    0.93
     Potter
    0.90
     Voldemort
    0.88
    Harry
    0.88
     Snape
    0.85
     Ron
    0.85
     Weasley
    0.83
    Act Density 0.173%

    No Known Activations