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

    Neuronpedia

    INDEX
    Explanations

    things or characters related to a fantasy world or game, potentially involving challenges and surprises

    oai_token-act-pair · gpt-3.5-turbo

    references to individual items or characters along with their unique attributes and narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibur
    -0.70
    essors
    -0.65
    soDeliveryDate
    -0.65
    nea
    -0.62
    ayne
    -0.61
     Bron
    -0.61
     Partners
    -0.59
    ptives
    -0.59
    dm
    -0.59
     Colbert
    -0.58
    POSITIVE LOGITS
     individually
    1.46
     separately
    1.11
     equally
    0.95
     independently
    0.93
     imaginable
    0.92
     unique
    0.90
     distinct
    0.86
     uniquely
    0.85
     varying
    0.84
     conceivable
    0.83
    Act Density 0.289%

    No Known Activations