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

    Neuronpedia

    INDEX
    Explanations

    words related to superlatives

    oai_token-act-pair · gpt-3.5-turbo

    important nouns and descriptors related to quality and status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Decoder
    -0.73
     Dragons
    -0.73
     Jackets
    -0.64
     Writers
    -0.64
     flats
    -0.63
     Generator
    -0.62
     Amendments
    -0.61
     Knights
    -0.61
     Growth
    -0.61
     Cobra
    -0.61
    POSITIVE LOGITS
    ctic
    1.07
    erous
    1.06
    isable
    1.03
    isible
    1.01
    accessible
    1.00
    fficient
    1.00
    istent
    1.00
    istic
    0.99
    entious
    0.97
    ivable
    0.97
    Act Density 0.455%

    No Known Activations