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

    Neuronpedia

    INDEX
    Explanations

    adjectives or adverbs describing a unique or distinctive quality

    oai_token-act-pair · gpt-3.5-turbo

    words that convey uniqueness or distinctiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTOS
    -0.77
     flaws
    -0.68
     adoption
    -0.67
    quickShipAvailable
    -0.67
     opposition
    -0.66
    Reviewer
    -0.65
     demolition
    -0.65
     conclusions
    -0.64
     substitution
    -0.63
     Onion
    -0.62
    POSITIVE LOGITS
     suited
    0.82
    responsible
    0.78
     narrated
    0.78
     differentiated
    0.75
     tailored
    0.74
     positioned
    0.72
     tuned
    0.72
     situated
    0.71
     trained
    0.71
     consulted
    0.70
    Act Density 0.018%

    No Known Activations