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

    Neuronpedia

    INDEX
    Explanations

    superlatives related to various attributes or achievements

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives and phrases comparing items or subjects in terms of their prominence or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asions
    -0.79
    eto
    -0.76
    ancies
    -0.75
    jad
    -0.69
    selves
    -0.68
    votes
    -0.68
     Nightmares
    -0.65
    ï¸
    -0.64
    é¾įåĸļ士
    -0.64
    skirts
    -0.64
    POSITIVE LOGITS
     conceivable
    0.83
     ever
    0.77
     possible
    0.75
     advanced
    0.74
     active
    0.74
     accomplished
    0.73
     indicator
    0.72
     smartest
    0.70
     sounding
    0.70
     thing
    0.70
    Act Density 0.128%

    No Known Activations