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

    Neuronpedia

    INDEX
    Explanations

    superlatives describing things

    oai_token-act-pair · gpt-3.5-turbo

    superlative adjectives indicating exceptional qualities or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Akin
    -0.72
    heit
    -0.68
     Shank
    -0.64
     Lyons
    -0.64
     Stella
    -0.62
    NK
    -0.62
     Koh
    -0.61
    ][/
    -0.61
    ENCE
    -0.61
    jad
    -0.60
    POSITIVE LOGITS
     distingu
    0.93
     challeng
    0.83
     notor
    0.83
     embr
    0.80
     quir
    0.75
     inspir
    0.75
     recurring
    0.70
     compress
    0.69
     Flavoring
    0.67
     undermin
    0.66
    Act Density 0.094%

    No Known Activations