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

    Neuronpedia

    INDEX
    Explanations

    phrases related to additional or contrasting information in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating multi-faceted scenarios or complexities involving human experiences and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guinness
    -0.71
     HK
    -0.64
     Tus
    -0.64
     Corpus
    -0.64
     Orbit
    -0.63
    opoly
    -0.63
     cous
    -0.63
     Clover
    -0.62
    crow
    -0.62
     Canary
    -0.61
    POSITIVE LOGITS
     nonetheless
    0.79
     risks
    0.77
     fundamentally
    0.75
     acknowledging
    0.75
     acknowledge
    0.71
     undeniably
    0.70
     embracing
    0.70
     acutely
    0.70
     reap
    0.70
    Impl
    0.68
    Act Density 0.385%

    No Known Activations