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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positive emotions or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to joy and celebration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chnology
    -0.65
    ngth
    -0.64
    arij
    -0.62
    ilater
    -0.59
     helicop
    -0.59
     dilig
    -0.59
    afety
    -0.58
    ividual
    -0.56
    senal
    -0.56
    insured
    -0.55
    POSITIVE LOGITS
     Cinderella
    0.61
     Pharaoh
    0.58
     Tanzania
    0.55
     Corpus
    0.55
     Buddha
    0.55
     Romantic
    0.54
     Carnival
    0.54
     Ashes
    0.53
     Birthday
    0.53
     Cooking
    0.53
    Act Density 1.377%

    No Known Activations