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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing happiness, excitement, or gratitude

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement and welcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¯
    -0.69
    uyomi
    -0.68
    ibaba
    -0.66
    agers
    -0.63
    olia
    -0.62
    grade
    -0.61
    FBI
    -0.61
    atter
    -0.61
    ailability
    -0.60
    Nin
    -0.59
    POSITIVE LOGITS
     CK
    0.70
     Featured
    0.66
    ttes
    0.64
     Sack
    0.63
    !]
    0.62
    cision
    0.60
    ports
    0.59
     Sieg
    0.59
     such
    0.58
    Featured
    0.58
    Act Density 0.174%

    No Known Activations