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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating statements or quoting someone

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "says" or "said" and its variations, indicating statements or quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.88
    folios
    -0.76
    theless
    -0.70
    anu
    -0.70
    thia
    -0.68
    aughs
    -0.68
    udos
    -0.67
    MENTS
    -0.65
    Tai
    -0.64
    posium
    -0.63
    POSITIVE LOGITS
     goodbye
    1.02
     nothing
    0.69
    ysis
    0.66
    ogun
    0.63
     otherwise
    0.63
     yes
    0.62
    ieu
    0.61
     bye
    0.60
     spies
    0.59
    auga
    0.59
    Act Density 0.131%

    No Known Activations