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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing disappointment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alach
    -0.77
    otin
    -0.72
    ittee
    -0.71
     appropriation
    -0.70
    ossession
    -0.70
     intensive
    -0.69
    aucas
    -0.68
    monary
    -0.67
    odynam
    -0.66
    natureconservancy
    -0.64
    POSITIVE LOGITS
     disappoint
    0.94
    imaru
    0.86
     disappointment
    0.83
    actory
    0.75
    ments
    0.74
     ABE
    0.73
     Masquerade
    0.72
     disappointed
    0.71
     Freddy
    0.69
     surprises
    0.69
    Act Density 0.024%

    No Known Activations