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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating financial transactions, impacts, or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quieter
    -0.21
     softer
    -0.20
     smaller
    -0.20
     poorer
    -0.20
     weaker
    -0.19
     thinner
    -0.18
     менÑĮ
    -0.18
     simpler
    -0.17
     lesser
    -0.17
    arser
    -0.17
    POSITIVE LOGITS
     More
    0.19
     slightly
    0.18
     more
    0.17
     somewhat
    0.16
     gri
    0.15
    argin
    0.15
    pps
    0.15
     ÏĢεÏģιÏĥÏĥÏĮÏĦε
    0.15
    More
    0.15
     MORE
    0.15
    Act Density 0.150%

    No Known Activations