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

    Neuronpedia

    INDEX
    Explanations

    interjections and phrases indicating emotional reactions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     material
    -0.71
     ‘
    -0.68
    Source
    -0.64
    Material
    -0.63
     inves
    -0.62
    ette
    -0.62
     aste
    -0.58
     Tas
    -0.58
    ('/');
    -0.57
    Tas
    -0.57
    POSITIVE LOGITS
     Réponses
    1.15
     Cah
    1.03
     Ahh
    1.01
    beh
    0.99
    bah
    0.99
     Doh
    0.97
    extAlignment
    0.97
    Aah
    0.96
    Ahh
    0.96
     ahh
    0.96
    Act Density 0.307%

    No Known Activations