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

    Neuronpedia

    INDEX
    Explanations

    expressions of sadness or negative emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stateProvider
    -0.65
     Voulez
    -0.65
     newBuilder
    -0.64
     gynhyrchwyd
    -0.62
     referenties
    -0.62
    PreferredItem
    -0.60
     Roskov
    -0.60
     nahilalakip
    -0.60
    IUrlHelper
    -0.60
    NameInMap
    -0.59
    POSITIVE LOGITS
     sad
    0.95
    😢
    0.90
     disappoint
    0.87
     Sad
    0.87
     😔
    0.85
     :(
    0.84
     😢
    0.82
    Sad
    0.82
     disappointment
    0.81
    😔
    0.78
    Act Density 0.112%

    No Known Activations