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

    Neuronpedia

    INDEX
    Explanations

    instances of smiling or expressions of happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelAdmin
    -0.61
    béco
    -0.51
    admin
    -0.48
     feroit
    -0.47
     getHeight
    -0.45
    Admin
    -0.44
    feder
    -0.44
    TestingModule
    -0.44
     administrative
    -0.44
     admin
    -0.44
    POSITIVE LOGITS
     smile
    2.92
     smiles
    2.48
     Smile
    2.36
     smiled
    2.34
    smile
    2.22
    Smile
    2.17
     smiling
    2.09
     sonrisa
    2.00
     Smiles
    1.90
     Smiling
    1.84
    Act Density 0.123%

    No Known Activations