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

    Neuronpedia

    INDEX
    Explanations

    expressions related to technology and creative activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thereunder
    -0.65
     restantes
    -0.61
     inicialmente
    -0.60
     asimismo
    -0.57
     yder
    -0.56
     exclusivamente
    -0.56
     respectivas
    -0.56
     nonché
    -0.54
     valamint
    -0.54
     vœux
    -0.54
    POSITIVE LOGITS
     stuff
    1.57
     things
    1.54
     weird
    1.18
     dingen
    1.06
    stuff
    1.05
     stupid
    1.04
     strange
    1.03
     wierd
    1.03
     STUFF
    1.00
     Stuff
    0.99
    Act Density 0.640%

    No Known Activations