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

    Neuronpedia

    INDEX
    Explanations

    contexts involving public observation and social scrutiny

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Unterkunft
    -0.38
    läufe
    -0.36
     Spannung
    -0.36
    lastung
    -0.35
    Enlaces
    -0.35
     tehd
    -0.34
    Kilder
    -0.34
    httphttps
    -0.32
     apresentar
    -0.32
    Външни
    -0.31
    POSITIVE LOGITS
     passers
    0.85
     pedestrians
    0.76
     paparazzi
    0.70
    路人
    0.67
     walkers
    0.63
    MLLoader
    0.63
     passer
    0.62
    haviors
    0.61
     tourists
    0.60
    ItemBackground
    0.60
    Act Density 0.492%

    No Known Activations