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

    Neuronpedia

    INDEX
    Explanations

    words related to movement or action, particularly those involving swinging dynamics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Maddox
    -0.80
     hâte
    -0.76
    Azur
    -0.75
     frattempo
    -0.75
     sabbia
    -0.73
     Herodotus
    -0.72
     APD
    -0.72
     SAE
    -0.71
     Mott
    -0.71
    BorderColor
    -0.71
    POSITIVE LOGITS
    swing
    1.95
    Swing
    1.93
     Swing
    1.88
     swing
    1.83
     swings
    1.64
     swinging
    1.62
     swung
    1.50
     pendulum
    1.05
    SwingConstants
    1.04
     bVar
    0.87
    Act Density 0.005%

    No Known Activations