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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to physical movement or interaction

    oai_token-act-pair · gpt-3.5-turbo

    physical actions and movements in a dynamic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Serving
    -0.72
     Identity
    -0.71
    insula
    -0.71
     Seventh
    -0.71
    ortment
    -0.66
    esan
    -0.66
    ourt
    -0.66
    xus
    -0.66
     cler
    -0.64
    uchin
    -0.64
    POSITIVE LOGITS
     collided
    0.83
     particles
    0.82
     tubes
    0.80
     uncontroll
    0.79
     distortion
    0.79
     debris
    0.78
    worms
    0.78
     collisions
    0.73
     velocity
    0.71
     sideways
    0.71
    Act Density 0.345%

    No Known Activations