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

    Neuronpedia

    INDEX
    Explanations

    words related to movement (such as verbs, nouns, and descriptions of movement)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to movement and physical actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esters
    -0.81
    redits
    -0.73
    redit
    -0.72
    geries
    -0.72
    rypt
    -0.71
    orah
    -0.71
    eno
    -0.71
    romeda
    -0.71
    ihil
    -0.70
    CLA
    -0.69
    POSITIVE LOGITS
     patterns
    1.18
     motions
    1.05
     movements
    0.98
     speeds
    0.96
     velocity
    0.94
     pattern
    0.92
     sickness
    0.92
     direction
    0.91
     Patterns
    0.90
    peed
    0.89
    Act Density 0.130%

    No Known Activations