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

    Neuronpedia

    INDEX
    Explanations

    terms related to complex systems or interactions

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unts
    -0.84
    gur
    -0.78
    iverpool
    -0.75
    gement
    -0.74
    chens
    -0.73
    azar
    -0.73
    inker
    -0.72
    cot
    -0.71
    istle
    -0.70
    jamin
    -0.69
    POSITIVE LOGITS
     dynamics
    1.04
     equation
    0.91
     equations
    0.89
     fluctuations
    0.76
    odynamics
    0.75
    models
    0.74
     perspect
    0.74
     incent
    0.73
     Dynam
    0.71
     modelling
    0.70
    Act Density 0.012%

    No Known Activations