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

    Neuronpedia

    INDEX
    Explanations

    words related to order and smooth functioning

    oai_token-act-pair · gpt-3.5-turbo

    terms related to orderliness and chaos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    href
    -0.84
    arte
    -0.81
    rays
    -0.80
    ateurs
    -0.80
    arium
    -0.75
    uries
    -0.75
    tips
    -0.74
    assador
    -0.74
    rose
    -0.73
    URI
    -0.72
    POSITIVE LOGITS
     orderly
    0.96
     transitions
    0.87
     disorderly
    0.81
     transition
    0.77
     chaotic
    0.74
     scaling
    0.70
    hess
    0.70
     Taj
    0.69
     Stability
    0.68
     Pace
    0.68
    Act Density 0.021%

    No Known Activations