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

    Neuronpedia

    INDEX
    Explanations

    parts or components of objects or projects

    oai_token-act-pair · gpt-3.5-turbo

    references to components or sections of a whole

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anche
    -0.80
    yrinth
    -0.78
    gee
    -0.76
    gently
    -0.75
    ça
    -0.75
    errilla
    -0.71
    asu
    -0.70
    ZE
    -0.69
    izu
    -0.69
    aga
    -0.67
    POSITIVE LOGITS
     parts
    1.23
     Parts
    1.09
    parts
    0.87
     Components
    0.80
    afety
    0.75
     seams
    0.72
     Ree
    0.71
     quarters
    0.70
    ridges
    0.67
    etter
    0.67
    Act Density 0.020%

    No Known Activations