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

    Neuronpedia

    INDEX
    Explanations

    words related to spatial relationships or physical locations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific and geopolitical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xual
    -0.95
    tower
    -0.93
    lessly
    -0.93
    wright
    -0.90
    cham
    -0.88
    esty
    -0.86
    kins
    -0.86
    holes
    -0.85
    boarding
    -0.84
    hole
    -0.83
    POSITIVE LOGITS
    ities
    1.07
    ity
    0.96
    ized
    0.94
     significance
    0.92
     impact
    0.90
     manifestations
    0.87
     imaging
    0.84
     anomalies
    0.84
     disturbances
    0.84
     ramifications
    0.83
    Act Density 0.075%

    No Known Activations