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

    Neuronpedia

    INDEX
    Explanations

    detailed physical descriptions of objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey critical observations or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doctrine
    -0.69
    Neill
    -0.59
     guessing
    -0.58
    ira
    -0.56
     Defensive
    -0.56
     Radical
    -0.56
    holding
    -0.56
    ysis
    -0.56
    ostic
    -0.56
     Book
    -0.55
    POSITIVE LOGITS
     accompanies
    1.07
     extends
    1.03
     spans
    1.01
     encompasses
    0.97
     arose
    0.93
     culmin
    0.93
     resembles
    0.93
     produces
    0.93
     dominates
    0.92
     includes
    0.92
    Act Density 0.210%

    No Known Activations