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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to change, development, and shifts

    oai_token-act-pair · gpt-3.5-turbo

    statements about conditions or situations related to various topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raph
    -0.65
     Mour
    -0.65
     retrie
    -0.64
     Architecture
    -0.63
     Pats
    -0.62
     Rhod
    -0.62
     Think
    -0.62
     Execution
    -0.61
     LV
    -0.61
     Heal
    -0.61
    POSITIVE LOGITS
     waning
    0.96
     dwindling
    0.94
     nonexistent
    0.94
     manifold
    0.91
     widespread
    0.89
     fraught
    0.88
     paralle
    0.87
     complicated
    0.85
     underway
    0.85
     hotly
    0.84
    Act Density 0.334%

    No Known Activations