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

    Neuronpedia

    INDEX
    Explanations

    terms related to technology and finance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to responsibility and regulatory matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     satell
    -0.84
     finishing
    -0.83
     fierce
    -0.82
     watering
    -0.81
     pony
    -0.77
     unbeat
    -0.75
     spitting
    -0.74
    zens
    -0.74
     smashing
    -0.74
     ferocious
    -0.73
    POSITIVE LOGITS
     Basics
    1.45
     Matters
    1.45
     Versus
    1.44
     Strategies
    1.42
     Overview
    1.38
     Practices
    1.38
     Revis
    1.38
     Increases
    1.37
     Causes
    1.37
     Disorder
    1.36
    Act Density 0.241%

    No Known Activations