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

    Neuronpedia

    INDEX
    Explanations

    research-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to research, data, and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernels
    -0.95
    rals
    -0.93
    ouls
    -0.92
    lees
    -0.91
    comings
    -0.89
    nces
    -0.83
    profits
    -0.83
    usions
    -0.81
    aways
    -0.80
    Americans
    -0.80
    POSITIVE LOGITS
     standpoint
    1.10
     regimen
    0.92
     programme
    0.91
     pact
    0.91
     package
    0.91
     nightmare
    0.89
     facility
    0.88
     program
    0.88
     project
    0.87
     scheme
    0.87
    Act Density 0.302%

    No Known Activations