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

    Neuronpedia

    INDEX
    Explanations

    statements or actions expressing support for something specific

    oai_token-act-pair · gpt-3.5-turbo

    mentions of support for various causes or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.85
    ashtra
    -0.81
    orbit
    -0.73
    NL
    -0.71
     crore
    -0.69
    Tracker
    -0.69
    nick
    -0.68
     ancest
    -0.68
    Fle
    -0.67
    ishi
    -0.64
    POSITIVE LOGITS
    gotten
    0.96
    bidden
    0.92
    gery
    0.90
    aging
    0.86
    cing
    0.79
    geries
    0.77
    thood
    0.73
    ints
    0.70
     purposes
    0.68
     equality
    0.67
    Act Density 0.100%

    No Known Activations