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

    Neuronpedia

    INDEX
    Explanations

    words related to global or societal concepts like countries, cultures, societies, and nations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to global or national contexts and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     detectors
    -0.82
    Rust
    -0.72
     bits
    -0.71
    ainers
    -0.66
    Congratulations
    -0.65
    iates
    -0.64
    prints
    -0.64
     cylinders
    -0.63
     vouchers
    -0.63
    eworks
    -0.63
    POSITIVE LOGITS
    wide
    0.88
    uci
    0.82
     starved
    0.77
     reckoning
    0.74
    ĨĴ
    0.73
    ét
    0.73
    ozy
    0.72
     comprised
    0.72
     composed
    0.72
    ustomed
    0.71
    Act Density 0.349%

    No Known Activations