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

    Neuronpedia

    INDEX
    Explanations

    words related to various concepts or attributes, such as noise, intellectual, currency, etc., with an emphasis on concepts related to information and analysis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social issues and public health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.75
    mma
    -0.73
    adra
    -0.69
    ungle
    -0.67
    iphate
    -0.66
    ixties
    -0.65
    aughters
    -0.64
    purpose
    -0.63
    HY
    -0.62
    endment
    -0.62
    POSITIVE LOGITS
     programmers
    0.78
     historians
    0.71
     policymakers
    0.70
     traders
    0.70
     fatigue
    0.70
     researchers
    0.69
     officials
    0.68
     scholars
    0.68
     engineers
    0.67
     developers
    0.67
    Act Density 0.566%

    No Known Activations