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

    Neuronpedia

    INDEX
    Explanations

    personal nouns referring to people or groups of people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "lives" and their improvement or significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NES
    -0.79
    AMI
    -0.74
    ority
    -0.70
    Null
    -0.69
    iban
    -0.68
    Rat
    -0.64
     neutrality
    -0.63
    CAST
    -0.63
    steamapps
    -0.62
     Syndicate
    -0.62
    POSITIVE LOGITS
    chool
    1.17
    cape
    1.04
    pring
    0.96
    ynthesis
    0.93
    paces
    0.90
    journal
    0.85
    erver
    0.84
    pace
    0.83
    guard
    0.83
    lihood
    0.81
    Act Density 0.026%

    No Known Activations