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

    Neuronpedia

    INDEX
    Explanations

    phrases related to calls for reform

    oai_token-act-pair · gpt-3.5-turbo

    references to reform and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gaard
    -0.73
    CTV
    -0.70
     Mehran
    -0.65
     Ala
    -0.63
     LIMITED
    -0.63
     tongues
    -0.62
     Printed
    -0.61
    LAN
    -0.61
     Anon
    -0.60
    FFER
    -0.60
    POSITIVE LOGITS
    atories
    0.96
    atted
    0.95
    ulated
    0.93
    ulation
    0.92
    atism
    0.88
    rats
    0.88
     reform
    0.87
    ulate
    0.85
    ers
    0.83
    tarians
    0.79
    Act Density 0.030%

    No Known Activations