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

    Neuronpedia

    INDEX
    Explanations

    references to political or social reforms

    oai_token-act-pair · gpt-3.5-turbo

    references to reform-related topics or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gaard
    -0.65
     infer
    -0.62
     McA
    -0.61
    ordon
    -0.61
     Saud
    -0.60
    ammy
    -0.60
    DoS
    -0.59
     Bryant
    -0.59
     Coulter
    -0.59
     Starg
    -0.58
    POSITIVE LOGITS
    ulation
    1.19
    atories
    1.17
    atted
    1.16
    ers
    1.16
    ulated
    1.16
    ulatory
    1.11
    ulations
    1.11
    er
    1.04
    rats
    1.01
    ulating
    0.96
    Act Density 0.041%

    No Known Activations