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

    Neuronpedia

    INDEX
    Explanations

    references to political matters and complex social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agency
    -0.16
    610
    -0.15
    ([{
    -0.14
    /address
    -0.14
     Attention
    -0.14
     Architect
    -0.14
    .defer
    -0.13
    ancestor
    -0.13
    obot
    -0.13
    AXB
    -0.13
    POSITIVE LOGITS
     aff
    0.83
     Aff
    0.79
    aff
    0.79
    Aff
    0.73
     AFF
    0.68
    -aff
    0.68
    'aff
    0.62
    _aff
    0.60
     af
    0.60
    AFF
    0.57
    Act Density 0.090%

    No Known Activations