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

    Neuronpedia

    INDEX
    Explanations

    references to political controversies and tactics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    577
    -0.19
    uitka
    -0.17
    immel
    -0.15
    mma
    -0.15
    iculos
    -0.15
     ev
    -0.15
    yna
    -0.15
     separat
    -0.14
     bols
    -0.14
    ÏĥÏĦα
    -0.14
    POSITIVE LOGITS
     Establishment
    0.17
     establishment
    0.16
    ialis
    0.15
    CHANT
    0.15
     Bradley
    0.15
    _lock
    0.15
    -serving
    0.15
    oplay
    0.14
    uci
    0.14
    VRT
    0.14
    Act Density 0.161%

    No Known Activations