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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and their actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InBackground
    -0.18
    uada
    -0.15
     GUIDE
    -0.15
     Reporting
    -0.14
    çIJ³
    -0.14
    _representation
    -0.14
    .qual
    -0.14
    VICE
    -0.13
    isyon
    -0.13
    arem
    -0.13
    POSITIVE LOGITS
     piv
    0.18
     preview
    0.18
    λÏī
    0.16
     jab
    0.16
     duck
    0.16
     malign
    0.15
     riff
    0.15
     again
    0.15
     spar
    0.15
     deliver
    0.15
    Act Density 0.110%

    No Known Activations