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

    Neuronpedia

    INDEX
    Explanations

    discussions surrounding political controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bipartisan
    -0.16
    bias
    -0.16
    Bias
    -0.15
    ugo
    -0.15
     Bias
    -0.15
     biased
    -0.15
    .gov
    -0.14
    biased
    -0.14
     Paz
    -0.14
    ยà¸ģ
    -0.14
    POSITIVE LOGITS
     party
    0.22
     internal
    0.21
     intra
    0.20
    åĨħéĥ¨
    0.18
    .internal
    0.18
     Party
    0.17
    internal
    0.17
    306
    0.17
    Party
    0.17
    party
    0.16
    Act Density 0.138%

    No Known Activations