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

    Neuronpedia

    INDEX
    Explanations

    references to government actions and political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pace
    -0.16
    Äįné
    -0.15
    abbo
    -0.15
    otton
    -0.15
    alars
    -0.14
     ç¦
    -0.14
     Bayer
    -0.14
    ürger
    -0.14
    urbed
    -0.14
    PLUGIN
    -0.14
    POSITIVE LOGITS
     coalition
    0.29
     formation
    0.26
     government
    0.26
     coal
    0.25
     Formation
    0.24
    coal
    0.24
     Prime
    0.23
     formed
    0.22
     Coal
    0.22
     Coalition
    0.22
    Act Density 0.067%

    No Known Activations