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

    Neuronpedia

    INDEX
    Explanations

    mentions of politicians and political engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Caps
    -0.14
    rix
    -0.14
    bor
    -0.14
    lak
    -0.14
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.14
    ootball
    -0.14
    odia
    -0.13
    ady
    -0.13
    igin
    -0.13
    .vertx
    -0.13
    POSITIVE LOGITS
    esch
    0.16
    Å¡k
    0.16
    sten
    0.14
     detain
    0.14
    ortal
    0.14
     jet
    0.14
    omer
    0.14
     Rooms
    0.14
    ter
    0.14
    #ga
    0.14
    Act Density 0.009%

    No Known Activations