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

    Neuronpedia

    INDEX
    Explanations

    references to political opposition in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eches
    -0.56
    indrical
    -0.56
    ampton
    -0.53
    lasz
    -0.51
     Trag
    -0.51
    carbons
    -0.50
    ámenes
    -0.50
    Tils
    -0.50
    õi
    -0.50
    prudence
    -0.49
    POSITIVE LOGITS
     against
    0.94
    against
    0.87
    Against
    0.78
     Against
    0.77
     AGAINST
    0.74
     forces
    0.67
    IndentedString
    0.65
     Réponses
    0.65
    complexContent
    0.62
     pinulongan
    0.62
    Act Density 0.301%

    No Known Activations