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

    Neuronpedia

    INDEX
    Explanations

    references to political dependence and relationships between countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.47
     pets
    -0.44
     pads
    -0.43
     EXPERIMENTAL
    -0.42
     lovingly
    -0.42
     hobbies
    -0.42
     costumbre
    -0.41
     experimente
    -0.41
     kids
    -0.40
     customizations
    -0.40
    POSITIVE LOGITS
     political
    0.69
     politically
    0.63
     geopolitical
    0.60
     politico
    0.60
    political
    0.57
     político
    0.56
     politic
    0.53
    Political
    0.52
     polity
    0.49
     destabili
    0.49
    Act Density 0.763%

    No Known Activations