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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific individuals and references to political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __':
    -0.91
     onOptions
    -0.83
    __":
    -0.75
    GeneratedMessage
    -0.74
    </caption>
    -0.70
    SuspendLayout
    -0.67
    ArgumentParser
    -0.67
     onBind
    -0.66
    BeginInit
    -0.65
     StringField
    -0.63
    POSITIVE LOGITS
     coronavirus
    0.95
     Coronavirus
    0.92
    Coronavirus
    0.92
    coronavirus
    0.90
     quarantine
    0.85
     Pandemic
    0.77
     pandemic
    0.76
     corona
    0.75
    Corona
    0.74
     lockdown
    0.74
    Act Density 0.087%

    No Known Activations