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

    Neuronpedia

    INDEX
    Explanations

    mentions of conflicts or disruptive events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks that indicate the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quir
    -0.89
     lookout
    -0.85
     wire
    -0.85
     carbohyd
    -0.81
     netted
    -0.79
     star
    -0.79
     paddle
    -0.77
     testing
    -0.76
     waterfall
    -0.76
     unidentified
    -0.75
    POSITIVE LOGITS
    Consider
    1.73
    Yet
    1.70
    Moreover
    1.69
    Thus
    1.63
    Advertisements
    1.62
    Indeed
    1.61
    SPONSORED
    1.60
    Therefore
    1.59
    Political
    1.59
    Nevertheless
    1.57
    Act Density 0.367%

    No Known Activations