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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Apparently
    -1.02
     apparently
    -0.99
     supuestamente
    -0.98
     supposedly
    -0.98
    Apparently
    -0.98
     seemingly
    -0.97
    apparently
    -0.96
     allegedly
    -0.95
     schein
    -0.87
     reportedly
    -0.82
    POSITIVE LOGITS
     overall
    0.77
     mostly
    0.74
     mainly
    0.74
     fair
    0.73
     ExecuteAsync
    0.71
     summed
    0.70
    Mostly
    0.70
     Mostly
    0.69
     fairest
    0.68
    overall
    0.68
    Act Density 0.256%

    No Known Activations