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

    Neuronpedia

    INDEX
    Explanations

    expressions related to statistical results and their presentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Viitteet
    -0.69
    ijnt
    -0.52
    ="#"><
    -0.49
    ServiceModel
    -0.49
     verwij
    -0.48
    say
    -0.46
     tekem
    -0.45
    Say
    -0.45
    principalTable
    -0.44
     conosci
    -0.44
    POSITIVE LOGITS
     summarized
    0.89
     illustrated
    0.87
     shown
    0.85
     summarised
    0.78
     explained
    0.78
     presented
    0.77
     depicted
    0.76
     given
    0.70
     detailed
    0.68
     described
    0.67
    Act Density 0.974%

    No Known Activations