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

    Neuronpedia

    INDEX
    Explanations

    narrative sequences involving interactions between people

    oai_token-act-pair · gpt-3.5-turbo

    sudden, unexpected events or encounters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.74
     redes
    -0.71
    vre
    -0.70
     satisf
    -0.70
    unal
    -0.69
    utterstock
    -0.69
     merits
    -0.68
     Profit
    -0.65
     independ
    -0.65
    Correct
    -0.64
    POSITIVE LOGITS
     backstage
    0.92
     [
    0.90
     ['
    0.86
     yelling
    0.85
     Coach
    0.84
     somebody
    0.83
     uh
    0.82
     saying
    0.81
     fuckin
    0.79
     wanna
    0.79
    Act Density 0.555%

    No Known Activations