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

    Neuronpedia

    INDEX
    Explanations

    phrases related to successful or impactful actions or events

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to success or achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fed
    -0.73
    ĨĴ
    -0.68
     Administ
    -0.67
    shown
    -0.64
    SPONSORED
    -0.62
    going
    -0.61
    uctor
    -0.61
    atus
    -0.60
    imens
    -0.60
    pired
    -0.59
    POSITIVE LOGITS
     stride
    0.92
     snag
    0.90
     iceberg
    0.83
     nail
    0.82
     hardest
    0.73
     plateau
    0.73
     nerve
    0.72
     accelerator
    0.71
     squarely
    0.71
    henko
    0.70
    Act Density 0.140%

    No Known Activations