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

    Neuronpedia

    INDEX
    Explanations

    words related to sudden events or actions

    oai_token-act-pair · gpt-3.5-turbo

    significant moments involving sudden changes or unexpected events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olicy
    -0.85
    exempt
    -0.78
    redit
    -0.75
    ategic
    -0.75
     agre
    -0.74
    ©¶æ¥µ
    -0.74
    mercial
    -0.73
    perate
    -0.72
    ropolitan
    -0.71
    arta
    -0.71
    POSITIVE LOGITS
     flashes
    1.11
     glances
    1.09
     moments
    1.06
     laughter
    1.06
     blinking
    0.97
     uttered
    0.96
     sudden
    0.95
     glimps
    0.94
     words
    0.94
     whiff
    0.93
    Act Density 0.909%

    No Known Activations