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

    Neuronpedia

    INDEX
    Explanations

    sudden events or changes

    oai_token-act-pair · gpt-3.5-turbo

    instances of abrupt or unexpected events described in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.80
    ippi
    -0.73
    itary
    -0.70
    rf
    -0.69
    gard
    -0.69
    alf
    -0.68
    iago
    -0.67
    rer
    -0.66
    Eva
    -0.66
    headers
    -0.65
    POSITIVE LOGITS
     suddenly
    1.05
     burst
    0.96
     vanish
    0.92
     abruptly
    0.92
     disappear
    0.86
    aneously
    0.84
     bursts
    0.77
     earthqu
    0.76
     mysteriously
    0.76
     disappears
    0.76
    Act Density 0.008%

    No Known Activations