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

    Neuronpedia

    INDEX
    Explanations

    words related to sudden changes or surprising events

    oai_token-act-pair · gpt-3.5-turbo

    the word "suddenly" and its variations, indicating unexpected changes or shifts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.83
    ippi
    -0.80
    artisan
    -0.69
    orem
    -0.69
    atu
    -0.67
    icion
    -0.66
    orously
    -0.65
    fman
    -0.64
    orius
    -0.63
    rf
    -0.62
    POSITIVE LOGITS
    aneously
    0.95
     burst
    0.92
     vanish
    0.89
     disappear
    0.89
     suddenly
    0.87
     bursts
    0.77
     realised
    0.73
     abruptly
    0.72
     earthqu
    0.70
     swoop
    0.70
    Act Density 0.014%

    No Known Activations