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

    Neuronpedia

    INDEX
    Explanations

    words related to surpassing or going beyond limits or expectations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "beyond" or transcending limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ICAN
    -0.93
    pmwiki
    -0.76
     WATCHED
    -0.74
     Assass
    -0.68
    TIME
    -0.67
    ALLY
    -0.67
    ãĤ·ãĥ£
    -0.67
     Mehran
    -0.66
    enos
    -0.65
    è¦ļéĨĴ
    -0.65
    POSITIVE LOGITS
     comprehension
    0.85
    esis
    0.77
     bounds
    0.73
     reach
    0.73
    ordinary
    0.73
     Borders
    0.71
    iche
    0.71
    atos
    0.70
     Horizons
    0.69
     reaching
    0.68
    Act Density 0.024%

    No Known Activations