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

    Neuronpedia

    INDEX
    Explanations

    the word "tipping" or phrases related to tipping points

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tipping" and its variations, indicating a focus on tipping points or tipping as a concept

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ires
    -0.80
    izes
    -0.77
    Interstitial
    -0.73
     Manual
    -0.72
     NCT
    -0.71
    EVA
    -0.70
    clamation
    -0.68
    oved
    -0.67
    semble
    -0.67
    76561
    -0.67
    POSITIVE LOGITS
     tipped
    1.27
     tipping
    1.23
     iceberg
    0.99
     tip
    0.93
    tip
    0.85
    ratulations
    0.83
    raviolet
    0.83
     iod
    0.80
     waiter
    0.77
     waitress
    0.77
    Act Density 0.013%

    No Known Activations