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

    Neuronpedia

    INDEX
    Explanations

    text snippets indicating a plan or action to address something in the future

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "later."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.83
    ³³³³³³³³³³³³³³³³
    -0.69
    Merit
    -0.68
    PORT
    -0.66
    ³³³³³³³³
    -0.66
    efe
    -0.63
    advertisement
    -0.62
    Pri
    -0.61
    HY
    -0.61
    waukee
    -0.60
    POSITIVE LOGITS
    ally
    1.12
     generations
    0.95
    iations
    0.94
    etheless
    0.92
     iterations
    0.90
     stages
    0.88
    ality
    0.87
     phases
    0.85
    iation
    0.84
     installments
    0.82
    Act Density 0.040%

    No Known Activations