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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tasks and completion

    oai_token-act-pair · gpt-3.5-turbo

    sentences and punctuation marks that indicate concluding statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ury
    -0.76
     swinging
    -0.74
     veter
    -0.69
    alian
    -0.68
    jug
    -0.66
     submar
    -0.65
    tnc
    -0.62
     conservation
    -0.61
     empt
    -0.61
     casting
    -0.61
    POSITIVE LOGITS
     [+
    1.02
     Logged
    0.89
     Conclusion
    0.88
     Recommend
    0.86
     Beware
    0.82
     References
    0.81
     Learns
    0.80
     Compare
    0.78
     Lack
    0.77
     Claims
    0.76
    Act Density 0.082%

    No Known Activations