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

    Neuronpedia

    INDEX
    Explanations

    words indicating a range or variation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe a variety or range of subjects or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertisement
    -0.81
    IDA
    -0.79
    mit
    -0.78
    scape
    -0.72
    wards
    -0.71
    si
    -0.71
    driving
    -0.71
    bal
    -0.71
    eon
    -0.71
    Gold
    -0.66
    POSITIVE LOGITS
     ranging
    1.05
     ranges
    1.00
     ranged
    0.88
     range
    0.82
    range
    0.75
    ranging
    0.72
     lengths
    0.71
    ãĤ¤ãĥĪ
    0.70
     Luxem
    0.70
     spans
    0.66
    Act Density 0.011%

    No Known Activations