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

    Neuronpedia

    INDEX
    Explanations

    words related to legislation and government actions

    oai_token-act-pair · gpt-3.5-turbo

    sections of text with numerical or measurement references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     knockout
    -0.74
     mushroom
    -0.74
     reserve
    -0.73
     fancy
    -0.73
     endeavour
    -0.72
     coral
    -0.72
     civilisation
    -0.72
     spitting
    -0.72
     mint
    -0.71
     organising
    -0.71
    POSITIVE LOGITS
    âĢ
    1.97
    ADVERTISEMENT
    1.78
    Advertisement
    1.74
    âĸł
    1.72
    >>>
    1.69
    âĸº
    1.67
    âĹı
    1.65
    **
    1.57
    »
    1.57
    ***
    1.57
    Act Density 0.446%

    No Known Activations