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

    Neuronpedia

    INDEX
    Explanations

    words related to legal, political, and governmental activities

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings or punctuation at the end of sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nightly
    -0.72
     casc
    -0.72
     ability
    -0.69
     continuous
    -0.68
     dra
    -0.67
     weekly
    -0.67
     reflex
    -0.67
     sil
    -0.67
     fluct
    -0.66
     waterfall
    -0.66
    POSITIVE LOGITS
    SPONSORED
    1.47
    WASHINGTON
    1.39
    ADVERTISEMENT
    1.32
    Interested
    1.31
    Advertisement
    1.30
    Britain
    1.28
    Officials
    1.27
    They
    1.27
    Instead
    1.26
    According
    1.25
    Act Density 0.424%

    No Known Activations