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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statements or comments made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and numeric indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.72
     curated
    -0.68
     domestically
    -0.67
     darn
    -0.65
     affili
    -0.65
     endeavors
    -0.64
     endeavor
    -0.64
    hemoth
    -0.63
     technologically
    -0.63
     homebrew
    -0.62
    POSITIVE LOGITS
    However
    1.12
    Meanwhile
    1.09
    Shape
    1.00
    Earlier
    1.00
    Despite
    0.98
    Nevertheless
    0.96
    Asked
    0.93
    Labour
    0.92
    Discuss
    0.91
    Relations
    0.91
    Act Density 0.409%

    No Known Activations