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

    Neuronpedia

    INDEX
    Explanations

    strong opinions or beliefs expressed by the author

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing personal opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    artney
    -0.83
    ategory
    -0.73
    clad
    -0.72
    =~=~
    -0.67
    announced
    -0.66
    agna
    -0.66
     flats
    -0.66
    eatured
    -0.66
    ueless
    -0.64
    inance
    -0.63
    POSITIVE LOGITS
    76561
    0.78
     saddened
    0.71
    onymous
    0.70
    ĸ
    0.69
     Chimera
    0.69
     strategically
    0.69
    asio
    0.68
    ^^^^
    0.67
     pse
    0.65
     capitals
    0.65
    Act Density 0.057%

    No Known Activations