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

    Neuronpedia

    INDEX
    Explanations

    numerical values followed by city names and dollar amounts

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and financial data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ihad
    -0.63
     anat
    -0.61
    andestine
    -0.57
    îĢ
    -0.57
     pen
    -0.56
    ÄŁ
    -0.56
     minds
    -0.56
    tein
    -0.56
     ·
    -0.56
     regul
    -0.56
    POSITIVE LOGITS
    ा
    0.65
    495
    0.61
    bis
    0.59
     Fury
    0.55
     Recap
    0.55
    åħī
    0.55
    nesia
    0.54
    à¤
    0.53
     Fairy
    0.53
     Darius
    0.53
    Act Density 0.253%

    No Known Activations