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

    Neuronpedia

    INDEX
    Explanations

    people's names or references to individuals

    oai_token-act-pair · gpt-3.5-turbo

    the letter "p" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.60
     GOODMAN
    -0.60
     divid
    -0.59
     lash
    -0.58
     Gleaming
    -0.54
     compe
    -0.54
     compounded
    -0.54
     Leilan
    -0.54
     bound
    -0.54
     juggling
    -0.53
    POSITIVE LOGITS
    olitan
    1.28
    ocalypse
    1.25
    isode
    1.19
    ulse
    1.19
    ilot
    1.12
    resents
    1.10
    ossible
    1.10
    ierre
    1.09
    redict
    1.07
    irit
    1.07
    Act Density 0.044%

    No Known Activations