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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and programming code

    oai_token-act-pair · gpt-3.5-turbo

    mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heit
    -0.80
     spoiler
    -0.71
     Droid
    -0.60
    bable
    -0.59
    Ń·
    -0.58
     Pandora
    -0.57
    metic
    -0.56
    sle
    -0.55
    adesh
    -0.55
     crate
    -0.55
    POSITIVE LOGITS
    ================================================================
    0.63
    ovember
    0.62
    arthed
    0.61
     Tong
    0.60
    Topics
    0.59
    MpServer
    0.58
    _{
    0.58
    arge
    0.58
    otyp
    0.57
    xit
    0.56
    Act Density 0.228%

    No Known Activations