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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "this" to highlight specific concepts or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aws
    -0.17
    tier
    -0.15
    ton
    -0.15
    minus
    -0.14
    sonian
    -0.14
     sn
    -0.14
    164
    -0.14
    tej
    -0.14
    lius
    -0.14
     sure
    -0.14
    POSITIVE LOGITS
    irror
    0.15
    pson
    0.15
    _DLL
    0.15
    uger
    0.15
    avana
    0.15
    orris
    0.15
    averse
    0.14
    ınızda
    0.14
    _Module
    0.13
    Ĭ
    0.13
    Act Density 0.014%

    No Known Activations