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

    Neuronpedia

    INDEX
    Explanations

    instances of expressions related to personal reflections and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nemonic
    -0.16
    aunch
    -0.14
    nothrow
    -0.14
    ottes
    -0.14
    edBy
    -0.13
    otti
    -0.13
     зави
    -0.13
    Äļ
    -0.13
    oldown
    -0.13
    ICLES
    -0.13
    POSITIVE LOGITS
     hence
    0.16
    orm
    0.16
    it
    0.15
    oin
    0.15
    奴
    0.15
    amil
    0.14
    defs
    0.14
    arent
    0.14
    ket
    0.14
     Monad
    0.14
    Act Density 0.247%

    No Known Activations