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

    Neuronpedia

    INDEX
    Explanations

    emphasis on certain keywords or phrases, possibly related to opinions or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istic
    -0.31
     ,
    -0.30
     the
    -0.28
     of
    -0.25
    匿名使用者
    -0.24
    1
    -0.23
    发表于
    -0.23
    ,
    -0.23
    ----------------
    -0.23
     如
    -0.23
    POSITIVE LOGITS
     nahilalakip
    0.97
    AccessorTable
    0.89
    :✨
    0.89
    featureID
    0.85
     propOrder
    0.82
    niſſe
    0.82
     müſſen
    0.78
    ésultats
    0.77
     ſehr
    0.77
    routeProvider
    0.76
    Act Density 0.287%

    No Known Activations