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

    Neuronpedia

    INDEX
    Explanations

    high numerical values, particularly those associated with prices or costs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    }")]
    -0.88
    SequentialGroup
    -0.77
     nahilalakip
    -0.69
     surla
    -0.69
    存于互联网档案馆
    -0.68
    /***/
    -0.65
    enumerate
    -0.65
    Hauptartikel
    -0.65
    multirow
    -0.64
    \{\\
    -0.63
    POSITIVE LOGITS
     Majefty
    0.83
     itſelf
    0.83
     ſhall
    0.81
     leſs
    0.79
     NDEBUG
    0.77
     themſelves
    0.77
     himſelf
    0.76
     ſee
    0.75
     raiſ
    0.73
     reaſon
    0.73
    Act Density 0.104%

    No Known Activations