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

    Neuronpedia

    INDEX
    Explanations

    expressions that highlight individual qualities or talents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     understatement
    -0.47
     
    -0.44
     quatre
    -0.42
     négy
    -0.41
    Jegyzetek
    -0.41
    ,
    -0.41
     vier
    -0.40
     “
    -0.40
     جمه
    -0.39
    ทร
    -0.39
    POSITIVE LOGITS
    )");
    0.90
    ſelf
    0.88
     Anſ
    0.87
     Reſ
    0.87
     дописавши
    0.85
     ſeveral
    0.85
    kloped
    0.83
     Forumite
    0.82
     Diſ
    0.82
     Conſ
    0.82
    Act Density 0.033%

    No Known Activations