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

    Neuronpedia

    INDEX
    Explanations

    mathematical and statistical notation and terms in formal writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.87
    enumi
    -0.81
     />;
    -0.74
    Hentet
    -0.71
    Rhestr
    -0.70
    .",
    -0.69
    . 
    -0.69
       
    -0.68
    ględ
    -0.68
    ]]:
    -0.68
    POSITIVE LOGITS
     delà
    0.95
     didalam
    0.94
     coté
    0.93
     تانيه
    0.93
     diatas
    0.92
    luß
    0.90
     perchè
    0.83
    の為
    0.79
     میتوان
    0.79
     للمعارف
    0.78
    Act Density 5.060%

    No Known Activations