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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and phrases indicating possibility or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     we
    -0.66
     We
    -0.59
     who
    -0.58
     I
    -0.57
     rahat
    -0.56
     byli
    -0.50
     belajar
    -0.49
     Jorg
    -0.48
     enjoy
    -0.48
     know
    -0.48
    POSITIVE LOGITS
     itſelf
    1.19
    Билгалдахарш
    0.88
    SharedDtor
    0.87
     gyhoeddwyd
    0.87
     unknownFields
    0.86
    رشف
    0.81
    السكان
    0.78
     tartalomajánló
    0.78
     Reſ
    0.78
    MessageOf
    0.78
    Act Density 0.608%

    No Known Activations