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

    Neuronpedia

    INDEX
    Explanations

    references to authors and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __":
    -0.90
    __':
    -0.87
     FetchType
    -0.72
    __':
    -0.70
    Diwedd
    -0.69
    KommentareTeilen
    -0.66
    __":
    -0.65
    شهاد
    -0.65
    脚注の使い方
    -0.65
     تانيه
    -0.64
    POSITIVE LOGITS
     responsible
    0.63
     Diſ
    0.59
     Reſ
    0.57
     Majefty
    0.56
     Eſ
    0.56
    claimer
    0.56
     Anſ
    0.55
     Conſ
    0.55
    фикации
    0.54
     ſeveral
    0.54
    Act Density 0.425%

    No Known Activations