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

    Neuronpedia

    INDEX
    Explanations

    different forms of articles and prepositions in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -1.32
     Monfieur
    -1.25
     Chriftian
    -1.24
     itſelf
    -1.23
     purpoſe
    -1.22
     Majefty
    -1.21
     Houſe
    -1.20
     pleaſure
    -1.20
     ſche
    -1.19
     raiſ
    -1.18
    POSITIVE LOGITS
     same
    1.12
     most
    1.03
     last
    0.95
     
    0.92
     “
    0.91
     latter
    0.89
     "
    0.85
     final
    0.84
     entire
    0.84
     new
    0.83
    Act Density 0.015%

    No Known Activations