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

    Neuronpedia

    INDEX
    Explanations

    tags and formatting indicators used in markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.71
    ↵
    -0.55
    ↵↵
    -0.55
    nek
    -0.53
    sek
    -0.52
    uri
    -0.51
    ren
    -0.50
    uta
    -0.48
    pec
    -0.48
     pe
    -0.47
    POSITIVE LOGITS
     Majefty
    1.71
     Jefus
    1.42
     pleaſure
    1.41
     Efq
    1.41
     myſelf
    1.40
     fubject
    1.40
     ſeveral
    1.35
     Houſe
    1.33
     itſelf
    1.30
     purpoſe
    1.30
    Act Density 0.038%

    No Known Activations