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

    Neuronpedia

    INDEX
    Explanations

    references to ranking, competition, and performance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /
    -0.65
     or
    -0.63
     (
    -0.62
    ↵↵
    -0.56
     [
    -0.52
     /
    -0.52
     and
    -0.51
     
    -0.48
     &
    -0.48
    <eos>
    -0.46
    POSITIVE LOGITS
     Majefty
    1.35
    ſelf
    1.29
     Monfieur
    1.26
     myſelf
    1.18
     doubtnut
    1.16
     ſeveral
    1.14
     ―――――
    1.12
     themſelves
    1.11
     Jefus
    1.11
     Anſ
    1.10
    Act Density 0.348%

    No Known Activations