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

    Neuronpedia

    INDEX
    Explanations

    sections of text that focus on theoretical or speculative frameworks in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.15
     Majefty
    -1.07
     iſt
    -1.06
     themſelves
    -1.05
    ſelves
    -1.04
     myſelf
    -1.04
     Monfieur
    -1.01
    ſelf
    -1.01
     ſy
    -0.99
     Jefus
    -0.99
    POSITIVE LOGITS
    ,
    0.90
    .
    0.82
     p
    0.69
     
    0.65
    </strong>
    0.65
    ↵
    0.65
    <strong>
    0.65
    to
    0.65
     l
    0.64
     in
    0.64
    Act Density 0.132%

    No Known Activations