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

    Neuronpedia

    INDEX
    Explanations

    technical terms and specific references related to physical equations and scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.77
      
    -0.63
     “
    -0.63
     .
    -0.62
    er
    -0.61
    {'
    -0.61
    </i>
    -0.61
    u
    -0.61
    awtextra
    -0.60
    ↵
    -0.59
    POSITIVE LOGITS
     myſelf
    1.24
     fhall
    1.14
     Theſe
    1.14
     Majefty
    1.14
     Efq
    1.13
     poffe
    1.12
     himſelf
    1.09
     Jefus
    1.09
     ſta
    1.07
     ſhall
    1.05
    Act Density 0.852%

    No Known Activations