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

    Neuronpedia

    INDEX
    Explanations

    timestamp-related markers or formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’
    -0.52
    .
    -0.51
     fibras
    -0.51
     \
    -0.49
     Miles
    -0.49
     dây
    -0.49
    ̬
    -0.49
     gyakor
    -0.48
     H
    -0.48
     ๆ
    -0.48
    POSITIVE LOGITS
     Majefty
    1.09
                   
    1.00
     ſy
    0.99
     perſon
    0.96
                       
    0.96
    +#+
    0.96
                             
    0.94
     themſelves
    0.93
     Inſ
    0.93
     ་་
    0.92
    Act Density 0.907%

    No Known Activations