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

    Neuronpedia

    INDEX
    Explanations

    function and method declarations or calls within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    u
    -0.62
    boxy
    -0.61
    -
    -0.59
    一
    -0.58
     &
    -0.58
    o
    -0.56
     int
    -0.56
     s
    -0.55
    t
    -0.54
     :
    -0.54
    POSITIVE LOGITS
     myſelf
    1.20
     himſelf
    1.17
    ſelf
    1.14
     themſelves
    1.13
     pleaſure
    1.12
     itſelf
    1.09
    ſelves
    1.07
    BibitemShut
    0.99
     leſs
    0.98
     Theſe
    0.97
    Act Density 0.043%

    No Known Activations