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

    Neuronpedia

    INDEX
    Explanations

    citing or referencing legal or formal regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.80
     a
    -0.77
     so
    -0.76
     the
    -0.75
     or
    -0.75
     at
    -0.72
     as
    -0.71
     no
    -0.68
     in
    -0.64
     is
    -0.62
    POSITIVE LOGITS
     Efq
    1.11
     myſelf
    1.10
     itſelf
    1.08
     Shakspeare
    1.02
     himſelf
    1.02
     تضيفلها
    1.01
     Monfieur
    0.99
     snippetHide
    0.99
    EDEFAULT
    0.98
     NSCoder
    0.96
    Act Density 0.022%

    No Known Activations