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

    Neuronpedia

    INDEX
    Explanations

    expressions related to personal beliefs and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /from
    -0.18
     itself
    -0.17
    /on
    -0.15
     etc
    -0.15
    -либо
    -0.14
     another
    -0.14
    one
    -0.14
    another
    -0.14
     its
    -0.14
     some
    -0.13
    POSITIVE LOGITS
    (ed
    0.20
    çļĦæĺ¯
    0.17
     pupper
    0.16
     wiÄĻc
    0.16
     donc
    0.15
    ardım
    0.15
    AFX
    0.15
     onDataChange
    0.14
    inha
    0.14
    lemn
    0.14
    Act Density 1.916%

    No Known Activations