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

    Neuronpedia

    INDEX
    Explanations

    references to programming classes and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     your
    -0.16
     YOUR
    -0.15
     yourself
    -0.15
    your
    -0.15
    åĿ¡
    -0.15
     Saw
    -0.14
    ux
    -0.14
    лаÑĤ
    -0.14
    ço
    -0.14
    ãģ§ãģĹãĤĩãģĨ
    -0.14
    POSITIVE LOGITS
     certain
    0.16
    Certain
    0.16
     (~
    0.16
     Certain
    0.15
    aldo
    0.15
     roughly
    0.15
    occasion
    0.14
    æĺ¯æĪij
    0.14
    oui
    0.14
    ~↵
    0.14
    Act Density 0.140%

    No Known Activations