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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the presentation or outlining of information and terms in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ิà¸Īารà¸ĵ
    -0.15
    ncia
    -0.15
     BA
    -0.14
    anke
    -0.14
    еп
    -0.14
    à¹ĭ
    -0.14
    -delay
    -0.14
    ë°±
    -0.14
    vens
    -0.13
    ìĿµ
    -0.13
    POSITIVE LOGITS
     forth
    0.26
    forth
    0.22
    anda
    0.17
    lement
    0.16
    icer
    0.15
    emer
    0.15
    von
    0.14
    uer
    0.14
    NOP
    0.14
    icipation
    0.14
    Act Density 0.013%

    No Known Activations