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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating significance or meaning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egas
    -0.15
    -FIRST
    -0.15
    gate
    -0.15
    brtc
    -0.14
    аниÑĨ
    -0.14
    姿
    -0.14
    culus
    -0.14
    alars
    -0.14
    £p
    -0.14
    onas
    -0.14
    POSITIVE LOGITS
    ioned
    0.17
    0.17
    forth
    0.16
    fully
    0.16
     Matte
    0.15
    enan
    0.14
    ÏĥÏĦÏĮ
    0.14
    ãĥ¶
    0.14
     Freder
    0.14
    /do
    0.14
    Act Density 0.049%

    No Known Activations