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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating recent actions or completed tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ£ļ
    -0.20
    uder
    -0.15
    ibold
    -0.15
    aign
    -0.14
    vailable
    -0.14
    agli
    -0.13
    亮
    -0.13
    EDITOR
    -0.13
     slov
    -0.13
     Bren
    -0.13
    POSITIVE LOGITS
    ifi
    0.17
    adar
    0.16
    pac
    0.15
    ifiable
    0.14
    ify
    0.14
     Heroes
    0.14
    inta
    0.14
    عب
    0.14
    geh
    0.14
     Rossi
    0.13
    Act Density 0.070%

    No Known Activations