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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "significant," particularly in contexts relating to importance or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ject
    -0.20
    erman
    -0.17
    orman
    -0.16
    ãģĦãģĨ
    -0.15
    å¼ı
    -0.15
    ican
    -0.15
    -centric
    -0.14
    bage
    -0.14
    uffer
    -0.14
    esian
    -0.14
    POSITIVE LOGITS
     amount
    0.23
     amounts
    0.23
     portion
    0.22
     portions
    0.22
    amount
    0.21
    /sign
    0.20
    ately
    0.20
     Portions
    0.19
     enough
    0.19
    LY
    0.18
    Act Density 0.034%

    No Known Activations