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

    Neuronpedia

    INDEX
    Explanations

    themes of loss and restriction related to choices and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grat
    -0.15
    abel
    -0.15
    Pont
    -0.15
     seg
    -0.14
    awi
    -0.14
    esk
    -0.14
    vit
    -0.14
    seg
    -0.14
    otel
    -0.14
    agh
    -0.14
    POSITIVE LOGITS
     future
    0.45
     forever
    0.43
    future
    0.40
     permanently
    0.30
     Future
    0.29
    æ°¸
    0.29
    以åIJİ
    0.29
    Future
    0.28
     Forever
    0.28
    æ°¸ä¹ħ
    0.27
    Act Density 0.268%

    No Known Activations