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

    Neuronpedia

    INDEX
    Explanations

    the concept of significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erman
    -0.16
    ucha
    -0.16
    oq
    -0.15
    o
    -0.15
    orman
    -0.14
    ject
    -0.14
     suff
    -0.14
    kir
    -0.14
    edo
    -0.14
    ys
    -0.14
    POSITIVE LOGITS
     amounts
    0.20
    ately
    0.19
    /sign
    0.19
    amount
    0.19
     amount
    0.18
    pants
    0.17
    ely
    0.17
     sayıda
    0.17
    itarian
    0.17
    ively
    0.17
    Act Density 0.033%

    No Known Activations