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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating new beginnings or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     backtrack
    -0.15
     antid
    -0.15
     nod
    -0.14
    compan
    -0.14
    §
    -0.14
    edu
    -0.14
    åĢ
    -0.14
    aload
    -0.13
    queda
    -0.13
     doInBackground
    -0.13
    POSITIVE LOGITS
    .jquery
    0.17
    /new
    0.16
    sworth
    0.15
    inez
    0.15
    umann
    0.14
     ways
    0.14
    velle
    0.14
     lạ
    0.14
    itos
    0.14
    serrat
    0.14
    Act Density 0.121%

    No Known Activations