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

    Neuronpedia

    INDEX
    Explanations

    phrases related to "first" occurrences or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignon
    -0.18
    echa
    -0.18
    ega
    -0.15
    ide
    -0.15
    borg
    -0.14
    inati
    -0.14
    ides
    -0.14
    uga
    -0.14
    ignant
    -0.14
     Bombay
    -0.13
    POSITIVE LOGITS
     æij
    0.15
    teri
    0.14
    ductive
    0.14
    orgh
    0.14
    ibur
    0.14
    metrics
    0.14
     BÄĽ
    0.14
    -thumbnails
    0.14
    erta
    0.13
    ricia
    0.13
    Act Density 0.059%

    No Known Activations