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

    Neuronpedia

    INDEX
    Explanations

    key terms and statistics related to scientific research and findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aho
    -0.16
    eka
    -0.15
    oka
    -0.14
    zik
    -0.14
     neither
    -0.14
     background
    -0.14
    rán
    -0.14
    iao
    -0.14
    mouseup
    -0.14
     raft
    -0.13
    POSITIVE LOGITS
     most
    0.21
     MOST
    0.21
    MOST
    0.21
     meisten
    0.18
    most
    0.18
     majority
    0.16
    UNK
    0.16
    major
    0.16
     vÄĽtÅ¡
    0.16
     overwhelmingly
    0.15
    Act Density 0.224%

    No Known Activations