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

    Neuronpedia

    INDEX
    Explanations

    questions that inquire about methods or ways to accomplish tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adora
    -0.17
    emd
    -0.15
    nova
    -0.15
    -strokes
    -0.14
    urgy
    -0.14
    undy
    -0.14
    หมาย
    -0.14
     ÎĴαÏĥ
    -0.14
     برابر
    -0.14
    educt
    -0.14
    POSITIVE LOGITS
    -to
    0.28
    itzer
    0.24
    dy
    0.23
    beit
    0.21
    to
    0.20
    -t
    0.20
     many
    0.20
    /
    0.20
    arde
    0.18
    -To
    0.17
    Act Density 0.041%

    No Known Activations