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

    Neuronpedia

    INDEX
    Explanations

    specific references to actions or movements related to direction or positioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     perc
    -0.15
     naughty
    -0.15
    tributes
    -0.15
    )))),
    -0.15
     dread
    -0.14
    ģn
    -0.14
    ibrary
    -0.14
     dear
    -0.14
     cannot
    -0.13
    ÙıÙħ
    -0.13
    POSITIVE LOGITS
    reet
    0.15
    itizen
    0.15
    neys
    0.15
    untime
    0.14
    habi
    0.14
     dinh
    0.14
    askell
    0.14
    .ImageAlign
    0.14
    ancies
    0.14
    anik
    0.14
    Act Density 0.001%

    No Known Activations