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

    Neuronpedia

    INDEX
    Explanations

    phrases involving large quantities or estimates, particularly the term "tens of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĮко
    -0.16
    gger
    -0.15
    chner
    -0.15
    پس
    -0.15
    ulace
    -0.15
    attles
    -0.15
    istine
    -0.14
    panies
    -0.14
    uito
    -0.14
    tek
    -0.14
    POSITIVE LOGITS
    ile
    0.20
    alar
    0.16
    ousands
    0.16
    OfWork
    0.16
    -of
    0.16
     thousands
    0.16
    acles
    0.16
     upon
    0.15
     strictly
    0.15
    ely
    0.14
    Act Density 0.006%

    No Known Activations