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

    Neuronpedia

    INDEX
    Explanations

    terms or references related to subscriptions or subsidization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thers
    -0.19
    eyer
    -0.19
    sko
    -0.17
    ebra
    -0.16
    toList
    -0.15
    to
    -0.15
    à¸Ńà¹Ģร
    -0.14
    icken
    -0.14
    nowled
    -0.14
    oters
    -0.14
    POSITIVE LOGITS
    istence
    0.31
    iding
    0.26
    urface
    0.26
    idence
    0.24
     subs
    0.24
    ides
    0.21
    istent
    0.21
    idi
    0.21
    ided
    0.21
    istance
    0.20
    Act Density 0.005%

    No Known Activations