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

    Neuronpedia

    INDEX
    Explanations

    terms related to quantifiable measures or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    аÑĢÑĩ
    -0.16
    Coupon
    -0.15
    baugh
    -0.15
    imiento
    -0.15
     Tick
    -0.15
    sburg
    -0.15
     Behind
    -0.14
     DÃŃky
    -0.14
    sk
    -0.14
    beh
    -0.14
    POSITIVE LOGITS
    件
    0.15
    wayne
    0.14
    ffen
    0.14
    ITH
    0.14
    icare
    0.14
    lets
    0.13
    ırak
    0.13
    AME
    0.13
    issions
    0.13
    .favorite
    0.13
    Act Density 0.002%

    No Known Activations