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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate attribution or source credit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pg
    -0.22
    wers
    -0.17
    quel
    -0.15
    lein
    -0.15
    ÑĢад
    -0.14
    اÙĬØ´
    -0.14
    lep
    -0.14
    ONENT
    -0.14
    ns
    -0.14
    ito
    -0.14
    POSITIVE LOGITS
    tesy
    0.18
    ably
    0.17
    ä¹İ
    0.17
     of
    0.16
    ately
    0.16
     Patri
    0.15
    inely
    0.15
    tae
    0.15
    arily
    0.14
    ously
    0.14
    Act Density 0.006%

    No Known Activations