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

    Neuronpedia

    INDEX
    Explanations

    references to hidden fees and costs associated with financial transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mmo
    -0.16
    elman
    -0.15
    éĢł
    -0.14
    ohn
    -0.14
     vouchers
    -0.14
    ãĥ¼ãĥĪ
    -0.13
    à¸Ńà¸ŀ
    -0.13
     narrowing
    -0.13
    pek
    -0.13
    é
    -0.13
    POSITIVE LOGITS
     terms
    0.20
    /terms
    0.17
     Terms
    0.16
     hidden
    0.16
    hidden
    0.16
    terms
    0.15
     penalties
    0.15
     penal
    0.15
     rip
    0.15
     Hidden
    0.14
    Act Density 0.035%

    No Known Activations