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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols associated with formatting or markup in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    work
    -0.17
     mere
    -0.15
    ces
    -0.14
    loomberg
    -0.14
    conto
    -0.14
     li
    -0.14
    \Blueprint
    -0.14
    æ¿Ł
    -0.14
    оÑĩной
    -0.13
     tá»
    -0.13
    POSITIVE LOGITS
    redi
    0.17
    jom
    0.16
    ifu
    0.16
    ucher
    0.16
    iswa
    0.15
    LOTS
    0.15
    ĶåĽŀ
    0.14
    .ga
    0.14
    oyer
    0.14
    IRA
    0.14
    Act Density 0.006%

    No Known Activations