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

    Neuronpedia

    INDEX
    Explanations

    words related to financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    references to "checks" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hots
    -0.86
    wcs
    -0.73
    æĺ
    -0.69
     Norn
    -0.68
    âĸ¬
    -0.63
     Argon
    -0.63
    BLE
    -0.63
    ãĥĩ
    -0.62
     solitary
    -0.61
    cipled
    -0.60
    POSITIVE LOGITS
    boxes
    1.04
    lists
    1.04
    er
    1.00
    enhagen
    1.00
    book
    0.94
    etts
    0.94
    strap
    0.94
    iard
    0.93
    box
    0.91
    list
    0.89
    Act Density 0.038%

    No Known Activations