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

    Neuronpedia

    INDEX
    Explanations

    words related to checks being written, received, or cashed

    oai_token-act-pair · gpt-3.5-turbo

    references to financial transactions or checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hots
    -0.81
     Argon
    -0.72
    addons
    -0.69
    wcs
    -0.68
    LOD
    -0.64
    ¥µ
    -0.62
    âĸ¬
    -0.62
    GGGGGGGG
    -0.62
    ————————
    -0.62
    SAY
    -0.62
    POSITIVE LOGITS
    etts
    1.01
    enhagen
    0.99
    boxes
    0.90
    rolled
    0.88
    engers
    0.84
    ariat
    0.84
    bags
    0.83
    er
    0.81
    rolling
    0.80
    lists
    0.80
    Act Density 0.016%

    No Known Activations