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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating quantities or degrees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ic
    -0.16
     sp
    -0.16
    atu
    -0.15
    atat
    -0.14
    ult
    -0.14
    ukt
    -0.14
     (<
    -0.14
    cq
    -0.14
    713
    -0.14
    668
    -0.13
    POSITIVE LOGITS
    kker
    0.18
    ocom
    0.15
    ertino
    0.15
    लत
    0.15
    ze
    0.14
    edor
    0.14
    ofire
    0.14
    ril
    0.14
    SqlParameter
    0.14
    ORIGINAL
    0.13
    Act Density 0.022%

    No Known Activations