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

    Neuronpedia

    INDEX
    Explanations

    phrases that express a preference for improvement or advantage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duto
    -0.19
    meli
    -0.14
    cket
    -0.14
    SqlConnection
    -0.14
    ATO
    -0.14
    rades
    -0.14
    ORIZED
    -0.14
    atori
    -0.14
    hl
    -0.14
    uml
    -0.14
    POSITIVE LOGITS
     than
    0.24
    than
    0.20
    idge
    0.20
     THAN
    0.20
     Than
    0.19
    -than
    0.18
     вÑģего
    0.17
    ija
    0.17
    ymm
    0.16
    _than
    0.16
    Act Density 0.062%

    No Known Activations