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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pendiente
    -0.70
    children
    -0.67
    pend
    -0.65
     Zust
    -0.64
     Eme
    -0.64
    estrian
    -0.64
     Children
    -0.62
     bint
    -0.61
     TSS
    -0.61
    Eme
    -0.61
    POSITIVE LOGITS
     Ratios
    1.17
     ratios
    1.14
     CURIAM
    1.03
     RATIO
    0.97
    ratios
    0.97
     Segura
    0.95
     Sura
    0.94
    djangoproject
    0.93
     Balboa
    0.92
     Ratio
    0.92
    Act Density 0.122%

    No Known Activations