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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or comparison in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Necesito
    -0.59
    InMillis
    -0.57
     StatefulWidget
    -0.56
    them
    -0.55
    ADT
    -0.52
     Siamese
    -0.52
     META
    -0.52
     Scip
    -0.51
    eurovision
    -0.51
    ########.
    -0.50
    POSITIVE LOGITS
    Whereas
    0.98
     Whereas
    0.95
     whereas
    0.93
    whereas
    0.87
    Meanwhile
    0.82
    omiast
    0.82
     Meanwhile
    0.82
     meanwhile
    0.79
    一方で
    0.76
     conversely
    0.75
    Act Density 0.274%

    No Known Activations